@article{ author = {Kazemitabar, Seyed Javad and Shahbazzadeh, Maji}, title = {Stock Market Fraud Detection, A Probabilistic Approach}, abstract ={In order to have a fair market condition, it is crucial that regulators continuously monitor the stock market for possible fraud and market manipulation. There are many types of fraudulent activities defined in this context. In our paper we will be focusing on "front running". According to Association of Certified Fraud Examiners, front running is a form of insider information and thus is very difficult to detect. Front running is committed by brokerage firm employees when they are informed of a customer's large transaction request that could potentially change the price by a substantial amount. The fraudster then places his own order before that of the customer to enjoy the low price. Once the customer's order is placed and the prices are increased he will sell his shares and makes profit. Detecting front running requires not only statistical analysis, but also domain knowledge and filtering. For example, the authors learned from Tehran's Over The Counter (OTC) stock exchange officials that fraudsters may use cover-up accounts to hide their identity. Or they could delay selling their shares to avoid suspicion.  Before being able to present the case to a prosecutor, the analyst needs to determine whether predication exists. Only then, can he start testing and interpreting the collected data. Due to large volume of daily trades, the analyst needs to rely on computer algorithms to reduce the suspicious list. One way to do this is by assigning a risk score to each transaction. In our work we build two filters that determine the risk of each transaction based on the amount of statistical abnormality. We use the Chebyshev inequality to determine anomalous transactions. In the first phase we focus on detecting a large transaction that changes market price significantly. We then look at transactions around it to find people who made profit as a consequence of that large transaction. We tested our method on two different stocks the data for which was kindly provided to us by Tehran Exchange Market. The officials confirmed we were able to detect the fraudster. }, Keywords = {Stock Exchange, Market manipulation, Front running, Fraud detection, Chebyshev inequality}, volume = {17}, Number = {1}, pages = {3-14}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {کشف تقلب در بازار بورس اوراق بهادار با استفاده از کاربرد نامساوی چبیشف}, abstract_fa ={یکی از راه­‌های مشارکت افراد در توسعه اقتصادی کشور، سرمایه‌­گذاری در بازار سرمایه و به‌خصوص، بورس اوراق بهادار است. به این منظور، بازارهای اوراق بهادار باید مورد اعتماد مردم و فعالان اقتصادی باشند. شفافیت و کارایی بازار می‌­تواند حقوق و منافع سرمایه‌­گذاران را حمایت کند و باعث رونق بازار شود. در این میان، بعضی از افراد با توجه به موقعیت خود از اطلاعات نهانی مربوط به بازار بورس اوراق بهادار سوء استفاده می‌­کنند و باعث بی‌­اعتمادی افراد به بازار سرمایه می‌­شود؛ از‌این‌رو در این مقاله، با استفاده از کاربرد نامساوی چبیشف، روشی برای شناسایی افرادی که از اطلاعات نهانی، استفاده شخصی کرده­ و در مدت کوتاهی سود کلانی به‌­دست آورد‌ه‌­اند، ارائه شده است. به‌منظور استفاده از این روش دو فیلتر در نظر گرفته شده­ است، به‌طوری‌که فیلتر نخست تراکنش‌­های بزرگ را شناسایی می‌کند و فیلتر دوم، افرادی که بیشترین سود حاصل از خرید و فروش سهام در مدت زمان اندک (سه روز)، به‌دست آورده‌­ا‌ند؛ در‌حالی‌که دست‌کم یک تراکنش بزرگ در این حد فاصل زمانی رخ داده باشد، شناسایی می­‌کند؛ سپس روش پیشنهادی، بر روی دو دسته از داده­‌های واقعی بازار بورس اعمال شده است. با تغییر ضرایب فیلترها، می‌­توان معیارهای مورد نظر را تغییر داد.}, keywords_fa = {بازار بورس اوراق بهادار, دست‌کاری بازار, پیش‌روی, کشف تقلب, نامساوی چبیشف}, doi = {10.29252/jsdp.17.1.3}, url = {http://jsdp.rcisp.ac.ir/article-1-850-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-850-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Kamandar, Mehdi and Maghsoudi, yaser}, title = {Low latency IIR digital filter design by using metaheuristic optimization algorithms}, abstract ={Filters are particularly important class of LTI systems. Digital filters have great impact on modern signal processing due to their programmability, reusability, and capacity to reduce noise to a satisfactory level. From the past few decades, IIR digital filter design is an important research field. Design of an IIR digital filter with desired specifications leads to a no convex optimization problem. IIR digital filter which design by minimizing the error between frequency response of desired and designed filters with some constraints such as stability, linear phase, and minimum phase by meta heuristic algorithms has gained increasing attention. The aim of this paper is to develop an IIR digital filter designing method that can provide relatively good time response characterizations beside good frequency response ones. One of the most important required time characterizations of digital filters for real time applications is low latency. To design a low latency digital filter, minimization of weighted partial energy of impulse response of the filter is used, in this paper. By minimizing weighted partial energy of impulse response, energy of impulse response concentrates on its beginning, consequently low latency for responding to inputs. This property beside minimum phase property of designed filter leads to good time specifications. In the proposed cost function in order to ensure the stability margin the term maximum pole radius is used, to ensure the minimum phase state the number of zeros outside the unit circle is considered, to achieve linear phase the constant group delay is considered. Due to no convexity of proposed cost function, three meta-heuristc algorithms GA, PSO, and GSA are used for optimization processes. Reported results confirmed the efficiency and the flexibility of the proposed method for designing various types of digital filters (frequency selective, differentiator, integrator, Hilbert, equalizers, and …) with low latency in comparison with the traditional methods. Designed low pass filter by proposed method has only 1/79 sample delay, that is ideal for most of the applications.}, Keywords = {Digital signal processing, IIR digital filter design, Low latency, Weighted partial energy, Meta-heuristic optimization algorithms}, volume = {17}, Number = {1}, pages = {15-28}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {طراحی فیلترهای دیجیتال IIR با تأخیر کم با استفاده از الگوریتم‌های بهینه‌سازی فرا ابتکاری}, abstract_fa ={طراحی فیلترهای دیجیتال IIR مبتنی بر کمینه‌کردن اختلاف پاسخ فرکانسی فیلتر طراحی‌شده و دلخواه به همراه قیودی همچون پایداری، فاز خطی و کمینه فازی توسط الگوریتم­‌های بهینه‌سازی فرا‌ابتکاری توجه زیادی را به خود جلب کرده است. یکی از مشخصه­‌های مهم زمانی فیلترها تأخیر کم آنها است که در کاربردهای هم‌زمان ضروری است. در این مقاله جهت طراحی یک فیلتر با تأخیر کم، مفهوم انرژی جزئی وزن‌دار پاسخ ضربه فیلتر پیشنهاد شده است. با کمینه‌‌کردن این معیار، انرژی پاسخ ضربه فیلتر در ابتدای آن متمرکز شده و باعث سریع‌تر از بین رفتن پاسخ گذرا و همچنین کاهش تأخیر فیلتر در پاسخ به ورودی می­‌شود. این خاصیت در کنار کمینه فازی منجر به مشخصات زمانی خوب علاوه‌بر مشخصات خوب فرکانسی برای فیلتر می‌شود، به این معنی که پاسخ پله فیلتر به پله نزدیک می‌شود که در بسیاری از کاربردها ضروری است. در تابع هزینه پیشنهادی برای افزایش حاشیه پایداری از کمینه‌کردن معیار بزرگ‌ترین اندازه قطب‌­ها، جهت کمینه فازی از کمینه‌کردن معیار تعداد صفرهای بیرون دایره واحد و جهت دست­‌یابی به فاز خطی از معیار تأخیر گروهی ثابت استفاده شده است. کمینه‌کردن تابع هزینه پیشنهادی به‌دلیل نا محدب‌بودن و تعداد زیادی بهینه­‌های محلی توسط الگوریتم‌­های فرا‌ابتکاری PSO، GA و GSA انجام شده است. نتایج گزارش‌شده، قابلیت و انعطاف‌­پذیری روش پیشنهادی را در طراحی انواع  فیلترهای دیجیتال فرکانس گزین، مشتق گیر و انتگرال گیر، همسان‌ساز و هیلبرت با مشخصات فرکانسی و زمانی خوب در مقایسه با روش­‌های رایج را نشان می­‌دهد. فیلتر طراحی‌شده با استفاده از روش پیشنهادی تنها 79/1 نمونه تأخیر دارد که برای بیش‌تر کاربردها ایده‌ال است.}, keywords_fa = {پردازش سیگنال دیجیتال, طراحی فیلتر دیجیتال IIR, تأخیر کم, انرژی جزئی وزن‌دار, الگوریتم‌های بهینه‌سازی فرا ابتکاری}, doi = {10.29252/jsdp.17.1.15}, url = {http://jsdp.rcisp.ac.ir/article-1-880-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-880-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {taherikhameneh, behnam and shokrzadeh, hami}, title = {Hierarchical Fuzzy Clustering Semantics (HFCS) in Web Document for Discovering Latent Semantics}, abstract ={This paper discusses about the future of the World Wide Web development, called Semantic Web. Undoubtedly, Web service is one of the most important services on the Internet, which has had the greatest impact on the generalization of the Internet in human societies. Internet penetration has been an effective factor in growth of the volume of information on the Web. The massive growth of information on the Web has led to some problems, the most important one is search query. Nowadays, search engines use different techniques to deliver high quality results, but we still see that search results are not ideal. It should also be noted that information retrieval techniques to a certain extent can increase the search accuracy. Most of the web content is designed for human usage and machines are only able to understand and manipulate data at word level. This is the major limitation for providing better services to web users. The solution provided for this topic is to display the content of the web in such a way that it can be readily understood and comprehensible to the machine. This solution, which will lead to a huge transformation on the Web is called the Semantic Web and will begin. Better results for responding to the search for semantic web users, is the purpose of this research. In the proposed method, the expression, searched by the user, will be examined according to the related topics. The response obtained from this section enters to a rating system, which is consisted of a fuzzy decision-making system and a hierarchical clustering system, to return better results to the user. It should be noted that the proposed method does not require any prior knowledge for clustering the data. In addition, accuracy and comprehensiveness of the response are measured. Finally, the F test is applied to obtain a criterion for evaluating the performance of the algorithm and systems. The results of the test show that the method presented in this paper can provide a more precise and comprehensive response than its similar methods and it increases the accuracy up to 1.22%, on average.}, Keywords = {Semantic Web, Fuzzy Logic, Hierarchical Clustering, Latent Semantic, HFCS}, volume = {17}, Number = {1}, pages = {29-46}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {خوشه‌بندی سلسله‌مراتبی فازی برای کشف روابط معنایی پنهان در اسناد وب‌معنایی}, abstract_fa ={رشد انبوه اطلاعات در وب مشکلاتی را به‌دنبال داشته است که از مهم‌ترین آن‌ها می‌توان به چالش­‌های ایجاد‌شده برای جستجو در وب اشاره کرد. با توجه به این که بیشتر محتویات وب امروزی برای استفاده توسط انسان طراحی ‌شده است، ماشین‌ها تنها قادر به دست‌کاری و فهم داده‌ها در سطح لغت هستند؛ این مسأله مهم‌ترین مانع در سرویس‌دهی بهتر به کاربران وب است. هدف این مقاله ارائه نتایج بهتر در پاسخ به جستجوی کاربران وب معنایی است. به این منظور در روش پیشنهادی ابتدا عبارت مورد نظر کاربر با توجه به میزان موضوعات مرتبط با آن، مورد بررسی قرار می‌گیرد. پاسخ به‌دست‌آمده از این بررسی، وارد یک سامانه رتبه‌دهی متشکل از سامانه تصمیم‌گیری فازی و خوشه‌بندی سلسله‌مراتبی می‌شود تا نتایج مطلوب‌تری را به کاربر بازگرداند. گفتنی است که روش پیشنهادی نیاز به هیچ‌گونه دانش قبلی برای خوشه‌بندی داده‌ها ندارد؛ علاوه‌بر این دقت و جامعیت این پاسخ نیز اندازه‌گیری می‌شود؛ درنهایت، بر روی نتایج به‌دست‌آمده آزمون F اعمال می‌شود که اغلب به‌عنوان یک معیار از عملکرد سامانه، برای ارزیابی الگوریتم و سامانه‌های مورد استفاده در نظر گرفته می‌شود. نتایج حاصل از این آزمون نشان می‌دهد که روش ارائه‌شده در این مقاله می‌تواند پاسخ دقیق‌تر و جامع‌تری نسبت به روش‌های مشابه خود ارائه دهد و به‌طور میانگین دقت را تا 22/1 درصد افزایش دهد.}, keywords_fa = {وب‌ معنایی, منطق فازی, خوشه‌بندی سلسله‌مراتبی, روابط معنایی پنهان, الگوریتم HFCS}, doi = {10.29252/jsdp.17.1.29}, url = {http://jsdp.rcisp.ac.ir/article-1-882-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-882-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Mahmoodzadeh, Azar and Agahi, Hamed and Vaghefi, Mahs}, title = {A Fall Detection System based on the Type II Fuzzy Logic and Multi-Objective PSO Algorithm}, abstract ={The Elderly health is an important and noticeable issue; since these people are priceless resources of experience in the society. Elderly adults are more likely to be severely injured or to die following falls. Hence, fast detection of such incidents may even lead to saving the life of the injured person. Several techniques have been proposed lately for the fall detection of people, mostly categorized into three classes. The first class is based on the wearable or portable sensors [1-6]; while the second class works according to the sound or vibration sensors [7-8]. The third one is based on the machine vision. Although the latter methods require cameras and image processing systems, access to surveillance cameras -which are economical- has made them be extensively used for the elderly.  By this motivation, this paper proposes a real-time technique in which, the surveillance video frames of the person’s room are being processed. This proposed method works based on the feature extraction and applying type-II fuzzy algorithm for the fall detection. First, using the improved visual background extraction (ViBe) algorithm, pixels of the moving person are separated from those of the background. Then, using the obtained image for the moving person, six features including ‘aspect ratio’, ‘motion vector’, ‘center-of-gravity’, ‘motion history image’, ‘the angle between the major axis of the bounding ellipse and the horizontal axis’ and the ‘ratio of major axis to minor axis of the bounding ellipse’ are extracted. These features should be given to an appropriate classifier. In this paper, an interval type-II fuzzy logic system (IT2FLS) is utilized as the classifier. To do this, three membership functions are considered for each feature. Accordingly, the number of the fuzzy laws for six features is too large, leading to high computational complexity. Since most of these laws in the fall detection are irrelevant or redundant, an appropriate algorithm is used to select the most effective fuzzy membership functions. The multi-objective particle swarm optimization algorithm (MOPSO) is an operative tool for solving large-scale problems. In this paper, this evolutionary algorithm tries to select the most effective membership functions to maximize the ‘classification accuracy’ while the ‘number of the selected membership functions’ are simultaneously minimized. This results in a considerably smaller number of rules. In this paper to investigate the performance of the proposed algorithm, 136 videos from the movements of people were produced; among which 97 people fell down and 39 ones were related to the normal activities (non-fall). To this end, three criteria including accuracy (ACC), sensitivity (Se.), and specificity (Sp.) are used. By changing the initial values of the parameters of the ViBe algorithm and frequent re-tuning after multiple frames, detecting the moving objects is done faster and with higher robustness against noise and illumination variations in the environment. This can be done via the proposed system even in microprocessors with low computational power. The obtained results of applying the proposed approach confirmed that this system is able to detect the human fall quickly and precisely.}, Keywords = {Fall Detection, ViBe Algorithm, Type II Fuzzy Logic, MOPSO}, volume = {17}, Number = {1}, pages = {47-60}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {سامانه تشخیص سقوط افراد مبتنی بر منطق فازی نوع دو و الگوریتم بهینه‌سازی اجتماع ذرات چندهدفه}, abstract_fa ={توجه به سلامت سالمندان به‌عنوان سرمایه‌های ارزشمند کشور، امری ضروری و شایان توجه است. آسیب‌های جدی یا حتی مرگ ناشی از زمین‌خوردن برای افراد سالمند بسیار محتمل است؛ بنابراین تشخیص سریع وقوع این رخداد در بسیاری موارد می‌تواند منجر به نجات جان شخص شود. در این مقاله روشی پیشنهاد شده است که بر اساس آن تصاویر ویدئویی نظارتی از محل حضور شخص همواره مورد پردازش قرار می‌گیرد. در ادامه، با استفاده از الگوریتم استخراج پس‌زمینه بصری (ViBe)، شخص متحرک از پس‌زمینه جدا شده و شش ویژگی مؤثر از تصویر استخراج می‌شود. در انتها سامانه منطق فازی نوع دو برای تشخیص سقوط فرد به کار گرفته می شود؛ همچنین به‌منظور کاهش پیچیدگی محاسباتی سامانه فازی، از الگوریتم بهینه سازی اجتماع ذرات چندهدفه برای انتخاب توابع تعلق مؤثر استفاده شده است. نتایج اعمال روش پیشنهادی تصدیق می‌کند که این سامانه قادر به تشخیص سقوط شخص با سرعت قابل قبول و دقت تصمیم‌گیری مناسب است.}, keywords_fa = {تشخیص سقوط, الگوریتم ViBe, منطق فازی نوع دو, الگوریتم بهینه سازی اجتماع ذرات چندهدفه}, doi = {10.29252/jsdp.17.1.47}, url = {http://jsdp.rcisp.ac.ir/article-1-886-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-886-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Fahmi, Ali and Shamsi, Mousa and Rouni, Houshang}, title = {Anthropometric Analysis of Face using Local Gaussian Distribution Fitting Applicable for Facial Surgery}, abstract ={Human facial plays a very important role in the human’s appearance. Many defects in the face affect the facial appearance, significantly. Facial plastic surgeries can correct the defects on the face. Analysis of facial color images is very important due to its numerous applications in facial surgeries. Different types of facial surgeries, such as Rhinoplasty, Otoplasty, Belpharoplasty and chin augmentation are performed on the face to make beautiful structure. Rhinoplasty and Otoplasty are widely used in the facial plastic surgeries. the former is performed to correct air passage, correct structural defects, and make a beautiful structure on bone, cartilage, and soft nasal tissue. Also, the latter is performed to correct defects in the ear area. Development of different tools in the field of facial surgery analysis can help surgeons before and after surgery. The main purpose of this study is the anthropometry analysis of facial soft tissue based on image processing methods applicable to Rhinoplasty and Otoplasty surgeries. The proposed method includes three parts.; (1) contour detection, (2) feature extraction, and (3) feature selection. An Active Contour Model (ACM) based on Local Gaussian Distribution Fitting (LGDF) has been used to extract contours from facial lateral view and ear area. The LGDF model is a region-based model which unlike other models such as the Chan-Vese (CV) model is not sensitive to the inhomogeneity of image spatial intensity. Harris Corner Detector (HCD) has been applied to extracted contour for feature extraction. HCD is a method based on calculating of auto-correlation matrix and changing the gray value. In this study, dataset of orthogonal stereo imaging system of Sahand University of Technology (SUT), Tabriz, Iran has been used. After detecting facial key points, metrics of facial profile view and ear area have been measured. In analysis of profile view, 7 angles used in the Rhinoplasty have been measured. Analysis of ear anthropometry includes measuring the length, width and external angle. In the Rhinoplasty analysis, accuracy of the proposed method was about %90 in the all measurement parameters, as well as, it was %96.432, %97.423 and %85.546 in the Otoplasty analysis for measuring in the length, width and external angle of the ear on AMI database, respectively. Using the proposed system in planning of facial plastic surgeries can help surgeons in the Rhinoplasty and Otoplasty analysis. This research can be very effective in developing simulation and evaluation systems for the mentioned surgeries.}, Keywords = {Facial Soft Tissue Analysis, Surgery Analysis, Orthogonal Stereo Imaging, Facial Key Points, LGDF Model}, volume = {17}, Number = {1}, pages = {61-78}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {آنالیز آنتروپومتری چهره به‌منظور کاربرد در جراحی چهره با استفاده از توزیع گوسین مکانی}, abstract_fa ={آنالیز تصاویر چهره انسان به­دلیل کاربردهای فراوان آن در جراحی­های چهره دارای اهمیت زیادی است. وجود ابزارهای سخت­افزاری و نرم‌افزاری در زمینه آنالیز جراحی­‌های چهره کمک شایانی را می‌­تواند به متخصصان جراحی­‌های چهره در قبل و بعد عمل جراحی داشته باشد. در این راستا، نیاز به دانستن آنتروپومتری­‌های موردنظر در آنالیز جراحی­‌های چهره و استخراج ویژگی­ هستیم. جهت استخراج کانتور نمای جانبی چهره و ناحیه گوش برای آنالیز در جراحی­های رینوپلاستی  و اتوپلاستی از مدل کانتور فعال مبتنی بر توزیع گوسین مکانی (مدل LGDF) استفاده شده است. در جراحی‌­های اشاره‌شده، ابتدا کانتور ناحیه موردنظر را با استفاده از مدل LGDF استخراج کرده و در مرحله بعد با اعمال گوشه‌­یاب هریس نقاط شاخص موردنظر جهت آنالیز آنتروپومتری موردنظر آشکارسازی شده‌­اند. دقت الگوریتم پیشنهادی در جراحی رینوپلاستی برای پایگاه داده دانشگاه سهند بالای %90 بوده و  در جراحی اتوپلاستی دقت الگوریتم پیشنهادی برای پایگاه داده AMI جهت اندازه­‌گیری طول، عرض و زاویه خارجی گوش به­‌ترتیب 432/96%، 423/97% و 546/85% هستند.}, keywords_fa = {آنالیز آنتروپومتری بافت نرم چهره, آنالیز جراحی چهره, سامانه تصویربرداری متعامد چهره, نقاط کلیدی چهره, مدل LGDF}, doi = {10.29252/jsdp.17.1.61}, url = {http://jsdp.rcisp.ac.ir/article-1-868-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-868-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Rahimi, Zeinab and HosseinNejad, Shadi}, title = {Corpus based coreference resolution for Farsi text}, abstract ={"Coreference resolution" or "finding all expressions that refer to the same entity" in a text, is one of the important requirements in natural language processing. Two words are coreference when both refer to a single entity in the text or the real world. So the main task of coreference resolution systems is to identify terms that refer to a unique entity. A coreference resolution tool could be used in many natural language processing tasks such as machine translation, automatic text summarization, question answering, and information extraction systems. Adding coreference information can increase the power of natural language processing systems. The coreference resolution can be done through different ways. These methods include heuristic rule-based methods and supervised/unsupervised machine learning methods. Corpus based and machine learning based methods are widely used in coreference resolution task in recent years and has led to a good performance. For using such these methods, there is a need for manually labeled corpus with sufficient size. For Persian language, before this research, there exists no such corpus. One of the important targets here, was producing a through corpus that can be used in coreference resolution task and other associated fields in linguistics and computational linguistics. In this coreference resolution research, a corpus of coreference tagged phrases has been generated (manually annotated) that has about one million words. It also has named entity recognition (NER) tags. Named entity labels in this corpus include 7 labels and in coreference task, all noun phrases, pronouns and named entities have been tagged. Using this corpus, a coreference tool was created using a vector space machine, with precision of about 60% on golden test data. As mentioned before, this article presents the procedure for producing a coreference resolution tool. This tool is produced by machine learning method and is based on the tagged corpus of 900 thousand tokens. In the production of the system, several different features and tools have been used, each of which has an effect on the accuracy of the whole tool. Increasing the number of features, especially semantic features, can be effective in improving results. Currently, according to the sources available in the Persian language, there are no suitable syntactic and semantic tools, and this research suffers from this perspective. The coreference tagged corpus produced in this study is more than 500 times bigger than the previous Persian language corpora and at the same time it is quite comparable to the prominent ACE and Ontonotes corpora. The system produced has an f-measure of nearly 60 according to the CoNLL standard criterion. However, other limited studies conducted in Farsi have provided different accuracy from 40 to 90%, which is not comparable to the present study, because the accuracy of these studies has not been measured with standard criterion in the coreference resolution field.}, Keywords = {Automatic coreference resolution, Anaphora resolution, mention}, volume = {17}, Number = {1}, pages = {79-98}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {هم‌مرجع‌یابی مبتنی بر پیکره در متون فارسی}, abstract_fa ={مرجع‌یابی یا مرجع‌گزینی یا پیدا‌کردن واژگان هم‌مرجع در متن، یکی از وظایف مهم در پردازش زبان طبیعی است که یک بخش عملیاتی مهم در مسائلی مانند خلاصه‌سازی خودکار، پرسش و پاسخ خودکار و استخراج اطلاعات به‌شمار می‌رود. طبق تعاریف زمانی، دو واژه زمانی هم‌مرجع هستند که هر دو به موجودیت واحدی در متن یا جهان حقیقی ارجاع بدهند. تاکنون برای حل این مسأله تلاش‌های متعددی صورت گرفته است که بنابر نتایج این مطالعات، عملیات مرجع‌گزینی را می‌توان با روش‌های متفاوتی مانند روش‌های قاعده‌مند، مبتنی بر قوانین مکاشفه‌ای و روش‌های یادگیری ماشین (بانظارت یا بی‌ناظر) انجام داد. نکته قابل توجه این است که در سال‌های اخیر استفاده از پیکره‌های برچسب‌گذاری‌شده در این زمینه رواج زیادی داشته و منجر به تولید نتایج مناسبی هم شده است. با تکیه بر این موضوع، در پژوهش حاضر، یک پیکره از واژگان هم‌مرجع تولید شده که حدود یک‌میلیون واژه به‌همراه برچسب موجودیت نامدار دارد. در بخش مرجع‌گزینی تمام گروه‌های اسمی، ضمایر و موجودیت‌های نامدار برچسب‌گذاری شده‌اند و برچسب‌های موجودیت نامدار پیکره شامل هفت برچسب است. در پژوهش حاضر با استفاده از این پیکره، یک ابزار مرجع‌گزینی خودکار با استفاده از ماشین بردار پشتیبان تولید شده که دقت آن بر روی داده‌های آزمایش طلایی در حدود شصت درصد است.}, keywords_fa = {هم‌مرجع یابی خودکار, مرجع‌گزینی, تحلیل مرجع ضمیر, عبارات ارجاعی}, doi = {10.29252/jsdp.17.1.79}, url = {http://jsdp.rcisp.ac.ir/article-1-873-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-873-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Mavaddati, Samira and Ahadi, Mohamm}, title = {Speech Enhancement using Adaptive Data-Based Dictionary Learning}, abstract ={In this paper, a speech enhancement method based on sparse representation of data frames has been presented. Speech enhancement is one of the most applicable areas in different signal processing fields. The objective of a speech enhancement system is improvement of either intelligibility or quality of the speech signals. This process is carried out using the speech signal processing techniques to attenuate the background noise without causing any distortion in the speech signal. In this paper, we focus on the single channel speech enhancement corrupted by the additive Gaussian noise. In recent years, there has been an increasing interest in employing sparse representation techniques for speech enhancement. Sparse representation technique makes it possible to show the major information about the speech signal based on a smaller dimension of the original spatial bases. The capability of a sparse decomposition method depends on the learned dictionary and matching between the dictionary atoms and the signal features. An over complete dictionary is yielded based on two main steps: dictionary learning process and sparse coding technique. In dictionary selection step, a pre-defined dictionary such as the Fourier basis, wavelet basis or discrete cosine basis is employed. Also, a redundant dictionary can be constructed after a learning process that is often based on the alternating optimization strategies. In sparse coding step, the dictionary is fixed and a sparse coefficient matrix with the low approximation error has been earned. The goal of this paper is to investigate the role of data-based dictionary learning technique in the speech enhancement process in the presence of white Gaussian noise. The dictionary learning method in this paper is based on the greedy adaptive algorithm as a data-based technique for dictionary learning. The dictionary atoms are learned using the proposed algorithm according to the data frames taken from the speech signals, so the atoms contain the structure of the input frames. The atoms in this approach are learned directly from the training data using the norm-based sparsity measure to earn more matching between the data frames and the dictionary atoms. The proposed sparsity measure in this paper is based on Gini parameter. We present a new sparsity index using Gini coefficients in the greedy adaptive dictionary learning algorithm. These coefficients are set to find the atoms with more sparsity in the comparison with the other sparsity indices defined based on the norm of speech frames. The proposed learning method iteratively extracts the speech frames with minimum sparsity index according to the mentioned measures and adds the extracted atoms to the dictionary matrix. Also, the range of the sparsity parameter is selected based on the initial silent frames of speech signal in order to make a desired dictionary. It means that a speech frame of input data matrix can add to the first columns of the over complete dictionary when it has not a similar structure with the noise frames. The data-based dictionary learning process makes the algorithm faster than the other dictionary learning methods for example K-singular value decomposition (K-SVD), method of optimal directions (MOD) and other optimization-based strategies. The sparsity of an input frame is measured using Gini-based index that includes smaller measured values for speech frames because of their sparse content. On the other hand, high values of this parameter can be yielded for a frame involved the Gaussian noise structure. The performance of the proposed method is evaluated using different measures such as improvement in signal-to-noise ratio (ISNR), the time-frequency representation of atoms and PESQ scores. The proposed approach results in a significant reduction of the background noise in comparison with other dictionary learning methods such as principal component analysis (PCA) and the norm-based learning method that are traditional procedures in this context. We have found good results about the reconstruction error in the signal approximations for the proposed speech enhancement method. Also, the proposed approach leads to the proper computation time that is a prominent factor in dictionary learning methods. }, Keywords = {Speech enhancement, Sparse representation, Dictionary learning, Data-Based learning, Greedy adaptive}, volume = {17}, Number = {1}, pages = {99-116}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {بهسازی گفتار به‌کمک یادگیری واژه‌نامه مبتنی‌بر داده}, abstract_fa ={بهسازی گفتار یکی از پرکاربردترین حوزه‌ها در زمینه پردازش گفتار است. در این مقاله، یکی از روش‌های بهسازی گفتار مبتنی‌بر اصول بازنمایی تُنُک بررسی می‌شود. بازنمایی تُنُک این امکان را فراهم می‌سازد که عمده اطلاعات لازم برای بازنمایی سیگنال‌، براساس بُعد بسیار کمتری از پایه‌های فضایی اصلی قابل مدل‌سازی باشد. روش‌ یادگیری در این مقاله براساس تصحیح الگوریتم تطبیقی حریصانه مبتنی‌بر داده خواهد بود که واژه‌نامه در آن، به‌طور مستقیم از روی سیگنال داده و براساس شاخص تُنُکی مبتنی‌بر نُرم به منظور تطابق بیشتر میان اتم‌ها و ساختار داده آموزش می‌بیند. در این مقاله شاخص تُنُکی جدیدی براساس معیار جینی پیشنهاد می‌شود. همچنین محدوده پارامتر تُنُکی بخش‌های نوفه‌ای با توجه به فریم‌های ابتدایی گفتار تعیین و طی یک روال پیشنهادی در تشکیل واژه‌نامه مورد استفاده قرار می‌گیرد. نتایج بهسازی نشان می‌دهد که عملکرد روش پیشنهادی در انتخاب قاب‌‌های داده براساس معیار معرفی‌شده در شرایط نوفه‌ای مختلف بهتر از شاخص تُنُکی مبتنی‌بر نُرم و سایر الگوریتم‌های پایه در این راستا است.}, keywords_fa = {بهسازی گفتار, بازنمایی تُنُک, یادگیری واژه‌نامه, مبتنی‌بر داده, تطبیقی حریصانه, شاخص تُنُکی جینی}, doi = {10.29252/jsdp.17.1.99}, url = {http://jsdp.rcisp.ac.ir/article-1-805-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-805-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {AsheghiDizaji, Zahra and AsghariAghjehdizaj, Sakineh and SoleimanianGharehchopogh, Farh}, title = {An Improvement in Support Vector Machines Algorithm with Imperialism Competitive Algorithm for Text Documents Classification}, abstract ={Due to the exponential growth of electronic texts, their organization and management requires a tool to provide information and data in search of users in the shortest possible time. Thus, classification methods have become very important in recent years. In natural language processing and especially text processing, one of the most basic tasks is automatic text classification. Moreover, text classification is one of the most important parts in data mining and machine learning. Classification can be considered as the most important supervised technique which classifies the input space to k groups based on similarity and difference such that targets in the same group are similar and targets in different groups are different. Text classification system has been widely used in many fields, like spam filtering, news classification, web page detection, Bioinformatics, machine translation, automatic response systems, and applications regarding of automatic organization of documents. The important point in obtaining an efficient text classification method is extraction and selection of key features of texts. It is proved that only 33% of words and features of the texts are useful and they can be used to extract information and most words existing in texts are used to represent purpose of a text and they are sometimes repeated. Feature selection is known as a good solution to high dimensionality of the feature space. Excessive number of Features not only increase computation time but also degrade classification accuracy. In general, purpose of extracting and selecting features of texts is to reduce data volume, time required for training, computational time and increase performance speed of the methods proposed for text classification. Feature extraction refers to the process of generating a small set of new features by combining or transforming the original ones, while in feature selection dimension of the space is reduced by selecting the most prominent features. In this paper, a solution to improve support vector machine algorithm using Imperialism Competitive Algorithm, are provided. In this proposed method, the Imperialism Competitive Algorithm for selecting features and the support vector machine algorithm for Classification of texts are used. At the stage of extracting the features of the texts, using weighting schemes such as NORMTF, LOGTF, ITF, SPARCK, and TF, each extracted word is allocated a weight in order to determine the role of the words in terms of their effects as the keywords of the texts. The weight of each word indicates the extent of its effect on the main topic of the text compared to other words used in the same text. In the proposed method, the TF weighting scheme is used for attributing weights to the words. In this scheme, the features are a function of the distribution of different features in each of the documents . Moreover, at this stage, using the process of pruning, low-frequency features and words that are used fewer than two times in the text are pruned. Pruning basically filters low-frequency features in a text [18]. In order to reduce the number of dimensions of the features and decrease computational complexity, the imperialist competitive algorithm (ICA) is utilized in the proposed method. The main goal of employing the imperialist competitive algorithm (ICA) in the proposed method is minimizing the loss of data in the texts, while also maximizing the reduction of the dimensions of the features. In the proposed method, since the imperialist competitive algorithm (ICA) has been used for selecting the features, there must be a mapping created between the parameters of the imperialist competitive algorithm (ICA) and the proposed method. Accordingly, when using the imperialist competitive algorithm (ICA) for selecting the key features, the search space includes the dimensions of the features, and among all the extracted features, , , or  of all the features are attributed to each of the countries. Since the mapping is carried out randomly, there may be repetitive features in any of the countries as well. Next, based on the general trend of the imperialist competitive algorithm (ICA),some countries which are more powerful are considered as imperialists, while the other countries are considered as colonies. Once the countries are identified, the optimization process can begin. Each country is defined in the form of an  array with different values for the variables as in Equations 2 and 3. (2) Country = [ , , …,  , ] (3) Cost = f (Country) The variables attributed to each country can be structural features, lexical features, semantic features, or the weight of each word, and so on. Accordingly, the power of each country for identifying the class of each text is increased or decreased based on its variables. One of the most important phases of the imperialist competitive algorithm (ICA) is the colonial competition phase. In this phase, all the imperialists try to increase the number of colonies they own. Each of the more powerful empires tries to seize the colonies of the weakest empires to increase their own power. In the proposed method, colonies with the highest number of errors in classification and the highest number of features are considered as the weakest empires. Based on trial and error, and considering the target function in the proposed method, the number of key features relevant to the main topic of the texts is set to  of the total extracted features, and only through using   of the key features of each text along with a classifier algorithm such as , support vector machine (SVM),  nearest neighbors, and so on, the class of that text can be determined in the proposed method. Since the classification of texts is a nonlinear problem, in order to classify texts, the problem must first be mapped into a linear problem. In this paper, the RBF kernel function along with  is used for mapping the problem. The hybrid algorithm is implemented on the Reuters21578, WebKB, and Cade 12 data sets to evaluate the accuracy of the proposed method. The simulation results indicate that the proposed hybrid algorithm in precision, recall and F Measure criteria is more efficient than primary support machine carriers.  }, Keywords = {Feature Selection, Text Classification, Imperialism Competitive Algorithm, Support Vector Machines Algorithm, Optimization}, volume = {17}, Number = {1}, pages = {117-130}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {بهبود الگوریتم ماشین بردار پشتیبان با الگوریتم رقابت استعماری برای دسته‌بندی اسناد متنی}, abstract_fa ={با توجه به رشد نمایی متون الکترونیکی، سازماندهی و مدیریت متون، مستلزم ابزاری است که اطلاعات و داده‏‌های مورد جستجوی کاربران را در کمترین زمان ارائه دهد؛ از‌این‌رو در سال‌های اخیر روش‌های دسته‌بندی اهمیت ویژه‎ای پیدا کرده است. هدف دسته‌بندی متون دست‌یابی به اطلاعات و داده‌ها در کسری از ثانیه است. یکی از مشکلات اصلی در دسته‏‌بندی متون، ابعاد بالای ویژگی‎هاست. برای کاهش ویژگی‎های متون، انتخاب ویژگی‎ها یکی از مؤثرترین راه‎حل‎هاست. چراکه هزینه محاسباتی که تابعی از طول بردار ویژگی‎هاست، بدون انتخاب ویژگی‌ها افزایش می‏‌یابد. در این مقاله روشی براساس بهبود الگوریتم ماشین بردار پشتیبان با الگوریتم رقابت استعماری برای دسته‌بندی اسناد متنی ارائه شده است. در روش پیشنهادی، از الگوریتم رقابت استعماری برای انتخاب ویژگی‎های و از الگوریتم ماشین بردار پشتیبان برای دسته‎بندی متون استفاده شده است. آزمایش و ارزیابی روش پیشنهادی بر روی مجموعه داده‌های Reuters21578, WebKB و Cade 12 انجام شده است. نتایج شبیه‎سازی حاکی از آن است که روش پیشنهادی در معیارهای دقت، بازخوانی و F Measure از روش‌ ماشین بردار پشتیبان بدون انتخاب ویژگی عملکرد بهینه‎تری دارد.}, keywords_fa = {انتخاب ویژگی, دسته‌بندی متون, الگوریتم رقابت استعماری, الگوریتم ماشین بردار پشتیبان, بهینه‌سازی}, doi = {10.29252/jsdp.17.1.117}, url = {http://jsdp.rcisp.ac.ir/article-1-871-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-871-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Hadizadeh, Hadi}, title = {Block-Based Compressive Sensing Using Soft Thresholding of Adaptive Transform Coefficients}, abstract ={Compressive sampling (CS) is a new technique for simultaneous sampling and compression of signals in which the sampling rate can be very small under certain conditions. Due to the limited number of samples, image reconstruction based on CS samples is a challenging task. Most of the existing CS image reconstruction methods have a high computational complexity as they are applied on the entire image. To reduce this complexity, block-based CS (BCS) image reconstruction algorithms have been developed in which the image sampling and reconstruction processes are applied on a block by block basis. In almost all the existing BCS methods, a fixed transform is used to achieve a sparse representation of the image. however such fixed transforms usually do not achieve very sparse representations, thereby degrading the reconstruction quality. To remedy this problem, we propose an adaptive block-based transform, which exploits the correlation and similarity of neighboring blocks to achieve sparser transform coefficients. We also propose an adaptive soft-thresholding operator to process the transform coefficients to reduce any potential noise and perturbations that may be produced during the reconstruction process, and also impose sparsity. Experimental results indicate that the proposed method outperforms several prominent existing methods using four different popular image quality assessment metrics.}, Keywords = {Compressive Sampling, Soft Thresholding, Adaptive Transform, Sparsity}, volume = {17}, Number = {1}, pages = {131-146}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {حس‌گری فشرده بلوکی با استفاده از آستانه‌گیری نرم ضرایب تبدیل تطبیقی}, abstract_fa ={در این مقاله، روشی نوین جهت بازسازی تصاویر بر اساس نمونه‌های به‌دست‌آمده از اعمال «حس‌گری فشرده بلوکی» ارائه می‌شود. جهت حصول به کیفیت بازسازی بالا در روش پیشنهادی، ابتدا یک تبدیل تطبیقی بلوکی توسعه داده می‌شود که از همبستگی و شباهت بلوک‌های همسایه یک بلوک موردنظر در تصویر برای حصول به تُنُک‌سازی بالاتر آن بلوک، استفاده می‌کند؛ سپس، برای کاهش نوفه و اعوجاجات احتمالی به‌وجود‌آمده در فرآیند بازسازی و در عین‌حال حفظ میزان تُنُکی ضرایب، از یک تابع آستانه‌گیری نرم استفاده می‌شود که قادر است به‌صورت تطبیقی، ضرایب تبدیل را برای افزایش کیفیت بازسازی تصویر، پالایش کند. نتایج تجربی به‌دست‌آمده نشان می‌دهند که روش پیشنهادی از دقت و کیفیت بازسازی بالاتری در مقایسه با چندین روش مطرح موجود برخوردار است.}, keywords_fa = {حس‌گری فشرده, آستانه‌گیری نرم, تبدیل تطبیقی, تُنُکی}, doi = {10.29252/jsdp.17.1.131}, url = {http://jsdp.rcisp.ac.ir/article-1-885-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-885-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {kavoosi, Vali and Dehghani, mohammad javad and Javidan, Rez}, title = {Three Dimensional Localization of an Unknown Target Using Two Heterogeneous Sensors}, abstract ={Heterogeneous wireless sensor networks consist of some different types of sensor nodes deployed in a particular area. Different sensor types can measure different quantity of a source and using the combination of different measurement techniques, the minimum number of necessary sensors is reduced in localization problems. In this paper, we focus on the single source localization in a heterogeneous sensor network containing two types of passive anchor-nodes: Omni-directional and vector sensors. An omni-directional sensor can simply measure the received signal strength (RSS) without any additional hardware. In other side, an acoustic vector sensor (AVS) consists of a velocity-sensor triad and an optional acoustic pressure-sensor, all spatially collocated in a point-like geometry. The velocity-sensor triad has an intrinsic ability in direction finding process. Moreover, despite its directivity, a velocity-sensor triad can isotropically measure the received signal strength and has a potential to be used in RSS-based ranging methods. Employing a heterogeneous sensor-pair consisting of one vector and one omni-directional sensor, this study tries to obtain unambiguity estimation for the location of an unknown source in a three-dimensional (3D) space. Using a velocity-sensor triad as an AVS, it is possible to determine the direction of arrival (DOA) of the source without any restriction on the spectrum of the emitted signal. However, the range estimation is a challenging problem when the target is closer to the omnidirectional sensor than the vector sensor. The existence method proposed for such configuration suffers from a fundamental limitation, namely the localization coverage. Indeed, this algorithm cannot provide an estimate for the target range in 50 percent of target locations due to its dependency to the relative sensor-target geometry. In general, our proposed method for the considered problem can be summarized as follows: Initially, we assume that the target's DOA is estimated using the velocity-sensor triad’s data. Then, considering the estimated DOA and employing the RSS measured by two sensors, we propose a computationally efficient algorithm for uniquely estimation of the target range. To this end, the ratio of RSS measured by two sensors is defined and, then, shown that this power ratio can be expressed as a monotonic function of the target range. Finally, the bisection search method is proposed to find an estimate for the target range. Since the proposed algorithm is based on bisection search method, a solution for the range of the target independent of its location is guaranteed. Moreover, a set of future aspects and trends is identified that might be interesting for future research in this area. Having a low computational complexity, the proposed method can enhance the coverage area mostly two times of that explored by the existence method. The simulated data confirms the speed and accuracy of developed algorithm and shows its robustness against various target ranges and different sensor spacing.}, Keywords = {Heterogeneous network, Unambiguous localization, Vector sensor, RSS, Bisection algorithm}, volume = {17}, Number = {1}, pages = {147-158}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {موقعیت‌یابی سه‌بُعدی یک هدف ناشناخته با استفاده از دو حس‌گر نامتجانس}, abstract_fa ={در شبکه­های حس‌گرغیر‌همگن، برای موقعیت­یابی هدف از چندین نوع گیرنده استفاده می­شود و هر گیرنده می­تواند کمیت متفاوتی از هدف را اندازه­گیری کند. استفاده از چندین کمیت اندازه­گیری‌شده از یک هدف باعث می­‌شود که تخمین موقعیت آن با سادگی و دقت بیشتری انجام شود. در اینجا، موقعیت­یابی هدف در یک فضای سه‌بُعدی با استفاده از یک شبکه غیر‌همگن شامل یک حس‌گر همه‌جهته و یک حس‌گر برداری مورد نظر است. الگوریتم موجود برای چنین شبکه­ای، به موقعیت نسبی هدف و حس‌گرها وابسته بوده و در پنجاه درصد موارد نمی‌تواند جوابی برای فاصله هدف ارایه کند. در الگوریتم پیشنهادی در این مقاله برای به‌دست‌آوردن یک تخمین بدون ابهام از فاصله هدف در هندسه مورد نظر، تنها از توان­های اندازه­گیری‌شده در دو حس‌گر استفاده می­‌شود. در این راستا، ابتدا یک تحلیل تئوری از مسأله انجام گرفته و سپس به‌منظور یافتن فاصله هدف یک الگوریتم جست­وجوی ساده و مؤثر مبتنی بر روش ریشه­یابی تصنیف پیشنهاد می‌شود. در الگوریتم ارایه‌شده، دست‌یابی به یک تخمین یکتا از فاصله هدف مستقل از موقعیت مکانی آن تضمین می­‌شود. شبیه­سازی­های انجام‌شده، سرعت و دقت الگوریتم ارایه‌شده و همچنین مقاوم‌بودن آن در برابر تغییرات فاصله هدف و موقعیت­های مختلف دو حس‌گر را اثبات می‌کند.}, keywords_fa = {شبکه غیر همگن, موقعیت‌یابی بدون ابهام, حس‌گر برداری, شدت سیگنال دریافتی, الگوریتم تصنیف}, doi = {10.29252/jsdp.17.1.147}, url = {http://jsdp.rcisp.ac.ir/article-1-860-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-860-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {MahmoudiNasr, Payam}, title = {A Petri-net Model for Operational Cycle in SCADA Systems}, abstract ={Supervisory control and data acquisition (SCADA) system monitors and controls industrial processes in critical infrastructures (CIs) and plays the vital role in maintaining the reliability of CIs such as power, oil, and gas system. In fact, SCADA system refers to the set of control process, which measures and monitors sensors in remote substations from a control center. These sensors usually have a type of automated response capability when a certain criteria is met. When an abnormal system status occurs, an alarm signal is raised in control center and as a result the operator will be notified. In this way, all normal and abnormal system statuses are monitored in control center. In CI’s application, since several substation resources and their related sensors are too high (because the CI’s grid is often large, complex and wide), the number of alarms is very high. It gets worse when the operator mistakes and as a result, cascading alarms are flooded. In this condition, the rate of raising alarms may be more than clearing them. In SCADA system, alarm clearing is one of the main duties of operators. When an alarm is raised in control center, the operator should clear it as soon as possible. However, the recent reports confirm the poor alarm clearing causes accidents in the SCADA system. As any operator mistake can increase the number of alarms and jeopardize the system reliability, alarms processing and decision-making for clearing them are a stressful and time-consuming for the SCADA operators. In a large and complex CI such as power system, when operators are overwhelmed by the system alarms, they may take wrong decisions and even ignore alarms. Alarm flooding, lots of operator’s workload and his/her fatigue as a result, are the main causes of operator’s mistake. If generating of an alarm in a remote substation is denoted as an operational cycle in an SCADA system until clearing it by the operator in control center, the aim of this paper is modeling the operational cycle by using colored petri nets. The proposed model is based on a general approach which alarm messages are integrated with the operator’s commands. Of course, the model focuses on generating of alarms by substation resources. To verify the proposed model, a real data set of power system of Iran is used and to demonstrate the potential of the proposed model some scenarios about operator’ workload and alarm flooding are simulated.}, Keywords = {Alarm, Modeling, Operational cycle, Petri nets, SCADA}, volume = {17}, Number = {2}, pages = {14-3}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {مدل‌سازی چرخه عملیاتی سامانه اسکادا با استفاده از شبکه‌ پتری}, abstract_fa ={سامانه‌های اسکادا وظیفه کنترل زیرساخت‌های حیاتی را به عهده داشته و مطالعه بر روی آن‌ها از اهمیت فراوانی برخوردار است. در سامانه‌ اسکادا وضعیت سلامت تمامی فرآیندهای صنعتی و تجهیزات میدانی در پست‌های راه دور به‌وسیله رویدادها و هشدارهای دریافتی در مرکز کنترل مورد پایش لحظه‌ای قرار می‌گیرند. اپراتورها با مشاهده رویدادها و هشدارها، دستورهای لازم را به‌منظور مدیریت و حفظ پایداری شبکه صادر می‌کنند. هرگونه تصمیم اشتباه اپراتور برای برطرف‌شدن هشدار می‌تواند موجب ایجاد هشدارهای جدید در شبکه شود. ازآنجاکه هشدارها نقش کلیدی در سامانه اسکادا دارند، مدل‌سازی چرخه عملیاتی سامانه اسکادا برای مدیریت هشدارها تأثیر فراوانی در تحلیل عملکرد اپراتور و بررسی ناهنجاری در شبکه می‌تواند داشته باشد. در این مقاله یک مدل جدید از چرخه عملیاتی سامانه اسکادا از مرحله ایجاد هشدار تا برطرف‌شدن آن توسط اپراتور با استفاده از شبکه‌های پتری رنگی ارائه‌ شده است. به‌منظور ارزیابی مدل پیشنهادی، چند سناریو در چند موردکاوی مختلف بررسی‌شده، و نتایج به‌دست‌آمده نشان می‌دهد که مدل ارائه‌شده از کارایی لازم در شبیه‌سازی رفتارهای پست، شبکه و اپراتور برخوردار است.}, keywords_fa = {چرخه عملیاتی, هشدار, مدل‌سازی, اسکادا, شبکه‌های پتری}, doi = {10.29252/jsdp.17.2.14}, url = {http://jsdp.rcisp.ac.ir/article-1-900-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-900-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Khosravani, bahareh and ghazi-maghrebi, saee}, title = {Proposed Pilot Pattern Methods for Improvement DVB-T System Performance}, abstract ={Recently, orthogonal frequency division multiplexing (OFDM) has been extensively used in communications systems to resist channel impairments in frequency selective channels. OFDM is a multicarrier transmission technology in wireless environment that use a large number of orthogonal subcarriers to transmit information. OFDM is one of the most important blocks in digital video broadcast-terrestrial (DVB-T) system. The goal of this paper is comparing the methods of interpolation in OFDM system that not used channel statistics information. Therefore, we used pilots for obtaining the information of channel, and by the method of estimation without use of channel statistics information, the channel primary frequency response estimated in pilot’s frequencies. Pilots, channel estimation and interpolation methods are key roles in the OFDM block. The number of pilots are different in the OFDM symbol for different pilot patterns.  In this article, we proposed three pilot patterns to improve DVB-T system performance. Our criteria for this purpose are error probability, calculation time, and the number of pilots. We have tested the performance improvement by using two-dimensional (2D) interpolation methods. Obviously, we do not obtain all of our requests and requirements via one pilot pattern. For example, the error may be decreases, but the number of pilots is increased. Therefore, we must select the pilot pattern that achieve the most important goal for us. We have applied six interpolation methods, for 2D interpolation, such as linear, nearest-neighbor, spline, cubic Hermite, cosine and low pass interpolations. We have compared three proposed pilot patterns with the conventional DVB-T pilot pattern in four different channels. In each channel, we have tested 30 interpolation methods. The applied channels are OFDM system with AWGN noise, OFDM system with AWGN noise and Rayleigh fading, DVB-T system with AWGN noise and DVB-T system with AWGN noise and Rayleigh fading. We observed that the best performance happens when we use linear interpolation in the first dimension and cosine interpolation in the second dimension of 2D interpolation. In addition, the worst performance will be happened when Nearest-neighbor interpolation is used in the second dimension of 2D interpolation. In the last step, we compared the proposed pilot patterns with the conventional DVB-T pilot pattern in 2D interpolation method that it leads to better performance in DVB-T system. We observed that the proposed pilot patterns have better performance than the conventional DVB-T pilot pattern. In the DVB-T, movement and velocity are very important and considered in this research. In the second step using DVB-T pilot pattern, we compared 2D interpolation methods in some different Doppler frequencies. Simulation results show that at 3 Doppler frequencies, i.e. 0, 30, 150Hz, the proposed schemes with a linear interpolation has better performance than the conventional method in the DVB-T systems.}, Keywords = {DVB-T, Interpolation, OFDM, Pilot}, volume = {17}, Number = {2}, pages = {32-15}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {ارائه روش‌های جدید الگوی چینش پایلوت به‌منظور بهبود عملکرد سامانه DVB-T}, abstract_fa ={یکی از بلوک­‌های مهم در سامانه DVB-T، بلوک OFDM است. در بلوک OFDM، پایلوت­ها، تخمین کانال و روش‌­های درون‌یابی نقش کلیدی دارند. تعداد پایلوت‌ها در هر سبل OFDM در الگوهای مختلف پایلوت‌ها متفاوت است. در این مقاله روش‌­های الگوی چینش پایلوتی جدیدی ارائه شده تا با استفاده از سه پارامتر احتمال خطا، زمان محاسباتی و تعداد پایلوت‌ها عملکرد سامانه DVB-T بهبود یابد. در این پژوهش بهبود عملکرد با استفاده از روش‌­های مختلف درون‌یابی دوبعدی بررسی شده است. بدیهی است تمام اهداف موردنظر در یک الگو برآورده نمی‌­شود؛ یعنی به‌طور مثال ممکن است، خطا کمتر، اما تعداد پایلوت بیشتر شده باشد؛ بنابراین الگویی را باید پذیرفت که مطابق با هدف مورد نظر باشد. در این پژوهش شش روش درون‌یابی دوبعدیlinear, Nearest-neighbor, spline, Cubic Hermite, cosine  و  low pass  استفاده شده و سه الگوی جدید برای پایلوت‌ها پیشنهاد شده که این سه الگو با الگوهای متداول DVB-T برای چهار کانال مختلف بررسی و برای هر کانال سی روش درون‌یابی آزمایش شده است. چهار کانال استفاده شده عبارتند از کانال سامانه OFDM با نوفه AWGN و سامانه OFDM با نوفه AWGN و محوشدگی، سامانه DVB-T با نوفه AWGN و سامانه DVB-T با نوفه AWGN و محوشدگی. نتایج حاصل از این پژوهش نشان می‌دهد که در بیشتر حالات، روش‌­های درون‌یابی خطی و کسینوسی در بعد دوم بهترین عملکرد را دارند و درون‌یابی نزدیک‌ترین همسایگی در بعد دوم بدترین عملکرد را دارد. درنهایت الگوهای پایلوت پیشنهادی با الگوی پایلوت مرسوم سامانه DVB-T مقایسه و ملاحظه شد الگوهای پایلوت پیشنهادی عملکرد بهتری نسبت به الگوی پایلوت مرسوم سیستم DVB-T دارند. از آن جا که در DVB-T جا‌به‌جایی و سرعت مطرح است، در مرحله دوم این پژوهش روش‌­های درون‌یابی دوبعدی در چند فرکانس داپلر مختلف در سامانه DVB-T با استفاده از الگوی پایلوت آن بررسی شده است. شبیه‌سازی‌ها نشان می‌دهد که در سه فرکانس داپلر صفر، سی و 150 هرتز الگوهای پیشنهادی پایلوت در‌حالی‌که یکی از درون‌یابی‌ها خطی باشد، عملکرد بهتری نسبت به روش متداول در DVB-T دارند.}, keywords_fa = {DVB-T, OFDM, پایلوت و درون‌یابی}, doi = {10.29252/jsdp.17.2.32}, url = {http://jsdp.rcisp.ac.ir/article-1-722-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-722-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {RahimiZadeh, Keyvan and Torkamani, MohammadAli and Dehghani, Abbas}, title = {Mapping of McGraw Cycle to RUP Methodology for Secure Software Developing}, abstract ={Designing a secure software is one of the major phases in developing a robust software. The McGraw life cycle, as one of the well-known software security development approaches, implements different touch points as a collection of software security practices. Each touch point includes explicit instructions for applying security in terms of design, coding, measurement, and maintenance of software. Developers are able to provide secure and robust software by applying such touch points. In this paper, we introduce a secure and robust approach to map McGraw cycle to RUP methodology, named RUPST. The traditional form of RUP methodology is revised based on the proposed activities for software security. RUPST adds activities like security requirements analysis, abuse case diagrams, risk-based security testes, code review, penetration testing, and security operations to the RUP disciplines. In this regard, based on RUP disciplines, new touch points of software security are presented as a table. Also, RUPST adds new roles such as security architect and requirement analyzer, security requirement designer, code reviewer and penetration tester which are presented in the form of a table along with responsibilities of each role. This approach introduces new RUP artifacts for disciplines and defines new roles in the process of secure software design. The offered artifacts by RUPST include security requirement management plan, security risk analysis model, secure software architecture document, UMLSec model, secure software deployment model, code review report, security test plan, security testes procedures, security test model, security test data, penetration report, security risks management document, secure installation and configuration document and security audit report. We evaluate the performance of the RUPST in real software design process in comparison to other secure software development approaches for different security aspects. The results demonstrate the efficiency of   the proposed methodology in developing of a secure and robust software.}, Keywords = {Secure software engineering, software development lifecycle, software design, RUP, artifact}, volume = {17}, Number = {2}, pages = {46-33}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {نگاشت چرخه McGraw به متدولوژی RUPبرای توسعه نرم‌افزار امن}, abstract_fa ={امنیت نرم‌افزار از چالش‌های مهم در توسعه نرم‌افزار است. هر روز آسیب‌پذیری‌ها و نفوذهای زیادی در نرم‌افزارهای مشهور گزارش می‌شود. همان‌‌طور که برای حل مشکل بحران نرم‌افزار بحث مهندسی نرم‌افزار مطرح شد، مهندسی نرم‌افزار امن در کاهش چالش­های امنیتی نرم‌افزار مؤثر است. چرخه McGraw  به‌عنوان یکی از ره‌یافت­‌های­ توسعه نرم‌افزار امن‌ تعدادی نقطه تماس امنیت نرم‌افزار را معرفی می­‌کند که شامل مجموعه‌ای از دستورالعمل‌های صریح و مشخص در راستای اِعمال مهندسی امنیت در نیازمندی‌ها، معماری، طراحی، کد‌نویسی، اندازه‌گیری و نگهداری نرم‌افزار است. نقاط تماس امنیت نرم‌افزار برای استفاده در ساخت نرم‌افزار، مستقل از پروسه نرم‌افزاری است و به هر فرآیند تولید نرم‌افزار قابل‌اعمال است. بنابراین، می‌توان با تغییر چرخه توسعه نرم‌افزار مورد نظر و اعمال نقاط تماس، چرخه توسعه نرم‌افزار امن را ایجاد کرد. در این پژوهش، راه‌کاری برای نگاشت چرخه McGraw به متدولوژی RUP؛ به‌عنوان متدولوژی سنگین وزن توسعه نرم‌افزار؛ و تلفیق این دو متدولوژی در راستای ایجاد یک متدولوژی ساده و کارآمد برای توسعه نرم‌افزار امن (که RUPST نام دارد) ارائه و همچنین، فراورده‌های جدید RUP برای توسعه نرم‌افزار امن به تفکیک هر نظم ارائه و چهار نقش جدید نیز برای انجام فعالیت‌های مرتبط با امنیت نرم‌افزار تعریف می‌شود. راه‌کار پیشنهادی در یک پروژه واقعی در شرکت کارخانجات مخابراتی ایران مورد استفاده و ارزیابی قرار گرفت. دست‌آوردها نشان می‌دهد که بهره‌گیری و اجرای صحیح این ره‌یافت توسط توسعه‌دهندگان، به پیاده‌سازی و توسعه امن‌تر و مستحکم­تر نرم‌افزار منجر می‌شود.}, keywords_fa = {مهندسی نرم‌افزار امن, چرخه توسعه نرم‌افزار, طراحی نرم‌افزار, نقاط تماس, فرآورده}, doi = {10.29252/jsdp.17.2.46}, url = {http://jsdp.rcisp.ac.ir/article-1-917-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-917-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Sherafati, Farimah and Tahmoresnezhad, Jafar}, title = {Image Classification via Sparse Representation and Subspace Alignment}, abstract ={Image representation is a crucial problem in image processing where there exist many low-level representations of image, i.e., SIFT, HOG and so on. But there is a missing link across low-level and high-level semantic representations. In fact, traditional machine learning approaches, e.g., non-negative matrix factorization, sparse representation and principle component analysis are employed to describe the hidden semantic information in images, where they assume that the training and test sets are from same distribution. However, due to the considerable difference across the source and target domains result in environmental or device parameters, the traditional machine learning algorithms may fail. Transfer learning is a promising solution to deal with above problem, where the source and target data obey from different distributions. For enhancing the performance of model, transfer learning sends the knowledge from the source to target domain. Transfer learning benefits from sample reweighting of source data or feature projection of domains to reduce the divergence across domains. Sparse coding joint with transfer learning has received more attention in many research fields, such as signal processing and machine learning where it makes the representation more concise and easier to manipulate. Moreover, sparse coding facilitates an efficient content-based image indexing and retrieval. In this paper, we propose image classification via Sparse Representation and Subspace Alignment (SRSA) to deal with distribution mismatch across domains in low-level image representation. Our approach is a novel image optimization algorithm based on the combination of instance-based and feature-based techniques. Under this framework, we reweight the source samples that are relevant to target samples using sparse representation. Then, we map the source and target data into their respective and independent subspaces. Moreover, we align the mapped subspaces to reduce the distribution mismatch across domains. The proposed approach is evaluated on various visual benchmark datasets with 14 experiments. Comprehensive experiments demonstrate that SRSA outperforms other latest machine learning and domain adaptation methods with significant difference.}, Keywords = {Image classification, Visual domains adaptation, Sparse representation, Subspace alignment}, volume = {17}, Number = {2}, pages = {58-47}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {طبقه‌بندی تصاویر با استفاده از نمایش تُنُک و تطبیق زیرفضا}, abstract_fa ={در بیش‌تر الگوریتم‌های یادگیری ماشین و پردازش تصویر، فرض اولیه بر این است که توزیع احتمال داده‌های آموزشی (دامنه منبع) و آزمایش (دامنه هدف) یکسان است؛ اما در کاربردهای دنیای واقعی، برخی معیارها نظیر حالت تصویر، روشنایی یا کیفیت تصویر، موجب ایجاد اختلاف قابل‌توجهی بین دو مجموعه آموزشی و آزمایش می‌شود. به همین دلیل، اغلب مدل‌های ایجاد‌شده بر روی داده‌های آموزشی عملکرد ضعیفی بر روی داده‌های آزمایش خواهند داشت؛ بااین‌حال‌، روش‌های تطبیق دامنه، راه‌حل بسیار مؤثری برای کاهش اختلاف توزیع بین دامنه‌های آموزشی و آزمایش هستند. در این مقاله یک روش تطبیق دامنه با عنوان نمایش تُنُک و تطبیق زیرفضا (SRSA) پیشنهاد شده است، که با وزن‌دهی مجدد نمونه‌های آزمایش و نگاشت داده‌ها به یک زیرفضای جدید مشکل اختلاف توزیع داده‌ها را به‌خوبی مرتفع می‌سازد. SRSA با استفاده از یک نمایش تُنُک، بخشی از مجموعه داده‌های هدف را که ارتباط قوی‌تری با داده‌های منبع دارند، انتخاب می‌کند؛ علاوه‌بر آن، SRSA با نگاشت داده‌های تُنُک هدف و داده‌های منبع به زیرفضاهای مستقل، اختلاف توزیع آنها را درفضای به‌دست‌آمده کاهش می‌دهد؛ درنهایت با برروی‌هم‌گذاری زیرفضاهای نگاشت‌شده، SRSA اختلاف توزیع بین داده‌های آموزشی و آزمایش را به کمینه می‌رساند. ما روش پیشنهادی خود را با ترتیب‌دادن چهارده آزمایش بر روی پایگاه داده‌های‌ بصری مختلف مورد ارزیابی قرار‌داده و با مقایسه نتایج به‌دست‌آمده، نشان داده‌ایم که SRSA عملکرد بهتری در مقایسه با جدیدترین روش‌های یادگیری ماشین و تطبیق دامنه دارد.}, keywords_fa = {طبقه‌بندی تصویر, تطبیق دامنه‌های بصری, نمایش تُنُک, تطبیق زیرفضا}, doi = {10.29252/jsdp.17.2.58}, url = {http://jsdp.rcisp.ac.ir/article-1-887-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-887-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Karimizadeh, Arezoo and Vali, Mansour and modaresi, mohammadrez}, title = {Symmetry of Frequency information in Right and Left Lung sound and Infection Detection in Cystic Fibrosis Patients}, abstract ={Cystic fibrosis (CF) is the most common autosomal recessive disorder in white skinned individuals. Chronic lung infection is the main cause of mortality in this disease. Approximately 60–75 % of adult CF patients frequently suffer from Pseudomonas aeruginosa (PA) infection that is strongly associated with inflammation, lung destruction, and increased mortality. Therefore, CF patients should be followed up by physicians to diagnose infection in the primary stage, start treatment, and reduce the risk of chronic infection. Although sputum culture is the gold standard for diagnosis of PA infections, a rapid and accurate diagnostic method can facilitate early initiation of appropriate therapy and easy monitoring of the condition. The aim of this study was to diagnose CF patients with infection using their lung sound. In this study, the symmetry of frequency information in right and left lung was investigated in CF patients with positive sputum culture results, negative sputum culture results‎, and patients who underwent treatment with antibiotics. Respiretorysounds were acquired from 34 CF patients (16 female, 18 male) who were being ‎followed-up at the Pediatric Respiratory and Sleep Medicine Research Center of Children's ‎Medical Center. The patient selection was based on their sputum microbiology culture. The selection ‎category was as follows: 12 patients with normal flora culture results and 11 patients with PA ‎infection. Also, respiratory sounds of 11 patients were recorded one month after antibiotic treatment and they used to investigate the effectiveness of the proposed method. In the preprocessing step, cardiac sound was removed, respiratory sound cycles were separated and the signals were divided into 64 milisecond frame and 15 features were extracted from each frame. Differences between these features were computed between right and left lungs for early, middle and late section of the respiratory cycle using the new proposed feature. Then, the best group of features was selected by applying Genetic Algorithm. The selected group of features was fed into Support Vector Machine, K Nearest Neighbor and Naïve Bayesian classifier. Also, an Ensemble classifier was examined. The best result was obtained by Ensemble classifier that diagnosed infection by the accuracy of 91.3% and differentiates a group of CF patients with infection from CF patients who underwent treatment with an accuracy of 90.9%. This study describes a novel method of infection detection in CF patients based only on respiratory sound analysis. The proposed method is a simple and available way for early diagnosis of infection and initiating therapeutic strategies.}, Keywords = {Cystic Fibrosis, Respiratory Sound, Information Symmetry, Ensemble classifier}, volume = {17}, Number = {2}, pages = {70-59}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {تقارن اطلاعات فرکانسی صدای ریه راست و چپ و تشخیص عفونت در بیماران فیبروز کیستیک}, abstract_fa ={بیماری فیبروز کیستیک(‏CF‏ یا ‏Cystic fibrosis‏) شایع‌ترین ‏اختلال چند‌سیستمی است که علت اصلی مرگ و میر ناشی از این بیماری مربوط به ‏عفونت مزمن ریوی و عوارض آن ‏است. حدود60-75% بیماران ‏CF‏ به‌صورت مداوم دچار عفونت ‏سودوموناس می‌شوند؛ لذا بیماران ‏CF‏ باید پیوسته تحت مراقبت پزشک ‏باشند تا در‌صورت بروز عفونت به‌سرعت نسبت به درمان آن ‏اقدام شود. اگر چه کشت خلط یا حلق روش استاندارد تشخیص ‏عفونت است، ولی به‌دست‌آوردن نتیجه آن، زمان‌بر بوده و ‏روشی که وجود عفونت را سریع‌تر تشخیص دهد، باعث ‏سهولت در امر تشخیص و شروع درمان با آنتی‌بیوتیک ‏می‌شود. این مطالعه با هدف استفاده از صدای تنفس بیماران ‏CF‏ برای تشخیص وجود عفونت  و موفقیت درمان انجام شد. به این منظور، تقارن اطلاعات سیگنال صدای ریه ‏راست و چپ در بیماران ‏CF‏ در حالت بدون عفونت، دارای عفونت ‏سودوموناس و نیز پس ‏از ‏درمان عفونت سودوموناس بررسی ‏شد. ابتدا صدای تنفس 34 بیمار CF ثبت و پس از انجام پیش پردازش‌های لازم، 15ویژگی از آنها استخراج و با روش الگوریتم ژنتیک بهترین دسته ویژگی از ویژگی‌‌های به‌دست‌آمده استخراج و با روش کنار‌گذاشتن یک شرکت‌کننده به سه طبقه‌بند ماشین بردار پشتیبان، K نزدیک‌ترین همسایگی و بیزین داده شد. همچنین روش ترکیب سه طبقه‌بند نیز بررسی شد. بهترین نتایج توسط روش ترکیب طبقه‌بندها به‌دست آمد که وجود عفونت با صحت %3/91 و موفقیت درمان با صحت %9/90 تشخیص ‏داده شدند. ‏در این مطالعه برای نخستین‌بار از صدای تنفس بیماران CF برای تشخیص عفونت استفاده شده است. روش پیشنهادی، آسان و در دسترس بوده و می‌تواند در شروع به درمان سریع و پیگیری روند درمان به پزشکان کمک کند.}, keywords_fa = {فیبروز کیستیک, صدای تنفس, تقارن اطلاعاتی, ترکیب طبقه‌بندها}, doi = {10.29252/jsdp.17.2.70}, url = {http://jsdp.rcisp.ac.ir/article-1-894-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-894-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {NematiKhalilAbad, Faezeh and Hadizadeh, Hadi and EbrahimiMoghadam, Abbas and KhademiDarah, Mortez}, title = {Just Noticeable Difference Estimation Using Visual Saliency in Images}, abstract ={Due to some physiological and physical limitations in the brain and the eye, the human visual system (HVS) is unable to perceive some changes in the visual signal whose range is lower than a certain threshold so-called just-noticeable distortion (JND) threshold. Visual attention (VA) provides a mechanism for selection of particular aspects of a visual scene so as to reduce the computational load on the brain. According to the current knowledge, it is believed that VA is driven by “visual saliency”. In a visual scene, a region is said to be visually salient if it possess certain characteristics, which make it stand out from its surrounding regions and draw our attention to it. In most existing researches for estimating the JND threshold, the sensitivity of the HVS has been consider the same throughout the scene and the effects of visual attention (caused by visual saliency) which have been ignored. Several studies have shown that in salient areas that attract more visual attention, visual sensitivity is higher, and therefore the JND thresholds are lower in those points and vice versa. In other words, visual saliency modulates JND thresholds. Therefore, considering the effects of visual saliency on the JND threshold seems not only logical but also necessary. In this paper, we present an improved non-uniform model for estimating the JND threshold of images by considering the mechanism of visual attention and taking advantage of visual saliency that leads to non-uniformity of importance of different parts of an image. The proposed model, which has the ability to use any existing uniform JND model, improves the JND threshold of different pixels in an image according to the visual saliency and by using a non-linear modulation function. Obtaining the parameters of the nonlinear function through an optimization procedure leads to an improved JND model. What make the proposed model efficient, both in terms of computational simplicity, accuracy, and applicability, are: choosing nonlinear modulation function with minimum computational complexity, choosing appropriate JND base model based on simplicity and accuracy and also Computational model for estimating visual saliency  that accurately determines salient areas, Finally, determine the Efficient cost function and solve it by determining the appropriate  objective Image Quality Assessment. To evaluate the proposed model, a set of objective and subjective experiments were performed on 10 selected images from the MIT database. For subjective experiment, A Two Alternative Forced Choice (2AFC) method was used to compare subjective image quality and for objective experiment SSIM and IWSSIM was used. The obtained experimental results demonstrated that in subjective experiment the proposed model achieves significant superiority than other existing models and in objective experiment, on average, outperforms the compared models. The computational complexity of proposed model is also analyzed and shows that it has faster speed than compared models.}, Keywords = {Visual Saliency (VS), Visual Attention (VA), Human Visual System (HVS), Just Noticeable Difference (JND)}, volume = {17}, Number = {2}, pages = {84-71}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {تخمین کمترین تفاوت قابل درک با استفاده از برجستگی بصری در تصاویر}, abstract_fa ={به‌علت وجود برخی محدودیت­های فیزیولوژیکی و فیزیکی مختلف در مغز و چشم، دستگاه بینایی انسان (HVS) قادر به درک برخی تغییرات سیگنال بصری که دامنه آن­ها از یک حد آستانه مشخص (موسوم به آستانه JND) پایین­تر باشند، نیست. در بیش‌تر پژوهش‌های موجود جهت تخمین آستانه JND، حساسیت HVS در تمام صحنه یکسان در نظر گرفته شده و تأثیرات توجه بصری (VA) ناشی از برجستگی بصری (VS) در این پژوهش‌ها لحاظ نشده است. مطالعات مختلف نشان داده­اند که حساسیت بصری در نواحی برجسته که توجه بصری بیشتری را جلب می­‌کنند بیشتر بوده و لذا در آن نقاط آستانه JND پایین­تر است و بالعکس. در این مقاله مدلی محاسباتی برای تخمین JND پیشنهاد می­‌شود که از رابطه بین JND و برجستگی بصری برای بهبود تخمین آستانه JND استفاده می‌­کند. این مدل با استفاده از یک مدل JND یکنواخت کارآمد و با به­‌کارگیری یک تابع مدولاسیون غیر خطی مناسب، آستانه­‌های JND پیکسل­های مختلف در یک تصویر را با توجه به برجستگی بصری آن­ها بهبود می‌دهد. تعیین پارامترهای تابع غیرخطی مدولاسیون در قالب یک مسأله بهینه‌­سازی، مدل‌­سازی می­‌شود که حل آن منجر به یافتن مدل JND بهبودیافته می‌شود. کلید کارآمدی روش پیشنهادی به‌کارگیری سازوکاری است که منجر به استفاده کارآمدتر از برجستگی بصری می­‌شود.آزمایش­‌های انجام‌گرفته نشان‌­دهنده برتری قابل ملاحظه روش پیشنهادی نسبت به روش‌­های مشابه موجود است.}, keywords_fa = {برجستگی بصری (VS), توجه بصری (VA), دستگاه بینایی مغز (HVS), کمترین تفاوت قابل درک (JND)}, doi = {10.29252/jsdp.17.2.84}, url = {http://jsdp.rcisp.ac.ir/article-1-899-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-899-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {VahidiFerdosi, Sedigheh and Amirkhani, Hossei}, title = {Weighted Ensemble Clustering for Increasing the Accuracy of the Final Clustering}, abstract ={Clustering algorithms are highly dependent on different factors such as the number of clusters, the specific clustering algorithm, and the used distance measure. Inspired from ensemble classification, one approach to reduce the effect of these factors on the final clustering is ensemble clustering. Since weighting the base classifiers has been a successful idea in ensemble classification, in this paper we propose a method to use weighting in the ensemble clustering problem. The accuracies of base clusterings are estimated using an algorithm from crowdsourcing literature called agreement/disagreement method (AD). This method exploits the agreements or disagreements between different labelers for estimating their accuracies. It assumes different labelers have labeled a set of samples, so each two persons have an agreement ratio in their labeled samples. Under some independence assumptions, there is a closed-form formula for the agreement ratio between two labelers based on their accuracies. The AD method estimates the labelers’ accuracies by minimizing the difference between the parametric agreement ratio from the closed-form formula and the agreement ratio from the labels provided by labelers. To adapt the AD method to the clustering problem, an agreement between two clusterings are defined as having the same opinion about a pair of samples. This agreement can be as either being in the same cluster or being in different clusters. In other words, if two clusterings agree that two samples should be in the same or different clusters, this is considered as an agreement. Then, an optimization problem is solved to obtain the base clusterings’ accuracies such that the difference between their available agreement ratios and the expected agreements based on their accuracies is minimized. To generate the base clusterings, we use four different settings including different clustering algorithms, different distance measures, distributed features, and different number of clusters. The used clustering algorithms are mean shift, k-means, mini-batch k-means, affinity propagation, DBSCAN, spectral, BIRCH, and agglomerative clustering with average and ward metrics. For distance measures, we use correlation, city block, cosine, and Euclidean measures. In distributed features setting, the k-means algorithm is performed for 40%, 50%,…, and 100% of randomly selected features. Finally, for different number of clusters, we run the k-means algorithm by k equals to 2 and also 50%, 75%, 100%, 150%, and 200% of true number of clusters. We add the estimated weights by the AD algorithm to two famous ensemble clustering methods, i.e., Cluster-based Similarity Partitioning Algorithm (CSPA) and Hyper Graph Partitioning Algorithm (HGPA). In CSPA, the similarity matrix is computed by taking a weighted average of the opinions of different clusterings. In HGPA, we propose to weight the hyperedges by different values such as the estimated clustering accuracies, size of clusters, and the silhouette of clusterings. The experiments are performed on 13 real and artificial datasets. The reported evaluation measures include adjusted rand index, Fowlkes-Mallows, mutual index, adjusted mutual index, normalized mutual index, homogeneity, completeness, v-measure, and purity. The results show that in the majority of cases, the proposed weighted-based method outperforms the unweighted ensemble clustering. In addition, the weighting is more effective in improving the HGPA algorithm than CSPA. For different weighting methods proposed for HGPA algorithm, the best average results are obtained when we use the accuracies estimated by the AD method to weight the hyperedges, and the worst results are obtained when using the normalized silhouette measure for weighting. Finally, among different methods for generating base clusterings, the best results in weighted HGPA are obtained when we use different clustering algorithms to come up with different base clusterings.}, Keywords = {Weighted Ensemble Clustering, Unsupervised Learning, HGPA, CSPA, AD}, volume = {17}, Number = {2}, pages = {100-85}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {ترکیب وزن‌دار خوشه‌بندی‌ها با هدف افزایش صحّت خوشه‌بندی نهایی}, abstract_fa ={با توجه به ماهیت بدون ناظر مسائل خوشه‌بندی و تأثیرگذاری مؤلفه‌های مختلف از جمله تعداد خوشه‌ها، معیار فاصله و الگوریتم انتخابی، ترکیب خوشه‌بندی‌ها برای کاهش تأثیر این مؤلفه‌ها و افزایش صحت خوشه‌بندی نهایی معرفی شده است. در این مقاله، روشی برای ترکیب وزن‌دار خوشه‌بندی‌های پایه با وزن‌دهی به خوشه‌بندی‌ها بر اساس روش AD ارائه شده است. روش AD برای برآورد صحّت انسان‌ها در مسائل جمع­سپاری از هماهنگی یا تضاد بین آرای آنها استفاده می‌کند و با پیشنهاد مدلی احتمالاتی، فرآیند برآورد صحّت را به‌کمک یک فرآیند بهینه‌سازی انجام می‌دهد. نوآوری اصلی این مقاله، تخمین صحت خوشه‌بندی‌های پایه با استفاده از روش AD و استفاده از صحت‌های تخمین زده‌شده در وزن‌دهی به خوشه‌بندی‌های پایه در فرآیند ترکیب است. نحوه تطبیق مسأله خوشه‌بندی به روش برآورد صحّت AD و نحوه استفاده از صحّت‌های برآورد‌شده در فرآیند ترکیب نهایی خوشه‌ها، از چالش‌هایی است که در این پژوهش به آنها پرداخته شده است. چهار روش برای تولید خوشه‌بندی‌های پایه شامل الگوریتم‌های متفاوت، معیارهای فاصله‌ی متفاوت در اجرای k-means، ویژگی‌های توزیع‌شده و تعداد خوشه‌های متفاوت بررسی شده است. در فرآیند ترکیب، قابلیت وزن‌‌دهی به الگوریتم‌های خوشه‌بندی ترکیبی CSPA و HGPA اضافه شده است. نتایج روش پیشنهادی روی سیزده مجموعه داده مصنوعی و واقعی مختلف و بر اساس نُه معیار ارزیابی متفاوت نشان می‌دهد که روش ترکیب وزن‌دار ارائه‌شده در بیش‌تر موارد بهتر از روش ترکیب خوشه‌بندی بدون وزن عمل می‌کند که این بهبود برای روش HGPA نسبت به CSPA بیشتر است.}, keywords_fa = {خوشه‌بندی ترکیبی وزندار, یادگیری بدون نظارت, HGPA, CSPA, AD}, doi = {10.29252/jsdp.17.2.100}, url = {http://jsdp.rcisp.ac.ir/article-1-816-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-816-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Bayat, Reza and Sadeghi, Mehdi and Aref, Mohammad Rez}, title = {Modeling gene regulatory networks: Classical models, optimal perturbation for identification of network}, abstract ={Deep understanding of molecular biology has allowed emergence of new technologies like DNA decryption.  On the other hand, advancements of molecular biology have made manipulation of genetic systems simpler than ever; this promises extraordinary progress in biological, medical and biotechnological applications.  This is not an unrealistic goal since genes which are regulated by gene regulatory networks (GRNs) are the core governors of life processes at the molecular level. In fact, manipulation of GRNs would be the ultimate strategy for optimal purposeful control of cell’s life.  GRNs are in charge of regulating the amounts of all the inter-cellular as well as intra-cellular molecular species produced all the time in all living organisms.  Manipulation of a GRN requires comprehensive knowledge about nodes and interconnections.  This paper deals with both aspects in networks having more than fifty nodes.  In the first part of the paper, restrictions of probabilistic models in modeling node behavior are discussed, i.e.: 1) unfeasibility of reliably predicting the next state of GRN based on its current state, 2) impossibility of modelling logical relations among genes, and 3) scarcity of biological data needed for model identification.  These findings which are supported by arguments from probability theory suggest that probabilistic models should not be used for analysis and prediction of node behavior in GRNs.  Next part of the paper focuses on models of GRN structure.  It is shown that the use of multi-tree models for structure for GRN poses severe limitations on network behavior, i.e. 1) increase in signal entropy while passing through the network, 2) decrease in signal bandwidth while passing through the network, and 3) lack of feedback as a key element for oscillatory and/or autonomous behavior (a requirement for any biological network).  To demonstrate that, these restrictions are consequences of model selection, we use information theoretic arguments.  At the last and the most important part of the paper we look into the gene perturbation experiments from a network-theoretic perspective to show that multi-perturbation experiments are not as informative as assumed so far.  A generally accepted belief among researches states that multi-perturbation experiments are more informative than single-perturbation ones, i.e., multiple simultaneously applied perturbations provide more information than a single perturbation.  It is shown that single-perturbation experiments are optimal for identification of network structure, provided the ultimate goal is to discover correct subnet structures. }, Keywords = {gene regulatory network (GRN), probabilistic model of gene, multi-tree model of GRN structure, Boolean model of gene, optimal perturbation experiment}, volume = {17}, Number = {2}, pages = {112-101}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {مدل‌‌سازی شبکه‌‌های تنظیم ژنی: مدل‌های کلاسیک، اختلال بهینه برای شناسایی شبکه}, abstract_fa ={ارتقای عمق و گستره درک ما از دانش زیست‏شناسی ملکولی، از یک سو امکان بهره‏‌برداری از آن را در توسعه فناوری­هایی مانند رمزگشایی فراهم ساخته است و از سوی دیگر، مداخله در سیستم ژنتیکی را امکان‏‌پذیر می‏سازد که نویدبخش آینده‏ای روشن برای علوم زیستی و پزشکی است. دست‌‌یابی به این هدف با مداخله در شبکه تنظیم ژنی (GRN) امکان‏پذیر می­شود؛ زیرا GRN کنترل‌کننده فعالیت‏های زیستی در سطح ملکولی است. در این مسیر، شناسایی GRN، شامل شناسایی مرز، ساختار و گره‌­های شبکه اهمیت به‏سزایی دارد. در این مقاله به دو جنبه ساختار و گره در مدل‏سازی و شناسایی GRN در شبکه‏های بزرگ (با بیش از پنجاه گره) پرداخته می‏شود. نخست محدودیت‏‌های کاربست مدل‌های احتمالاتی برای گره (ژن) مورد بررسی قرار می‏‌گیرد. همچنین محدودیت‏‌های کاربست مدل چند-درختی برای ساختار GRN مورد بررسی قرار می‏‌گیرد. در بخش اصلی مقاله، مسأله شناسایی GRN با مدل بولی مورد بحث قرار گرفته و نشان داده می‏‌شود که بر‌خلاف تصور معمول، آزمایش بهینه از دید شناسایی ساختار GRN، آزمایش تک‌اختلال است.}, keywords_fa = {شبکه تنظیم ژنی, مدل احتمالاتیِ ژن, مدل چند‌درختیِ ساختار, مدل بولیِ ژن, آزمایش بهینه اختلال}, doi = {10.29252/jsdp.17.2.112}, url = {http://jsdp.rcisp.ac.ir/article-1-918-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-918-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {AsghariBejestani, Mohammad Reza and Mohammadkhani, Gholam Reza and Gorgin, Saeed and Nafisi, Vahid Reza and Farahani, Ghaolam Rez}, title = {Classification of EEG Signals for Discrimination of Two Imagined Words}, abstract ={In this study, a Brain-Computer Interface (BCI) in Silent-Talk application was implemented. The goal was an electroencephalograph (EEG) classifier for three different classes including two imagined words (Man and Red) and the silence. During the experiment, subjects were requested to silently repeat one of the two words or do nothing in a pre-selected random order. EEG signals were recorded by a 14 channel EMOTIV wireless headset. Two combinations of features and classifiers were used: Discrete Wavelet Transform (DWT) features with Support Vector Machine (SVM) classifier and Principle Component Analysis (PCA) features with a Minimum-Distance classifier. Both combinations were capable of discriminating between the three classes much better than the chance level (33.3%), none of them was reliable and accurate enough for a real application though. The first method (DWT+SVM) showed better results. In this case, feature set was D2, D3, D4 and A4 coefficients of 4-level DWT decomposition of the EEG signals, roughly corresponding to major frequency bands (Delta, Theta, Alpha and Beta) of these signals. Three binary SVM machines were used. Each machine was trained to classify between two of the three classes, namely Man/Red, Man/Silence or Red/Silence. Majority Selection Rule was used to determine final class. Once two of these classifiers presented the true class, a win (correct classification) was counted, otherwise a loss (false classification) was considered. Finally, Monte-Carlo Cross Validation showed an overall performance of about 56.8% correct classification which is comparable with the results reported for similar experiments.}, Keywords = {Silent Talk, Imagined Speech, EEG signals, Classification, Brain-Computer interface}, volume = {17}, Number = {2}, pages = {120-113}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {طبقه‌‎بندی سیگنال‎های مغزی EEG برای تشخیص بین دو واژه در گفتار خاموش}, abstract_fa ={در این پژوهش، یک رابط مغز-رایانه در کاربرد مکالمه خاموش برای شناسایی و تفکیک بین دو واژه پیاده‎سازی شده ‎است. در طی آزمایش، بر اساس یک زمان‌بندی مشخص، افراد یکی از دو واژه یا سکوت را  که به‌صورت تصادفی انتخاب شده ‎است، بدون آن‌که برزبان آورند؛ در ذهن خود تکرار می‎کنند و سیگنال‎های مغزی آنان توسط یک دستگاه ثبت EEG آزمایشگاهی چهارده کاناله ثبت می‎شود. پس از پیش‎پردازش و حذف داده‎های مخدوش، ویژگی‎های مناسب از این سیگنال‎ها استخراج و برای شناسایی به یک رده‎بند داده می‎شود. دو ترکیب برای استخراج ویژگی و رده‌بندی انتخاب و بررسی شدند: استخراج ضرایب ویولت همراه با رده‌‎بند SVM و ویژگی حاصل از تحلیل مؤلفه‎های اساسی همراه با رده‌‎بند کمینه فاصله که ترکیب نخست عملکرد بهتری از خود نشان داد. تعداد کل رده‌‎ها در این آزمایش سه عدد بوده که شامل دو واژه منتخب و سکوت می‎باشد. نتایج حاصل، نشان‌دهنده امکان تفکیک واژگان با دقت متوسط 8/56 درصد (بیش از 7/1 برابر نرخ تصادف) است که در سازگاری با نتایج گزارش‌شده در فعالیت‎های مشابه است؛ اما هنوز دقت کافی برای کاربردهای واقعی ندارد.}, keywords_fa = {مکالمه خاموش, رابط‌ ‎مغز-رایانه, تصور گفتار, سیگنال‎های مغزی}, doi = {10.29252/jsdp.17.2.120}, url = {http://jsdp.rcisp.ac.ir/article-1-843-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-843-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {sahlani, hossein and Hourali, maryam and Minaei-Bidgoli, Behrouz}, title = {Corefrence resolution with deep learning in the Persian Labnguage}, abstract ={Coreference resolution is an advanced issue in natural language processing. Nowadays, due to the extension of social networks, TV channels, news agencies, the Internet, etc. in human life, reading all the contents, analyzing them, and finding a relation between them require time and cost. In the present era, text analysis is performed using various natural language processing techniques, one of the challenges in this field is the low accuracy in detecting name entities' reference, which detection process has been named as coreference resolution. Coreference resolution is finding all expressions that refer to a name entity, and two expressions are coreference together when these expressions located in the same coreference cluster.      Coreference resolution could be used in many natural language processing tasks such as question answering, text summarization, machine translation, information extraction, etc. Coreference resolution methods are into two main categories; machine learning and rule-based approaches. In the rule-based approaches for detecting coreferences, a set of rich rule ordinary which written by a specialist is execued. These methods are quick, but these are language-dependent and necessary written to each language firstly again by a specialist. The machine learning method divides into supervised and unsupervised methods, in a supervised approach, it is require to have data labeled by a specialist. Coreference resolution included three main phases: named entities recognition, features extraction of name entities, and analyzes the coreferences, in which the primary phase is feature extraction. After corpus creation, name entities should be recognized in the corpus. This step depends on a corpus, in some corpora entities named as golden data, in this paper, we used RCDAT corpus, which determined name entities itself. After the name entities recognition phase, the mention pairs are determined, and the features are extracted. The proposed method uses two categories of the features: the first is word embedding vector, the second is handcrafted features, which are the distance between the mentions, head matching, gender matching, etc. This paper used a deep neural network to train the features extracted, in the analyze coreferences phase a Feed Forward Neural Network (FFNN) is trained by the candidate mention pairs (extracted features from them) and their labels (coreference / non-coreference or 1/0) so that the trained FFNN assigns a probability (between 0 and 1) to any given mention pair. Then used the graph technique with a threshold level to determine different or compatible name entities in the coreference resolution cluster.  This step creates the graph by using the extracted mention pairs from the previous step. In this graph, nodes are the mention pairs that are clustered by using the agglomerative hierarchical clustering algorithm inorder to locate similar mention pairs in a group. The resulting clusters are considered as coreference resolution chains. In this paper, RCDAT Persian language corpus is used for training the proposed coreference resolution approach and for testing the Uppsala Persian language dataset which is used and in the calculation of the accurate of system, different tools have been taken for features extraction which each of them effects on the accuracy of the whole system. The corpora, tools, and methods used in the system are standard. They are quite comparable to the ACE and Ontonotes corpora and tools used at the same time in the coreference resolution algorithm.  The results of the improvements proposed method (F1 = 62.09) is expressed in the text of the paper.}, Keywords = {Coreference resolution, Deep neural networks, Graph, Named entities ecognition, Information extraction}, volume = {17}, Number = {2}, pages = {138-121}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {مرجع‌گزینی در زبان فارسی با استفاده از شبکه عصبی عمیق}, abstract_fa ={در حال حاضر با توجه به کثرت شبکه‌های اجتماعی و شبکه‌های خبری تلویزیونی، رادیویی، اینترنتی و غیره، خواندن تمام متون مختلف و به‌تبع آن تحلیل آن‌ها و دست‌یابی به ارتباطات این متون نیازمند صرف هزینه زمانی و انسانی بسیار بالا است که در عصر کنونی با استفاده از فن‌های مختلف پردازش زبان طبیعی صورت می‌گیرد، یکی از چالش‌های موجود در این زمینه پایین‌بودن دقت سامانه‌های مرجع‌گزینی است که سبب کشف روابط ناصحیح و یا عدم کشف روابط صحیح می‌شود. مراحل کلی حل مسأله مرجع‌گزینی از سه‌گامِ شناسایی موجودیت­‌های نامدار، استخراج ویژگی‌های موجودیت­‌های نامدار و مرجع‌گزینی آن‌ها تشکیل ‌شده است. موجودیت­های نامدار ویژگی‌های فراوانی دارند، وجود ویژگی‌های مختلف (متناسب و متناقض با مرجع) در گراف‌ها این امکان را می‌دهند که بتوان حد آستانه‌ای را از ترکیب ویژگی‌های مختلف استخراج کرد. در مقاله ارائه‌شده ابتدا پیش‌پردازش‌های مختلف روی پیکره پژوهشگاه خواجه‌نصیر [1] انجام گرفت؛ سپس با استفاده از الگوریتم‌های مبتنی بر شبکه عصبی عمیق داده‌های موجود به بردارهای عددی تبدیل شدند و پس از آن با استفاده از گراف و با ویژگی‌هایی که در متن مقاله عنوان‌شده هرس اولیه انجام گرفت؛ درواقع رویکردهای مبتنی بر گراف، موجودیت‌ها را همچون مجموعه‌ای از عناصر مرتبط با یکدیگر می‌شناسد که تحلیل روابط میان موجودیت‌های اولیه در گراف و وزن‌دهی به این ارتباط‌ها، منجر به استخراج ویژگی‌های سطح بالاتر و مرتبط‌تری می‌‌شود و نیز تناقضات ایجادشده بر اساس کمبود اطلاعات را تا حدودی کاهش می‌دهد. سپس با استفاده از شبکه‌های عصبی، روی پیکره مورداشاره در [30] (پیکره آزمون اپسلا) مرجع‌گزینی انجام گرفت که نتایج حاصل بیان‌گر بهبود روش پیشنهادی (رسیدن به دقت 09/62) است که در متن مقاله به‌طور مشروح بیان‌شده است.}, keywords_fa = {مرجع‌گزینی, گراف, شناسایی موجودیت نامدار, استخراج اطلاعات از متن, شبکه‌های عصبی عمیق}, doi = {10.29252/jsdp.17.2.138}, url = {http://jsdp.rcisp.ac.ir/article-1-888-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-888-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {KuchakiRafsanjani, Marjan and BorumandSaeid, Arsham and Mirzapour, Farzane}, title = {Hybrid multi-criteria group decision-making for supplier selection problem with interval-valued Intuitionistic fuzzy data}, abstract ={The main objectives of supply chain management are reducing the risk of supply chain and production cost, increase the income, improve the customer services, optimizing the achievement level, and business processes which would increase ability, competency, customer satisfaction, and profitability. Further, the process of selecting the appropriate supplier capable of providing buyer's requirements in terms of quality products with suitable price and at a suitable time and size is one of the most essential activities to create an efficient supply chain. Consequently, false decisions in the context of supplier selection would lead to negative effects. Usually, suitable supplier selection methods have been multi-criteria or attribute, so finding the optimal solution for supplier selection is demanding. The customary methods in this field have struggled with quantitative criteria however there are a wide range of qualitative criteria in supplier selection. this article has used interval valued intuitionistic fuzzy sets for selecting the appropriate suppliers, which reflect ambiguity and uncertainty far better than other methods. In this article, trapezoidal fuzzy membership function is used for lingual qualitative values. Goal programming satisfaction function (GPSF) is a kind of technique that helps decision makers in solving problems involving conflicting and competing criteria and objectives. Due to the importance of the issue, in this paper, hybrid approach with a group decision-making in Multiple Criteria Decision Making (MCDM) in the context of a range of interval-valued intuitionistic fuzzy sets is implemented to solve the supplier selection problem. In this model in phase 1, decision makers express their opinion about each alternative based on different attribute qualitatively, and after creating interval valued intuitionistic fuzzy membership, a new variable is defined that via its help, interval-valued intuitionistic fuzzy amounts are calculated for each alternative. because of Having capabilities and comprehensiveness in their inside, not only they are better than other fuzzy sets but also they are the best for tracing the real condition and environment in order to select suppliers. Thereafter, for each alternative upper and lower bonds are calculated based on interval-valued intuitionistic fuzzy amounts. In phase 2, Operator Weighted Average (OWA) algorithm is used to reach a collective consensus. After computing the degree of consensus, closeness coefficients is evaluated within the help of TOPSIS method, which is in fact one of the most practicable methods between multi-criteria decision-making methods, such as SAW, AHP, CP, VIKOR. With regard to closeness coefficient, the amount of closeness between individual and collective’s agreement is accounted. The main aim of this article is optimizing the closeness coefficient. The alternative with maximum closeness coefficient is closer to the ideal solution. The final goal of proposed model is ranking the suppliers, meaning that satisfy the main factors of decision making, which is why GPSF model is used. After giving goal and restrict functions, GPSF model will be solved and rank alternatives. }, Keywords = {Interval-valued intuitionistic fuzzy set, Collective preference, Fuzzy TOPSIS, Multi-criteria, Supplier selection, Goal programming satisfaction function}, volume = {17}, Number = {3}, pages = {3-16}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {تصمیم‌گیری گروهی چند‌معیاره ترکیبی برای مسأله انتخاب تأمین‌کننده با داده‌های فازی شهودی بازه‌ای مقدار}, abstract_fa ={فرآیند انتخاب تأمین­‌کننده مناسب که قادر به فراهم‌کردن نیاز خریدار از نظر محصولات باکیفیت با قیمت مناسب و در یک زمان و حجم مناسب باشد، یکی از ضروری‌­ترین فعالیت‌­ها برای ایجاد یک زنجیره تأمین کارا است. با توجه به اهمیت موضوع، در این مقاله، برای حل مسأله انتخاب تأمین­‌کننده، رویکردی ترکیبی به همراه تصمیم‌­گیری گروهی در مسائل تصمیم­‌گیری چند­معیاره در بستر فازی شهودی بازه‌ای مقدار ارائه شده است. در این روش مقادیر متناسب با هر تأمین­‌کننده در بستر فازی شهودی بازه­ای مقدار مشخص شده است؛ سپس ­اولویت­‌های جمعی متناسب با هر تأمین­‌کننده به‌دست آورده می‌شوند و از روش تاپسیس، ضریب نزدیکی (شاخص شباهت) محاسبه و سپس تأمین‌­کننده‌­ها بر اساس این مقدار ارزیابی می­‌شوند. در انتها از روش برنامه­‌ریزی هدفمند با تابع رضایت­‌بخش برای رتبه­‌بندی نهایی به تأمین­‌کننده‌­ها استفاده می‌شود. مدل پیشنهادی به‌وسیله نرم‌افزار متلب پیاده‌­سازی شده و با طرح سناریویی روند کاری مدل پیشنهادی برای رتبه‌­بندی تأمین­‌کننده‌­ها تشریح شده است.}, keywords_fa = {مجموعه فازی شهودی بازه‌ای مقدار, اولویت‌های جمعی, تاپسیس فازی, معیارهای چند‌گانه, انتخاب تأمین‌کننده, برنامه‌ریزی خطی هدف‌دار}, doi = {10.29252/jsdp.17.3.3}, url = {http://jsdp.rcisp.ac.ir/article-1-941-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-941-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Mavaddati, Samir}, title = {A New Method for Speech Enhancement Based on Incoherent Model Learning in Wavelet Transform Domain}, abstract ={Quality of speech signal significantly reduces in the presence of environmental noise signals and leads to the imperfect performance of hearing aid devices, automatic speech recognition systems, and mobile phones. In this paper, the single channel speech enhancement of the corrupted signals by the additive noise signals is considered. A dictionary-based algorithm is proposed to train the speech and noise models for each subband of wavelet decomposition level based on the coherence criterion. Using the presented learning method, the self-coherence measure between different atoms of each dictionary and mutual coherence between the atoms of speech and noise dictionaries are minimized and lower sparse reconstruction error is yielded. In order to reduce the computation time, a composite dictionary is utilized including only the speech dictionary and one of the noise dictionaries selected corresponding to the noise condition in the test environment. The speech enhancement algorithm is introduced in two scenarios, supervised and semi-supervised situations. In each scenario, a voice activity detector (VAD) scheme is employed based on the energy of sparse coefficient matrices when the observed data is coded over the related dictionary. The presented VAD algorithms are based on the energy of the coefficient matrices in the sparse representation of the observation data over the specified dictionaries. These speech enhancement schemes are different in the mentioned scenarios. In the proposed supervised scenario, domain adaptation technique is employed to transform a learned noise dictionary into an adapted dictionary according to the noise conditions of the test environment. Using this step, the observed data is sparsely coded with low sparse approximation error based on the current situation of the noisy environment. This technique has a prominent role to obtain better enhancement results particularly when the noise signal has non-stationary characteristics. In the proposed semi-supervised scenario, adaptive thresholding of wavelet coefficients is carried out based on the variance of the estimated noise for each frame in different subbands. These implementations are carried out in two different conditions, the training and test steps, as speaker dependent and speaker independent scenarios. Also, different measures are applied to evaluate the performance of the presented enhancement procedures. Moreover, a statistical test is used to have a more precise performance evaluation for different considered methods in the various noisy conditions. The experimental results using different measures show that the presented supervised enhancement scheme leads to much better results in comparison with the baseline enhancement methods, learning-based approaches, and earlier wavelet-based algorithms. These results have been obtained for an extensive range of noise types including the structured, unstructured, and periodic noise signals in different SNR values.}, Keywords = {Speech enhancement, Dictionary learning, Sparse representation, Domain adaptation, Voice activity detector, Wavelet transform}, volume = {17}, Number = {3}, pages = {17-36}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {ارائه یک روش جدید بهسازی گفتار بر مبنای یادگیری مدل ناهمدوس به‌کمک ضرایب تبدیل موجک}, abstract_fa ={بهسازی گفتار یکی از زمینه‌های پرکاربرد در پردازش سیگنال است که در حوزه‌های مختلفی مورد استفاده قرار می‌گیرد. در این مقاله از مفاهیم بازنمایی تُنُک و یادگیری واژه‌نامه به‌منظور حذف نوفه از سیگنال گفتار در فضای ویژگی تبدیل موجک استفاده می‌شود. ساختار مورد نیاز جهت بازنمایی هر مؤلفه از سیگنال به‌کمک مفاهیم بازنمایی تُنُک، براساس تعداد کمی از اتم‌های یادگیری‌شده امکان‌پذیر است. به‌منظور دست‌‌یابی به نتایج مطلوب در بهسازی گفتار، از روال یادگیری واژه‌نامه‌ ناهمدوس بهره گرفته می‌شود. به‌‌کمک ضرایب تبدیل موجک، تجزیه سیگنال در زیرباندهای مختلف که شامل اطلاعات دقیقی از محتوای سیگنال هستند، فراهم می‌شود. در روش پیشنهادی، دو سناریوی نظارت‌شده و نیمه‌نظارت‌شده مورد بررسی قرار گرفته و یک الگوریتم آشکارساز فعالیت گفتاری در هر سناریو با توجه به شرط‌های معرفی‌شده بر اساس واژه‌نامه‌های یادگیری‌شده در گام آموزش، پیشنهاد می‌شود. با استفاده از نتایج خروجی آشکارساز پیشنهادی، سیگنال گفتار تخمینی طی یک روال بهسازی در گام بعد به‌دست خواهد آمد. نتایج گزارش‌شده براساس معیارهای مختلف ارزیابی عملکرد، بر توانایی این روش در زمینه کاهش نوفه سیگنال گفتار تأکید می‌کند. روش‌های پیشنهادی، توانایی بالایی را در‌خصوص کاهش نوفه‌های ناایستا به‌خصوص در مقادیر سیگنال به نوفه پایین دارد.}, keywords_fa = {بهسازی گفتار, بازنمایی تُنُک, واژه‌نامه ناهمدوس, تبدیل موجک, آشکارساز فعالیت گفتار}, doi = {10.29252/jsdp.17.3.17}, url = {http://jsdp.rcisp.ac.ir/article-1-835-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-835-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Ahmadi, Tahere and Karshenas, Hossein and Babaali, Bagher and Alinejad, Batool}, title = {Allophone-based acoustic modeling for Persian phoneme recognition}, abstract ={Phoneme recognition is one of the fundamental phases of automatic speech recognition. Coarticulation which refers to the integration of sounds, is one of the important obstacles in phoneme recognition. In other words, each phone is influenced and changed by the characteristics of its neighbor phones, and coarticulation is responsible for most of these changes. The idea of modeling the effects of speech context, and using the context-dependent models in phoneme recognition is a method which used to compensate the negative effects of coarticulation. According to this method, if two similar phonemes in speech have different contexts, each of them constitute a separate model. In this research, a linguistic method called allophonic modeling has been used to model context effects in Persian phoneme recognition. For this purpose, in the first phase, the rules required for occurrence of various allophones of each phoneme, are extracted from Persian linguistic resources. So each phoneme is considered as a class, consisting of its various context-dependent forms named allophones. The necessary prerequisites for modeling and identifying allophones, is an allophonic corpus. Since there was no such corpus in Persian language, SMALL FARSDAT corpus has been used. This corpus is segmented and labelled manually for each sentence, word and phoneme. So the phonological and lingual context required for the realization of allophones, is implemented in this corpus. For example, the syllabification has been performed on the corpus and then, for each phoneme, its position (first, middle and end) in the word and syllable is specified using different numeric tags. In the next step, allophonic labeling has been performed by searching for each of the allophonic contexts in the corpus. These allophonic corpus is used to model and recognize the allophones of input speech. Finally, each allophone is assigned to a proper phonemic class so phoneme recognition has been done using allophones. The experimental results show a high accuracy of the proposed method in phenome recognition, indicating a significant improvement comparing with other state-of-the-art methods.}, Keywords = {automatic speech recognition, automatic phoneme recognition, context-dependent models, phoneme, allophone, coarticulation}, volume = {17}, Number = {3}, pages = {37-54}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {بازشناسی خودکار واج‌های فارسی با استفاده از مدل‌سازی واج‌گونه‌ها}, abstract_fa ={یکی از مراحل زیربنایی در بازشناسی خودکار گفتار، بازشناسی واج‌ها و از موانع جدی برای بازشناسی واج‌ها، هم‌تولیدی است. یک روش برای جبران تأثیر هم‌تولیدی، استفاده از مدل‌های وابسته به بافت در بازشناسی واج‌هاست. در این پژوهش، از یک روش زبان‌شناختی برای مدل‌سازی واج‌گونه‌ها استفاده شده است. بدین‌منظور ابتدا قواعد وقوع واج‌گونه‌ها در زبان فارسی استخراج و مشخص شده است که هر واج چه واج‌گونه‌هایی دارد. برای مدل‌سازی و شناسایی واج‌گونه‌ها، یک پیکره واج‌گونه‌ای لازم است که به‌‌منظور تولید آن، از پیکره فارس‌دات کوچک استفاده و برچسب‌گذاری واج‌گونه‌ای آن انجام و از این پیکره‌، برای مدل‌سازی و سپس شناسایی واج‌گونه‌های مختلف گفتار ورودی استفاده شده است. درنهایت، با قرار‌گرفتن هر یک از واج‌گونه‌های شناسایی‌شده در دسته واجی مربوط به خود، بازشناسی واج‌ها از مسیر واج‌گونه‌ها انجام شده است. با این روش، دقت بازشناسی واج‌ها در زبان فارسی در مقایسه با بهترین نتایج گزارش‌شده تاکنون، بهبود قابل‌ملاحظه‌ای نشان داده است.}, keywords_fa = {بازشناسی خودکار گفتار, بازشناسی خودکار واج, مدل‌های وابسته به بافت, واج, واج‌گونه, هم‌تولیدی}, doi = {10.29252/jsdp.17.3.37}, url = {http://jsdp.rcisp.ac.ir/article-1-903-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-903-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Bouyer, Asgarali and Norouzi, Somayeh}, title = {Sampling from social networks’s graph based on topological properties and bee colony algorithm}, abstract ={In recent years, the sampling problem in massive graphs of social networks has attracted much attention for fast analyzing a small and good sample instead of a huge network. Many algorithms have been proposed for sampling of social network’ graph. The purpose of these algorithms is to create a sample that is approximately similar to the original network’s graph in terms of properties such as degree distribution, clustering coefficient, internal density and community structures, etc. There are various sampling methods such as random walk-based methods, methods based on the shortest path, graph partitioning-based algorithms, and etc. Each group of methods has its own pros and cones. The main drawback of these methods is the lack of attention to the high time complexity in making the sample graph and the quality of the obtained sample graph. In this paper, we propose a new sampling method by proposing a new equation based on the structural properties of social networks and combining it with bee colony algorithm. This sampling method uses an informed and non-random approach so that the generated samples are similar to the original network in terms of features such as network topological properties, degree distribution, internal density, and preserving the clustering coefficient and community structures. Due to the random nature of initial population generation in meta-heuristic sampling methods such as genetic algorithms and other evolutionary algorithms, in our proposed method, the idea of ​​consciously selecting nodes in producing the initial solutions is presented. In this method, based on the finding hub and semi-hub nodes as well as other important nodes such as core nodes, it is tried to maintain the presence of these important nodes in producing the initial solutions and the obtained samples as much as possible. This leads to obtain a high-quality final sample which is close to the quality of the main network. In this method, the obtained sample graph is well compatible with the main network and can preserve the main characteristics of the original network such as topology, the number of communities, and the large component of the original graph as much as possible in sample network. Non-random and conscious selection of nodes and their involvement in the initial steps of sample extraction have two important advantages in the proposed method. The first advantage is the stability of the new method in extracting high quality samples in each time. In other words, despite the random behavior of the bee algorithm, the obtained samples in the final phase mostly have close quality to each other. Another advantage of the proposed method is the satisfactory running time of the proposed algorithm in finding a new sample. In fact, perhaps the first question for asking is about time complexity and relatively slow convergence of the bee colony algorithm. In response, due to the conscious selection of important nodes and using them in the initial solutions, it generates high quality solutions for the bee colony algorithm in terms of fitness function calculation. The experimental results on real world networks show that the proposed method is the best to preserve the degree distribution parameters, clustering coefficient, and community structure in comparison to other method.}, Keywords = {Sampling, Social networks, Clustering coefficient, Artificial Bee Colony}, volume = {17}, Number = {3}, pages = {55-70}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {نمونه‌گیری از گراف شبکه‌های اجتماعی براساس ویژگی‌های توپولوژیکی و الگوریتم کلونی زنبور عسل}, abstract_fa ={با توجه به رشد سریع شبکه‌های اجتماعی در چند سال اخیر، مسأله نمونه‌گیری از گراف‌های بسیار بزرگ شبکه­های اجتماعی با هدف تجزیه و تحلیل سریع شبکه بر اساس نمونه­های کوچک، اهمیت خاصی پیدا کرده است. مطالعات زیادی در این راستا انجام شده است، ولی آنها تا حد زیادی با مشکل انتخاب تصادفی، عدم حفظ ویژگی‌های شبکه­های پیچیده در گراف حاصل و یا صرف هزینه زمانی بالا برای استخراج گراف نمونه مواجه هستند. در این مقاله یک روش نمونه­گیری جدید را برای نخستین‌­بار با ارائه یک رابطه جدید مبتنی بر ویژگی‌های ساختاری برای مشخص‌کردن اهمیت گره‌ها و استفاده از الگوریتم کلونی زنبور عسل پیشنهاد می­کنیم. این روش نمونه­گیری با ارائه یک رویکرد آگاهانه غیرتصادفی در نمونه­گیری سعی دارد تا نمونه حاصله از لحاظ ویژگی‌هایی مانند توپولوژی شبکه، توزیع درجه، تراکم داخلی، درجه ورودی و خروجی و غیره شباهت زیادی با شبکه اصلی داشته باشد. نتایج حاصل، برتری روش پیشنهادی را از لحاظ حفظ ویژگی‌های توزیع درجه، ضریب خوشه­بندی و غیره در نمونه گراف به‌دست‌آمده نشان می­دهد.}, keywords_fa = {نمونه‌گیری, شبکه‌های اجتماعی, ضریب خوشه‌بندی, کلونی زنبور عسل}, doi = {10.29252/jsdp.17.3.55}, url = {http://jsdp.rcisp.ac.ir/article-1-1009-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-1009-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Rezaeian, Mohammad Rez}, title = {Analytical determination of the chemical exchange saturation transfer (CEST) contrast in molecular magnetic resonance imaging}, abstract ={Magnetic resonance based on molecular imaging allows tracing contrast agents thereby facilitating early diagnosis of diseases in a non-invasive fashion that enhances the soft tissue with high spatial resolution. Recently, the exchange of protons between the contrast agent and water, known as the chemical exchange saturation transfer (CEST) effect, has been measured by applying a suitable pulse sequence to the magnetic resonance imaging (MRI) scanner. CEST MRI is increasingly used to probe mobile proteins and microenvironment properties, and shows great promise for tumor and stroke diagnosis. This effect leads to a reduction in magnetic moments of water causing a corresponding decrease in the gray scale intensity of the image, providing a negative contrast in the CEST image. The CEST effect is complex, and it depends on the CEST agent concentration, exchange rates, the characteristic of the magnetization transfer (MT), and the relaxation properties of the tissue. The CEST contrast is different from the inherent MT of macromolecule bounded protons which evidently occurs as a dipole-dipole interaction between water and macromolecular components. Recently it was shown that CEST agents can be strongly affected by the MT and direct saturation effects, so corrections are needed to derive accurate estimates of CEST contrast. Specifically, the existence of an analytical relation between the chemical exchange rate and physiological parameters such as the core temperature, glucose level, and PH has generated more interest in quantification of the CEST contrast. The most important model was obtained by analyzing water saturation spectrum named magnetization transfer ratio spectrum that was quantified by solving Bloch equations. This paper provides an analytical closed-formula of CEST contrast under steady state and transient conditions based on the eigenspace solution of the Bloch-McConnell equations for both of the MT and CEST effects as well as their interactions. In this paper, the CEST contrast has been modeled in two- and three-pool systems using measured (experimental- real data) and fitted data similar to the muscle tissue by considering interfering factors. The resulting error was characterized by an average of relative sum-square between three experimental data and fitted CEST contrast based on the proposed formulation lower than 4 percent. For further validation, these formulations were compared to the empirical formulation of the CEST effect based on a diamagnetic contrast agent introduced in the two-pool system. Using the proposed analytical expression for the CEST contrast, we optimized critical parameters such as concentration contrast agent, chemical exchange rate and characteristics of the electromagnetic radio frequency pulse via amplitude and pulse width in the rectangular pulse.}, Keywords = {Chemical exchange saturation transfer, Bloch-McConnell equations, Magnetization transfer, Numerical solution, Z-spectra modeling}, volume = {17}, Number = {3}, pages = {71-86}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {تعیین کنتراست CEST به روش تحلیلی در تصویربرداری مولکولی تشدید مغناطیسی}, abstract_fa ={تصویربرداری مولکولی به روش تشدید مغناطیسی با ردیابی عامل‌های کنتراست، امکان تشخیص زود‌هنگام بیماری‌ها به شیوه­ای غیر‌تهاجمی را فراهم کرده است. درهمین‌اواخر با طراحی رشته پالس تصویربرداری مناسب بر روی پویش‌گر تشدید مغناطیسی، امکان اندازه‌گیری میزان تبادل شیمیایی بین عامل کنتراست و آب که به پدیده انتقال اشباع به‌واسطه تبادل شیمیایی (CEST) مشهور است، امکان‌پذیر شده است. اثر CEST منجر به کاهش تعداد هیدروژن­های آب و پایین­آمدن شدت روشنایی تصویر تشدید مغناطیسی می‌شود؛ لذا به این اثر کنتراست منفی CEST هم گفته می­شود. وجود رابطه­ای تحلیلی بین نرخ تبادل شیمیایی و شاخص­های بالینی (دما، مصرف گلوکز، pH و موارد دیگر)، علاقه‌مندی به اندازه‌گیری و کمّی­سازی کنتراست CEST را افزایش داده است. این پژوهش یک فرمول ریاضی بسته دقیق از کنتراست CEST در حالت­های گذرا و دایمی ارایه می­دهد. در این مطالعه با شناسایی عوامل تخریبی مزاحم، مانند انتقال مغناطیس شوندگی توسط ماکرومولکول‌ها (MT) و اثر اشباع مستقیم آب، کنتراست CEST در مدل‌های دو و سه‌حوضچه­ای با استفاده از داده­های پارامتری برگرفته از بافت بدن و داده­های ناشی از مشاهدات تجربی، مدل‌سازی می­شود. تطابق کنتراست CEST پیشنهادی با روش اندازه­گیری غیر­متقارن که مورد استناد بسیاری از پژوهش‌گران است، برای عامل‌های کنتراست پارامگنتیک در یک مدل سه‌حوضچه‌ای بررسی شده است. میزان خطای نسبی برازش به‌طور متوسط بر روی سه دسته داده تجربی از چهار درصد کمتر بود؛ علاوه‌بر آن سازگاری مقبولی بین کنتراست CEST پیشنهادی با یک فرمول تجربی بر اساس داده­های مبتنی بر عامل­های دیامگنتیک در مدل دو‌حوضچه­ای هم دیده می­شود. با دست‌یابی به این رابطه تحلیلی از کنتراست CEST، امکان بهینه­سازی و درک نحوه وابستگی آن به پارامترهای اثرگذاری مانند میزان غلظت عامل کنتراست، نرخ تبادل شیمیایی و ویژگی­های پالس الکترومغناطیسی (مانند دامنه و عرض پالس در پالس­های مستطیلی) فراهم می­‌شود.}, keywords_fa = {انتقال اشباع و مغناطیس شوندگی, حل عددی, طیف Z, کنتراست CEST, معادلات بلاخ مک کانل}, doi = {10.29252/jsdp.17.3.71}, url = {http://jsdp.rcisp.ac.ir/article-1-994-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-994-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Sekhavat, Yoones and Namani, Mohammad Sadegh}, title = {Believable Visual Feedback in Motor Learning Using Occlusion-based Clipping in Video Mapping}, abstract ={Gait rehabilitation systems provide patients with guidance and feedback that assist them to better perform the rehabilitation tasks. Real-time feedback can guide users to correct their movements. Research has shown that the quality of feedback is crucial to enhance motor learning in physical rehabilitation. Common feedback systems based on virtual reality present interactive feedback in a monitor in front of a user. However, in this technique, there is a gap between where the feedback is presented and where the actual movement occurs. In particular, there is a discrepancy between where the actual movement occurs (e.g., on a treadmill) and the place of presenting feedback (e.g., a screen in front of the user). As a result, the feedback is not provided in the same location, which requires users perform additional cognitive processing to understand and apply the feedback. This discrepancy is misleading and can consequently result in difficulties to adapt the changes in rehabilitation tasks. In addition, the occlusion problem is not well handled in existing feedback systems that results in misleading the users to assume that the obstacle is on the foot. To address this problem, we need to make an illusion of putting a foot on the obstacle. In this paper, we propose a visual feedback system based on video mapping to provide a better understanding of the relationship between body perception and movement kinematics. This system is based on Augmented Reality (AR) in which visual cues in the form of light are projected on the treadmill using video projectors. In this system, occlusion-based clipping is used to enhance the believability of the feedback. We argue that this system contributes to the correct execution of rehabilitation exercises by increasing patients’ awareness of gait speed and step length. We designed and implemented two prototypes including the video projection with occlusion-based clipping (OC) and a prototype with no occlusion-based clipping (NOC). A set of experiments were performed to assess and compare the ability of unimpaired participants to detect real-time feedback and make modifications to gait using our feedback system. In particular, we asked 24 unimpaired participants to perform stepping and obstacle avoidance tasks. Since the focus of the paper is the quality of the feedback than the effect of feedback on training in long-term, unimpaired participants were recruited for this study. In the experiments, a motion capture device was used to measure the performance of participants. We demonstrated that our system is effective in terms of steps to adapt changes, obstacles to adapt changes, normalized accumulative deviation, quality of user experience, and intuitiveness of feedback. The results showed that projection-based AR feedback can successfully guide participants through a rehabilitation exercise. In particular, the results of this study showed statistically significant differences between the fault-rate of participants using OC and NOC prototypes in the stepping (p=0.0031) and obstacle avoidance (0.021) tasks. In addition, participates rated OC more intuitive than NOC in terms of the quality of feedback. Our feedback system showed a significant improvement in participants’ ability to adapt the changes while walking on the treadmill.}, Keywords = {Video mapping, real-time feedback, motor learning, augmented reality}, volume = {17}, Number = {3}, pages = {87-100}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {نمایش باورپذیر بازخورد تصویری در سامانه توان‌بخشی با استفاده از انسداد تصویر در نگاشت ویدیو}, abstract_fa ={کیفیت بازخورد تصویری و نمایش مناسب آن تأثیر به‌سزایی در انجام درست حرکات توان‌بخشی با استفاده از سامانه‌­های توان‌بخشی حرکتی دارند. یکی از مشکلات اساسی سامانه­‌های معمول مبتنی بر واقعیت مجازی آن است که محل وقوع حرکت بر روی زمین و یا تردمیل بوده، درحالی‌که محل نمایش بازخورد این حرکت در صفحه‌نمایش روبه­‌روی بیمار است. در این مقاله، روشی جدید برای نمایش بازخوردهای حرکت با استفاده از نگاشت ویدیو بر روی صفحه تردمیل ارائه شده که سعی در کم‌کردن فاصله میان محل وقوع حرکت و محل نمایش بازخورد آن حرکت برای دریافت بهتر بازخورد دارد. در این روش، بازخورد تصویری با استفاده از ویدیو‌پروژکتور بر روی صفحه تردمیل نمایش داده می­‌شود. ویژگی مهم این روش در مقایسه با کارهای قبلی، ارایه روشی برای باورپذیر‌کردن بازخورد با استفاده از انسداد تصویر است. پس از طراحی و پیاده‌­سازی سامانه بازخورد با انسداد تصویر و بدون انسداد تصویر، یک مطالعه کاربری برای ارزیابی سامانه و مقایسه آنها انجام شد. در این مطالعه، از 24 نفر از شرکت‌کنندگان بدون مشکل حرکتی خواسته شد تا تمرین­‌های قدم‌زدن و عبور از موانع بر اساس پروتکل طراحی‌شده انجام دهند. با توجه به اینکه هدف این مقاله تنها ارایه روشی برای بهبود کیفیت نمایش بازخورد حرکتی بوده و نه بررسی تأثیر سامانه ارایه‌شده بر روی بهبود و توان‌بخشی بیماران، از شرکت‌کنندگان بدون مشکل حرکتی برای ارزیابی این مطالعه استفاده شده است. نتایج حاصل از این پژوهش حاکی از آن است که اختلاف معنادار آماری میان نرخ خطای سامانه نگاشت ویدیو مبتنی بر انسداد تصویر و سامانه بدون انسداد تصویر در تمرین قدم‌زدن (p=0.0031) و عبور از موانع (p=0.021) وجود دارد. از لحاظ شهودی‌بودن بازخورد بر اساس خود‌اظهاری شرکت‌کنندگان در پژوهش، نتایج حاصل بیان‌گر برتری معنادار آماری (p=0.011) سامانه نگاشت ویدیو با انسداد تصویر در مقایسه با سامانه بدون انسداد تصویر است.}, keywords_fa = {نگاشت ویدیو, بازخورد تصویری, سامانه‌های توان‌بخشی, انسداد تصویر, واقعیت مجازی}, doi = {10.29252/jsdp.17.3.87}, url = {http://jsdp.rcisp.ac.ir/article-1-915-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-915-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Kazemitabar, Javad and Tavakkoli, Mitr}, title = {A Bayesian approach for image denoising in MRI}, abstract ={Magnetic Resonance Imaging (MRI) is a notable medical imaging technique that is based on Nuclear Magnetic Resonance (NMR). MRI is a safe imaging method with high contrast between soft tissues, which made it the most popular imaging technique in clinical applications. MR Image's visual quality plays a vital role in medical diagnostics that can be severely corrupted by existing noise during the acquisition process. Therefore, the denoising of these images has great importance in medical applications. During the last decades, lots of MR denoising approaches from various groups of techniques have been proposed that can be classified into two general groups of acquisition-based noise reduction and post-acquisition denoising methods. The first group's approaches will add imaging time and led to a much time-consuming process. The second group's issues are its complicated mathematical equations required for image denoising, in which stochastic algorithms are usually required to solve these complex equations. This study aims to find an appropriate statical post-acquisition denoising MR imaging method based on the Bayesian technique. Finding the appropriate prior density function also has great importance since the Bayesian technique's performance is related to its prior density function. In this study, the uniform distribution has been applied as the prior density function. The prior uniform distribution function will reduce the Bayesian algorithm to its simplest possible state and lower computational complexity and time consumption. The proposed method can solve the numerical problems with an adequate timing process without complex algorithms and remove noise in less than 120 seconds on average in all cases. To quantitatively assess image improvement, we used the Structural Similarity Function (SSIM) in MATLAB. The similarity with this function shows an average improvement of more than 0.1 in all images. Considering the results, it can be concluded that combining the uniform distribution function as a prior density function and the Bayesian algorithm can significantly reduce the image's noise without the time and computational cost.}, Keywords = {Bayesian estimation, Rician distribution, Magnetic Resonance Imaging}, volume = {17}, Number = {3}, pages = {101-108}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {کاهش نوفه در تصویربرداری تشدید مغناطیسی با استفاده از الگوریتم تخمین بیزین}, abstract_fa ={تصویربرداری تشدید مغناطیسی[1] (MRI) که اساس آن بر پایه تشدید مغناطیسی هسته‎ای بنا نهاده شده، به‎عنوان یک روش بارز در زمینه کاربردهای پزشکی مطرح است. به‎دلیل وضوح مناسب و فناوری کم‌ضرر،MRI در کاربردهای بالینی بسیار مورد توجه قرار گرفته است. کیفیت تصاویر MR نقش کلیدی‎ در نحوه تشخیص پزشک ایفا می‎کند؛ اما به‎دلیل ایجاد نوفه حین فرآیند تصویربرداری، اغلب کیفیت تصاویر دریافتی کاهش می‌یابد. از این‌رو حذف نوفه جهت ارتقای قابلیت تشخیص بسیار مورد توجه قرار گرفته است. نوفه موجود در تصاویر MR که منجر به کاهش شدت نور تصویر شده و بایاس وابسته به سیگنال ایجاد می‎کند، به بهترین شکل با تابع توزیع رایسین مدل می‌شود. به‌طور‌کلی هدف از این پژوهش پیداکردن تابع چگالی احتمال پیشین مناسبی برا یسیگنال بدون نوفه[2] MR و استفاده از تخمین بیزین در راستای کاهش نوفه تصویر است که در مقایسه با سایر روش­های گروه آماری روشی کم‌هزینه با پیچیدگی محاسباتی پایین­تر است. [1] Magnetic Resonance Imaging [2] Noiseless signal}, keywords_fa = {تخمین بیزین, توزیع رایس, تصویربرداری تشدید مغناطیسی}, doi = {10.29252/jsdp.17.3.101}, url = {http://jsdp.rcisp.ac.ir/article-1-893-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-893-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Ghofrani, Faegheh and Amini, Mortez}, title = {Privacy Preserving Dynamic Access Control Model with Access Delegation for eHealth}, abstract ={eHealth is the concept of using the stored digital data to achieve clinical, educational, and administrative goals and meet the needs of patients, experts, and medical care providers. Expansion of the utilization of information technology and in particular, the Internet of Things (IoT) in eHealth, raises various challenges, where the most important one is security and access control. In this regard, different security requirements have been defined; such as the physician’s access to the patient’s EHR (electronic health record) based on the physician’s physical location, detection of emergency conditions and dynamically granting access to the existing physician or nurse, preserving patients’ privacy based on their preferences, and delegation of duties and related permissions. In security and access control models presented in the literature, we cannot find a model satisfying all these requirements altogether. To fill this gap, in this paper, we present a privacy preserving dynamic access control model with access delegation capability in eHealth (called TbDAC). The proposed model is able to tackle the security challenges of these environments when the physicians and nurses access the patients’ EHR. The model also includes the data structures, procedures, and the mechanisms necessary for providing the access delegation capability. The proposed access control model in this paper is in fact a family of models named TbDAC for access control in eHealth considering the usual hospital procedures. In the core model (called TbDAC0), two primitive concepts including team and role are employed for access control in hospitals. In this model, a set of permission-types is assigned to each role and a medical team (including a set of hospital staff with their roles) is assigned to each patient. In fact the role of a person in a team determines his/her permissions on the health information of the patient. Since patients’ vital information is collected from some IoT sensors, a dynamic access control using a set of dynamic and context-aware access rules is considered in this model. Detecting emergency conditions and providing proper permissions for the nearest physicians and nurses (using location information) is a key feature in this model. Since health information is one of the most sensitive individuals’ personal information, the core model has been enhanced to be a privacy preserving access control model (named TbDAC1). To this aim, the purpose of information usage and the privacy preferences of the patients are considered in the access control enforcement procedure. Delegation of duties is a necessity in medical care. Thus, we added access delegation capability to the core model and proposed the third member of the model family, which is named TbDAC2. The complete model that considers all security requirements of these environments including emergency conditions, privacy, and delegation is the last member of this family, named TbDAC3. In each one of the presented models, the therapeutic process carried out in the hospitals, the relational model, and the entities used in the model are precisely and formally defined. Furthermore in each model, the access control process and the dynamic access rules for different situations are defined. Evaluation of the proposed model is carried out using three approaches; comparing the model with the models proposed in related research, assessing the real-world scenarios in a case study, and designing and implementing a prototype of an access control system based on the proposed model for mobile Android devices. The evaluations show the considerable capabilities of the model in satisfying the security requirements in comparison to the existing models which proposed in related research and also its applicability in practice for different simple and complicated access scenarios.}, Keywords = {eHealth, IoT, Dynamic Access Control, Privacy, Access Delegation}, volume = {17}, Number = {3}, pages = {109-140}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {مدل کنترل دسترسی پویای حافظ حریم خصوصی با قابلیت وکالت دسترسی درسلامت الکترونیکی}, abstract_fa ={گسترش استفاده از فناوری اطلاعات و به‌طور خاص اینترنت اشیا در حوزه سلامت الکترونیکی، مسائل مختلفی را به‌همراه دارد که از مهم‌ترین آنها مسأله امنیت و کنترل دسترسی است. در این راستا نیازمندی‌های مختلفی از جمله مسأله دسترسی پزشک به پرونده بیمار بر اساس موقعیت فیزیکی پزشک، مسأله تشخیص شرایط اضطراری و اعطای پویای دسترسی موقت به پزشک حاضر، حفظ حریم خصوصی بیمار بر اساس ترجیحات وی و مسأله اعطای وکالت دسترسی به حقوق دسترسی پزشک دیگر مطرح است که در مدل‌های ارائه‌شده تاکنون پوشش داده نشده است. در این مقاله یک مدل کنترل دسترسی پویا و حافظ حریم خصوصی با قابلیت وکالت دسترسی در سلامت الکترونیکی با نام TbDAC ارائه شده است؛ به‌طوری‌که هنگام دسترسی پزشکان و پرستاران به پرونده بیمار بتواند چالش‌های امنیتی مطرح در این محیط‌ها را برطرف‌کند. با پیاده‌سازی یک سامانه کنترل دسترسی بر اساس مدل پیشنهادی و بررسی سناریوهایی واقعی در محیط بیمارستانی با استفاده از آن، کاربرد عملی این مدل در محیط واقعی و کارایی آن نشان داده شده است.}, keywords_fa = {سلامت الکترونیکی, اینترنت اشیا, کنترل دسترسی پویا, حفظ حریم خصوصی, وکالت دسترسی}, doi = {10.29252/jsdp.17.3.109}, url = {http://jsdp.rcisp.ac.ir/article-1-916-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-916-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Ahmadi, Morteza ali and Dianat, Rouhollah}, title = {Introducing a method for extracting features from facial images based on applying transformations to features obtained from convolutional neural networks}, abstract ={In pattern recognition, features are denoting some measurable characteristics of an observed phenomenon and feature extraction is the procedure of measuring these characteristics. A set of features can be expressed by a feature vector which is used as the input data of a system. An efficient feature extraction method can improve the performance of a machine learning system such as face recognition in the image field. Most of the feature extraction methods in facial images are categorized as geometric feature extractor methods, linear transformation-based methods and neural network-based methods. Geometric features include some characteristics of the face such as the distance between the eyes, the height of the nose and the width of the mouth. In the second category, a linear transformation is applied to the original data and displaces them to a new space called feature space. In the third category, the last layer in the network, which is used for categorization, is removed, and the penultimate layer output is used as the extracted features. Convolutional Neural Networks (CNNs) are one the most popular neural networks and are used in recognizing and verifying the face images, and also, extracting features. The aim of this paper is to present a new feature extraction method. The idea behind the method can be applied to any feature extraction problem. In the proposed method, the test feature vector is accompanied with the training feature vectors in each class. Afterward, a proper transform is applied on feature vectors of each class (including the added test feature vector) and a specific part of the transformed data is considered. Selection of the transform type and the other processing, such as considering the specific part of the transformed data, is in such a way that the feature vectors in the actual class are encountered with less disturbing than the other ones. To meet this goal, two transformations, Fourier and Wavelet, have been used in the proposed method. In this regard, it is more appropriate to use transformations that concentrate the energy at low frequencies. The proposed idea, intuitively, can lead to improve the true positive (TP) rate. As a realization, we use the idea in CNN-based face recognition problems as a post-processing step and final features are used in identification. The experimental results show up to 3.4% improvement over LFW dataset.}, Keywords = {Feature extraction - Convolutional neural networks - Wavelet transform - Fourier transform}, volume = {17}, Number = {3}, pages = {141-156}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {ارائه یک روش استخراج ویژگی از تصاویر چهره مبتنی بر اعمال تبدیل روی ویژگی‌‌های به‌‌دست‌‌آمده از شبکه‌‌های عصبی کانولوشن}, abstract_fa ={در این مقاله، یک روش استخراج ویژگی از داده ارائه شده است. ایده پیشنهادی، کلی بوده و قابل به‌کارگیری در استخراج ویژگی از هر نوع داده‏ است. در این روش، بردار ویژگی آزمون، به ویژگی‏‌های موجود در همه دسته‏‌ها اضافه و سپس تبدیل مناسبی روی مجموعه ویژگی‌‏های هر دسته (با احتساب بردار آزمون اضافه‌شده)، اعمال می‏‌شود. نحوه اعمال تبدیل و مجموعه اقدامات بعد از آن، به‌نحوی صورت می‏‌گیرد که موجب می‏‌شود ویژگی‏‌های موجود در دست‌ه‏ای که داده آزمون در‌واقع متعلق به آن است، دچار آسیب چندانی نشود و در مقابل، ویژگی‌‏های دسته‌‏هایی که داده آزمون متعلق به آنها نیست، دچار تخریب شوند. به‌طور شهودی می‏‌توان گفت، این امر، منجر به افزایش نرخ پذیرش به‌درستی (TP‏) در الگوریتم‌‏های دسته‌‏بندی یا شناسایی الگو می‏‌شود. به‌عنوان یک نمونه، ایده پیشنهادی، در مسأله شناسایی چهره با استفاده از شبکه‌‏های عصبی کانولوشن (CNN)، به‌عنوان یک پس‌‏پردازش و ویژگی‏‌های حاصل، به‌‏عنوان ویژگی‌‏های نهایی، برای عملیات شناسایی چهره به‌کار گرفته شد. نتایج پیاده‌سازی، نشان‏‌دهنده بهبود حدود %4/3 روی پایگاه داده LFW است.}, keywords_fa = {استخراج ویژگی, شبکه‌‌های عصبی کانولوشن, تبدیل موجک, تبدیل فوریه}, doi = {10.29252/jsdp.17.3.141}, url = {http://jsdp.rcisp.ac.ir/article-1-837-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-837-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Mokhlessi, Omid and SeyedMahdaviChabok, Seyedjavad and Alirezaee, Ai}, title = {Selecting effective features from Phonocardiography by Genetic Algorithm based on Pearson`s Coefficients Correlation}, abstract ={The heart is one of the most important organs in the body, which is responsible for pumping blood into the valvular systems. Beside, heart valve disorders are one of the leading causes of death in the world. These disorders are complications in the heart valves that cause the valves to deform or damage, and as a result, the sounds caused by their opening and closing compared to a healthy heart. Obviously, due to the complexities of cardiac audio signals and their recording, designing an accurate diagnosis system free of noise and fast enough is difficult to achieve. One of the most important issues in designing an intelligent heart disease diagnosis system is the use of appropriate primary data. This means that these data must not only be recorded according to the patient's equipment and clinical condition, but also must be labeled according to the correct diagnosis of the physician. However, in this study, an attempt has been made to provide an intelligent system for diagnosing valvular heart failure using phonocardiographic sound signals to have maximum diagnostic power. For this purpose, the signals are labeled and used under the supervision of a specialist doctor. The main goal is to select the effective feature vectors using the genetic optimization method and also based on the evaluation function by Pearson correlation coefficients. Before extraction feature step, preprocessing from data recording, normalization, segmentation, and filtering were used to increase system performance accuracy. For better result, Signal temporal, wavelet and signal energy components are extracted from the prepared signal as feature extraction step. Whereas extracted problem space were not correlated enough, in next step principal component analysis, linear separator analysis, and uncorrelated linear separator analysis methods were used to make feature vectors in a final correlated space. In selecting step, an efficient and simple method is used inorder to estimate the number of optimal features. In general, correlation is a criterion for determining the relationship between variables. The difference between the correlations of all feature subsets is calculated (for both in-class and out-of-class subsets) and then categorized in descending order according to the evaluation function. As a result, in the feature selection step the evaluation function is based on the Pearson statistical method, which is evaluated by a genetic algorithm with the aim of identifying more effective and correlated features in the final vectors. Eventually In this paper, two widely used neural networks with dynamic and static structure including perceptron and Elman neural networks have been used to evaluate the accuracy of the proposed vectors. The results of modeling the process of selecting effective features and diagnosing the disease show the efficiency of the proposed method.}, Keywords = {phonocardiography, cardiac valvular disease, integration features, genetic optimization algorithm, Pearson correlation coefficients}, volume = {17}, Number = {3}, pages = {157-176}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {انتخاب ویژگی‌های مؤثر در ناهنجاری‌های دریچه‌ای قلب با استفاده از الگوریتم ژنتیک بر اساس ارزیابی همبستگی پیرسون}, abstract_fa ={امروزه اختلالات دریچه​های قلبی یکی از اصلی​ترین عوامل مرگ و میر در جهان هستند. این اختلالات عبارت است از بروز عوارضی در دریچه‌های قلبی به‌نحوی که موجب تغییر شکل و یا تخریب دریچه‌ها شده و به تبع آن صداهای ناشی از باز و بسته‌شدن آنها نسبت به قلب سالم، دچار تغییر شوند. بدیهی است با توجه به پیچیدگی‌های سیگنال‌های صوتی قلبی و ثبت آنها، طراحی سامانه‌ای عاری از خطا و در عین حال دقیق از نظر میزان صحت تشخیص به‌سختی دست‌یافتنی باشد. با این وجود در این پژوهش تلاش شده است، سامانه‌ای هوشمند برای تشخیص نارسایی​های دریچه​ای قلب با استفاده از سیگنال‌های صوتی فونوکاردیوگرافی ارائه شود تا بیشینه قدرت تشخیصی را داشته باشد. هدف اصلی در روش پیشنهادی انتخاب بردارهای ویژگی مؤثر با استفاده از روش بهینه​سازی ژنتیک و نیز بر اساس تابع ارزیابی مبتنی بر ضرایب همبستگی پیرسون است. پیش از انتخاب ویژگی با توجه به ماهیت سیگنال های صوتی قلب، مراحل پیش​پردازشی شامل ثبت داده‌ها، نرمال​سازی، تقسیم‌بندی و فیلتر‌کردن مورد استفاده قرار گرفته تا صحت عملکرد سامانه را افزایش دهد. در گام بعدی سه دسته ویژگی‌های مختلف زمانی، موجک و انرژی سیگنال (هر یک پانزده ویژگی) از روی سیگنال عاری از نوفه استخراج شده که با توجه به تراکم و ناهمبستگی این ویژگی​ها، به‌کمک روش‌های ادغام، همبسته‌سازی و نیز کاهش فضای مسأله شامل تجزیه و تحلیل مؤلفه‌های اصلی، تحلیل جداکننده‌های خطی و تحلیل جداکننده‌های خطی ناهمبسته بردارهای ویژگی در فضای جدیدی استخراج می‌شوند. این بردارها شامل هجده بردار جدید (هر یک شش بردار) بوده که در‌نهایت از شبکه پرسپترون چند​لایه و المن برای طبقه‌بندی آنها استفاده می‌شود. نتایج مدل‌سازی فرآیند انتخاب ویژگی‌های مؤثر و تشخیص بیماری نشان از کارایی روش پیشنهادی دارد.}, keywords_fa = {فونوکاردیوگرافی, بیماری‌های دریچه‌ای قلبی, ادغام ویژگی, روش بهینه‌سازی ژنتیک, ضرایب همبستگی پیرسون}, doi = {10.29252/jsdp.17.3.157}, url = {http://jsdp.rcisp.ac.ir/article-1-508-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-508-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2020} } @article{ author = {Eskandari, Sadegh}, title = {Online Streaming Feature Selection Using Geometric Series of the Adjacency Matrix of Features}, abstract ={Feature Selection (FS) is an important pre-processing step in machine learning and data mining. All the traditional feature selection methods assume that the entire feature space is available from the beginning. However, online streaming features (OSF) are an integral part of many real-world applications. In OSF, the number of training examples is fixed while the number of features grows with time as new features stream in. For instance, in the problem of semantic segmentation of images using texture-based features, the number of features can be infinitely growing. In these dynamically growing scenarios, a rudimentary approach is waiting a long time for all features to become available and then carry out the feature selection methods. However, due to the importance of optimal decisions at every time step, a more rational approach is to design an online streaming feature selection (OSFS) method which selects a best feature subset from so-far-seen information and updates the subset on the fly when new features stream in. Any OSFS method must satisfy three critical conditions; first, it should not require any domain knowledge about feature space, because the full feature space is unknown or inaccessible. Second, it should allow efficient incremental updates in selected features. Third, it should be as accurate as possible at each time instance to allow having reliable classification and learning tasks at that time instance. In this paper, OSFS is considered from the geometric series of features adjacency matrix and, a new OSFS algorithm called OSFS-GS is proposed. This algorithm ranks features based on path integrals and the centrality concept on an online feature adjacency graph. The most appealing characteristics of the proposed algorithm are; 1) all possible subsets of features are considered in evaluating the rank of a given feature, 2) it is extremely efficient, as it converts the feature ranking problem to simply calculating the geometric series of an adjacency matrix and 3) beside selected features subset, it uses a redundant features subset that provides the reconsideration of good features at different time instances. This algorithm is compared with three state-of-the-art OSFS algorithms, namely information-investing, fast-OSFS and OSFSMI. The information-investing algorithm is an embedded online feature selection method that considers the feature selection as a part of learning process. This algorithm selects a new incoming feature if it reduces the model entropy more than the cost of the feature coding. The fast-OSFS algorithm is a filter method that gradually generates a Markov-blanket of feature space using causality-based measures. For any new incoming feature, this algorithm executes two processes: an online relevance analysis and then an online redundancy analysis. OSFSMI is a similar algorithm to fast-OSFS, in which uses information theory for feature analysis. The algorithms are extensively evaluated on eight high-dimensional datasets in terms of compactness, classification accuracy and run-time. In order to provide OSF scenario, features are considered one by one. Moreover, in order to strengthen the comparison, the results are averaged over 30 random streaming orders. Experimental results demonstrate that OSFS-GS algorithm achieves better accuracies than the three existing OSFS algorithms.}, Keywords = {Streaming Features, Feature Selection, Geometric Series}, volume = {17}, Number = {4}, pages = {3-14}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {انتخاب برخط ویژگی‌های جریانی با استفاده از سری هندسی ماتریس مجاورت ویژگی‌ها}, abstract_fa ={انتخاب، ویژگی یکی از گام‌های پیش‌پردازش مهم در یادگیری ماشینی و داده‌کاوی است. تمامی الگوریتم‌های انتخاب ویژگی سنتی فرض می‌کنند که کل فضای ویژگی از ابتدای چرخه انتخاب در دسترس است؛ با این وجود در بسیاری از کاربردهای دنیای واقعی با سناریوی ویژگی‌های جریانی مواجه هستیم. در این سناریو، تعداد ویژگی‌ها به‌مرور زمان افزایش می‌یابد. در این مقاله، مسأله انتخاب برخط ویژگی‌های جریانی از منظر سری‌های هندسی گراف ارتباط ویژگی‌ها مورد بررسی قرار گرفته و یک الگوریتم جدید به نام OSFS-GS پیشنهاد شده است. این الگوریتم با استفاده از مفهوم سری هندسی گراف مجاورت، ویژگی‌های افزونه را به شکل برخط حذف می‌کند؛ علاوه‌براین، الگوریتم پیشنهادی از یک سازوکار نگهداری ویژگی‌های افزونه بهره می‌بَرَد که امکان بررسی مجدد ویژگی‌های بسیار خوبی را که درقبل حذف شده‌اند، فراهم می‌آورد. الگوریتم پیشنهادی بر روی هشت مجموعه‌داده با ابعاد بزرگ اعمال شده و نتایج نشان‌دهنده دقت بالای این الگوریتم در نمونه‌های زمانی مختلف است.  }, keywords_fa = {ویژگی‌های جریانی, انتخاب ویژگی, سری هندسی}, doi = {10.29252/jsdp.17.4.3}, url = {http://jsdp.rcisp.ac.ir/article-1-942-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-942-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2021} } @article{ author = {riazi, ladan and pourebrahimi, alireza and alborzi, mahmood and radfar, rez}, title = {A hybrid method to improve Steganography in JPEG images using metaheuristic algorithms}, abstract ={This paper presents a method for improving steganography and enhancing the security using combinatorial Meta-heuristic algorithms. The goal is to achieve an improved PSNR value in order to preserve the image quality in the steganography process. Steganography algorithms, in order to insert message signal information inside the host data, create small changes based on the message signal in the host data, so that they are not visible to the human eye. Each cryptographic algorithm has two steps: insert a stego signal and extract it. You can use the area of the spatial or transformation area to insert the stego signal. Extraction can be done using the correlation with the original watermark or independently of it. Clearly, the choice of insertion method and how to extract are interdependent. In spatial techniques, information is stored directly in pixel color intensity but in the transform domain, the image is initially converted to another domain (such as frequency), and then the information is embedded in the conversion coefficients. Using optimization algorithms based on Metahuristic algorithms in this field is widely used and many researchers have been encouraged to use it. Using a suitable fitness function, these methods are useful in the design of steganography algorithms. In this research, seven commonly used Metahuristic algorithms, including ant colony, bee, cuckoo search, genetics, Particle Swarm Optimization, Simulated Annealing and firefly were selected and the performance of these algorithms is evaluated individually on existing data after being applied individually. Among the applied algorithms, cuckoo search, firefly and bee algorithms that have the best fitness function and therefore the highest quality were selected. All 6 different modes of combining these 3 algorithms were separately examined. The best combination is the firefly, bee and cuckoo search algorithms, which provides a mean signal-to-noise ratio of 54.89. The proposed combination compared to the individual algorithms of optimization of ant colony, bee, cuckoo search, genetics, Particle Swarm Optimization, Simulated Annealing and firefly, provides 59.29, 29.61, 37.43, 52.56, 54.84, 57.82, and 3.82% improvement in the PSNR value.}, Keywords = {steganography, Metahuristic algorithms, firefly algorithm, bee algorithm, cuckoo search algorithms}, volume = {17}, Number = {4}, pages = {15-32}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {یک روش ترکیبی برای بهبود پنهان‌نگاری در تصاویر با استفاده از روش‌های فرا ابتکاری}, abstract_fa ={در این مقاله روشی برای بهبود عملیات پنهان‌نگاری و بالا‌بردن امنیت، با استفاده از ترکیب الگوریتم‌های فراابتکاری ارائه شده است. هدف، دست‌یابی به مقدار بهبود‌یافته PSNR است؛ به‌گونه‌ای که کیفیت تصویر در فرایند پنهان‌نگاری حفظ شود. در این روش ابتدا هفت الگوریتم فراابتکاری متداول در این حوزه، از جمله بهینه‌سازی کلونی مورچه، زنبور عسل، جستجوی فاخته، ژنتیک، حرکت ذرات، تبرید شبیه‌سازی‌شده، کرم شب‌تاب انتخاب و کارایی الگوریتم‌های یادشده پس از اعمال به‌صورت انفرادی بر روی داده‌های موجود مورد ارزیابی قرار می‌گیرد. از میان الگوریتم‌های اعمال‎‌شده، سه الگوریتم جستجوی فاخته، کرم شب‌تاب، زنبور عسل که دارای بهترین مقدار تابع برازش و در‌نتیجه بالاترین کیفیت هستند، انتخاب شدند. تمامی شش حالت مختلف از ترکیب این سه الگوریتم به‌طور مجزا بررسی شد. بهترین ترکیب به‌کار‌رفته به‌ترتیب، الگوریتم های کرم شب‌تاب، زنبور عسل و جستجوی فاخته است که این ترکیب، میانگین نسبت سیگنال به نوفه برابر 89/54 را فراهم کرده است. ترکیب یادشده در مقایسه با الگوریتم‌های انفرادی بررسی‌شده بهینه‌سازی کلونی مورچه، زنبور عسل، جستجوی فاخته، ژنتیک، حرکت ذرات، تبرید شبیه‌سازی‌شده، کرم شب‌تاب، به‌‌ترتیب به میزان 29/59، 61/29، 43/37 ، 56/52، 84/54، 82/57 و 82/3 درصد بهبود در مقدار PSNR را ارائه می‌کند.}, keywords_fa = {پنهان‌نگاری, الگوریتم‌های فرا ابتکاری, الگوریتم کرم شب‌تاب, الگوریتم زنبور عسل, الگوریتم جستجوی فاخته}, doi = {10.29252/jsdp.17.4.15}, url = {http://jsdp.rcisp.ac.ir/article-1-936-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-936-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2021} } @article{ author = {khojasteh, fatemeh and Kahani, Mohsen and Behkamal, Behashi}, title = {Concept drift detection in business process logs using deep learning}, abstract ={Process mining provides a bridge between process modeling and analysis on the one hand and data mining on the other hand. Process mining aims at discovering, monitoring, and improving real processes by extracting knowledge from event logs. However, as most business processes change over time (e.g. the effects of new legislation, seasonal effects and etc.), traditional process mining techniques cannot capture such “second-order dynamics” and analyze these processes as if they are in steady-state. Such changes can significantly impact the performance of processes. Hence, for the process management, it is crucial that changes in processes be discovered and analyzed. Process change detection is also known as business process drift detection. All the existing methods for process drift detection are dependent on the size of windows used for detecting changes. Identifying convenient features that characterize the relations between traces or events is another challenge in most methods. In this thesis, we propose an automated and window-independent approach for detecting sudden business process drifts by introducing the notion of trace embedding. Using trace embedding makes it possible to automatically extract all features from the relations between traces. We show that the proposed approach outperforms all the existing methods in respect of its significantly higher accuracy and lower detection delay.}, Keywords = {process mining, concept drifts, process changes, word embedding}, volume = {17}, Number = {4}, pages = {33-48}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {شناسایی رانش مفهومی در نگاره‌های فرایند کسب‌وکار با استفاده از یادگیری عمیق}, abstract_fa ={فرایندهای کسب‌وکار در دنیای واقعی بسیار پیچیده هستند و متناسب با تحولات محیطی دچار تغییر می‌شوند. این در حالی است که روش‌‌های کشف فرایند پایه، قادر به شناسایی این تغییرات نیستند و تنها فرایندهای ثابت را تحلیل می‌کنند؛ از‌این‌رو، روش­هایی به‌منظور شناسایی رانش مفهومی در فرایندهای کسب­­وکار مطرح شدند. همه روش‌های موجود در این حوزه، با انتخاب ویژگی­­ها و مقایسه آنها با استفاده از پنجره سعی در شناسایی این تغییرات دارد. انتخاب ویژگی مناسب و همچنین اندازه مناسب پنجره چالش­های اصلی این روش‌ها به‌شمار می­آیند. در این پژوهش، با بیان مفهوم تعبیه دنباله که برگرفته از تعبیه واژه در دنیای پردازش زبان طبیعی است، روشی خودکار و مستقل از پنجره به‌منظور شناسایی رانش ناگهانی در نگاره‌های کسب‌وکار ارائه کرده‌ایم. استفاده از روش تعبیه دنباله، این امکان را فراهم می­کند که انواع روابط میان دنباله­ها و رویدادها را استخراج‌ و رانش‌های موجود در فرایندها را شناسایی کنیم. ارزیابی‌ها نشان می‌دهد که روش پیشنهادی نسبت به روش‌های موجود دقت بالاتر و تأخیر شناسایی رانش کمتری دارد.}, keywords_fa = {فرایندکاوی, رانش مفهومی, تغییرات فرایند, تعبیه واژه}, doi = {10.29252/jsdp.17.4.33}, url = {http://jsdp.rcisp.ac.ir/article-1-912-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-912-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2021} } @article{ author = {abbasi, zeinab and rahmani, mohsen and ghaffarian, hossei}, title = {IFSB-ReliefF: A New Instance and Feature Selection Algorithm Based on ReliefF}, abstract ={Increasing the use of Internet and some phenomena such as sensor networks has led to an unnecessary increasing the volume of information. Though it has many benefits, it causes problems such as storage space requirements and better processors, as well as data refinement to remove unnecessary data. Data reduction methods provide ways to select useful data from a large amount of duplicate, incomplete and redundant data. These methods are often applied in the pre-processing phase of machine learning algorithms. Three types of data reduction methods can be applied to data: 1. Feature reduction.2. Instance reduction: 3. Discretizing feature values. In this paper, a new algorithm, based on ReliefF, is introduced to decrease both instances and features. The proposed algorithm can run on nominal and numeric features and on data sets with missing values. In addition, in this algorithm, the selection of instances from each class is proportional to the prior probability of classes. The proposed algorithm can run parallel on a multi-core CPU, which decreases the runtime significantly and has the ability to run on big data sets. One type of instance reduction is instance selection. There are many issues in designing instance selection algorithms such as representing the reduced set, how to make a subset of instances, choosing distance function, evaluating designed reduction algorithm, the size of reduced data set and determining the critical and border instances. There are three ways of creating a subset of instances. 1) Incremental. 2) Decremental. 3) Batch. In this paper, we use the batch way for selecting instances. Another important issue is measuring the similarity of instances by a distance function. We use Jaccard index and Manhattan distance for measuring. Also, the decision on how many and what kind of instances should be removed and which must remain is another important issue. The goal of this paper is reducing the size of the stored set of instances while maintaining the quality of dataset. So, we remove very similar and non-border instances in terms of the specified reduction rate. The other type of data reduction that is performed in our algorithm is feature selection. Feature selection methods divide into three categories: wrapper methods, filter methods, and hybrid methods. Many feature selection algorithms are introduced. According to many parameters, these algorithms are divided into different categories; For example, based on the search type for the optimal subset of the features, they can be categorized into three categories: Exponential Search, Sequential Search, and Random Search. Also, an assessment of a feature or a subset of features is done to measure its usefulness and relevance by the evaluation measures that are categorized into various metrics such as distance, accuracy, consistency, information, etc. ReliefF is a feature selection algorithm used for calculating a weight for each feature and ranking features. But this paper is used ReliefF for ranking instances and features. This algorithm works as follows: First, the nearest neighbors of each instances are found. Then, based on the evaluation function, for each instance and feature, a weight is calculated, and eventually, the features and instances that are more weighed are retained and the rest are eliminated. IFSB-ReliefF (Instance and Feature Selection Based on ReliefF) algorithm is tested on two datasets and then C4.5 algorithm classifies the reduced data. Finally, the obtained results from the classification of reduced data sets are compared with the results of some instance and feature selection algorithms that are run separately.}, Keywords = {data reduction, instance selection, feature selection, ReliefF}, volume = {17}, Number = {4}, pages = {49-66}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {IFSB-ReliefF: یک روش انتخاب نمونه و ویژگی هم‌زمان بر مبنای ReliefF}, abstract_fa ={افزایش استفاده از اینترنت و برخی از پدیده­ها مانند شبکه‌­های حس‌گر، منجر به افزایش غیر­ضروری اطلاعات شده است. اگرچه این امر مزایای بسیاری دارد، اما باعث ایجاد مشکلاتی مانند نیاز به فضای ذخیره‌­سازی و پردازنده‌­های بهتر و همچنین پالایش اطلاعات برای حذف اطلاعات غیرضروری می‌شود. الگوریتم‌­های کاهش داده، روش‌­هایی برای انتخاب اطلاعات مفید از مقدار زیادی داده‌­های تکراری، ناقص و زائد فراهم می­‌کنند. در این مقاله، الگوریتم ReliefF که یک الگوریتم رتبه‌­بندی ویژگی است، تغییر داده شده تا به‌طور هم‌زمان ویژگی­‌ها و نمونه‌­ها را انتخاب کند. الگوریتم پیشنهاد‌شده می­‌تواند بر روی ویژگی­‌های اسمی و عددی و مجموعه‌داده‌­ها با مقادیر مفقود اجرا و هم‌چنین، می­‌تواند به‌صورت موازی روی یک پردازنده چند‌هسته‌­ای اجرا شود، که این امر باعث کاهش بسیار چشم‌گیر زمان اجرا و امکان اجرای آن روی مجموعه‌داده­‌های بزرگ می­شود؛ علاوه‌بر‌این، در این الگوریتم، انتخاب نمونه از هر رده متناسب با احتمال پیشین رده است و در نتیجه توازن و نسبت اولیه رده‌ها در مجموعه اصلی از بین نخواهد رفت. نتایج آزمایش بر روی چهار مجموعه‌داده نشان‌دهنده موفقیت الگوریتم پیشنهادی در این امر است.}, keywords_fa = {کاهش داده‌ها, انتخاب نمونه, انتخاب ویژگی, ReliefF}, doi = {10.29252/jsdp.17.4.49}, url = {http://jsdp.rcisp.ac.ir/article-1-902-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-902-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2021} } @article{ author = {Veisi, Hadi and Ghoreishi, Sayed Akbar and Bastanfard, Azam}, title = {Spoken Term Detection for Persian News of Islamic Republic of Iran Broadcasting}, abstract ={Islamic Republic of Iran Broadcasting (IRIB) as one of the biggest broadcasting organizations, produces thousands of hours of media content daily. Accordingly, the IRIB's archive is one of the richest archives in Iran containing a huge amount of multimedia data. Monitoring this massive volume of data, and brows and retrieval of this archive is one of the key issues for this broadcasting. The aim of this research is to design a content retrieval engine for the IRIB’s media and production using spoken term detection (STD) or keyword spotting. The goal of an STD system is to search for a set of keywords in a set of speech documents. One of the methods for STD is using a speech recognition system in which speech is recognized and converted into text and then, the text is searched for the keywords. Variety of speech documents and the limitation of speech recognition vocabulary are two challenges of this approach. Large vocabulary continuous speech recognition systems (LVCSR) usually have limited but large vocabulary and these systems can't recognize out of vocabulary (OOV) words. Therefore, LVCSR-based STD systems suffer OOV problem and can't spotting the OOV keywords. Methods such as the use of sub-word units (e.g., phonemes or syllables) and proxy words have been introduced to overcome the vocabulary limitation and to deal with the out of vocabulary (OOV) keywords. This paper proposes a Persian (Farsi) STD system based on speech recognition and uses the proxy words method to deal with OOV keywords. To improve the performance of this method, we have used Long Short-Term Memory-Connectionist Temporal Classification (LSTM-CTC) network. In our experiments, we have designed and implemented a large vocabulary continuous speech recognition systems for Farsi language. Large FarsDat dataset is used to train the speech recognition system. FarsDat contains 80 hours voices from 100 speakers. Kaldi toolkit is used to implement speech recognition system. Since limited dataset, Subspace Gaussian Mixture Models (SGMM) is used to train acoustic model of the speech recognition. Acoustic model is trained based context tri-phones and language model is probability tri-gram words model. Word Error Rate (WER) of Speech recognition system is 2. 71% on FARSDAT test set and also 28.23% on the Persian news collected from IRIB data. Term detection is designed based on weighted finite-state transducers (WFST). In this method, first a speech document is converted to a lattice by the speech recognizer (the lattice contains the full probability of speech recognition system instead of the most probable one), and then the lattice is converted to WFST. This WFST contains the full probability of words that speech recognition computed. Then, text retrieval is used to index and search over the WFST output. The proxy words method is used to deal with OOV. In this method, OOV words are represented by similarly pronunciation in-vocabulary words. To improve the performance of the proxy words methods, an LSTM-CTC network is proposed. This LSTM-CTC is trained based on charterers of words separately (not a continuous sentence). This LSTM-CTC recomputed the probabilities and re-verified proxy outputs. It improves proxy words methods dues to the fact that proxy words method suffers false alarms. Since LSTM-CTC is an end-to-end network and is trained based on the characters, it doesn't need a phonetic lexicon and can support OOV words. As the LSTM-CTC is trained based on the separate words, it reduces the weight of the language model and focuses on acoustic model weight. The proposed STD achieve 0.9206 based Actual Term Weighted Value (ATWV) for in vocabulary keywords and for OOV keywords ATWV is 0.2 using proxy word method. Applying the proposed LSTM-CTC improves the ATWV rate to 0.3058. On Persian news dataset, the proposed method receives ATWV of 0.8008.}, Keywords = {Persian Spoken Term Detection, IRIB, Persian News, Keyword Spotting, Speech Recognition, Kaldi}, volume = {17}, Number = {4}, pages = {67-88}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {تشخیص عبارت‌های گفتاری برای اخبار فارسی صداوسیمای جمهوری اسلامی ایران}, abstract_fa ={هدف از تشخیص عبارت‌های گفتاری یا جستجوی کلیدواژه، تشخیص و جستجوی مجموعه‌ای از کلیدواژه‌ها در مجموعه‌ای از اسناد گفتاری (مانند سخنرانی‌ها،‌ جلسه‌ها) است. در این پژوهش تشخیص عبارت‌های گفتاری فارسی برپایه سامانه‌های بازشناسی گفتار با کاربرد در بازیابی اطلاعات در بایگانی‌های گفتاری و ویدئویی سازمان صدا و سیما طراحی و پیاده‌سازی شده است. برای این کار، ابتدا اسناد گفتاری به متن، بازشناسی، سپس بر روی این متون جستجو انجام می‌شود. برای آموزش سامانه بازشناسی گفتار فارسی، دادگان فارس‌دات بزرگ به‌کار رفته است. این سامانه به نرخ خطای واژه 71/2 درصد بر روی همین دادگان و 23/28 درصد بر روی دادگان اخبار فارسی با استفاده از مدل‌ زیر فضای مخلوط گوسی (SGMM) رسید. برای تشخیص عبارت‌های گفتاری از روش پایه واژگان نماینده استفاده شده و با استفاده از شبکه حافظه کوتاه-مدت ماندگار و دسته‌بندی زمانی پیوندگرا (LSTM-CTC) روشی برای بهبود تشخیص واژگان خارج از واژگان (OOV) پیشنهاد شده است. کارایی سامانه تشخیص عبارات با روش واژه‌های نماینده بر روی دادگان فارس‌دات بزرگ بر طبق معیار ارزش وزنی واقعی عبارت (ATWV) برابر با 9206/0 برای کلیدواژه‌های داخل واژگان و برابر با 2/0 برای کلیدواژه‌های خارج از واژگان رسید که این نرخ برای واژگان OOV با استفاده از روش LSTM-CTC با حدود پنجاه درصد بهبود به مقدار 3058/0 رسید؛ همچنین، در تشخیص عبارت‌های گفتاری بر روی دادگان اخبار فارسی، ATWV برابر 8008/0 حاصل شد.}, keywords_fa = {تشخیص عبارت‌های گفتاری فارسی, جستجوی کلیدواژه, بازشناسی گفتار, سازمان صداوسیما, کلدی}, doi = {10.29252/jsdp.17.4.67}, url = {http://jsdp.rcisp.ac.ir/article-1-922-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-922-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2021} } @article{ author = {Pashaei, Zahra and Dehkharghani, Rahim}, title = {Stock Market Modeling Using Artificial Neural Network and Comparison with Classical Linear Models}, abstract ={Stock market plays an important role in the world economy. Stock market customers are interested in predicting the stock market general index price, since their income depends on this financial factor; Therefore, a reliable forecast in stock market can be extremely profitable for stockholders. Stock market prediction for financial markets has been one of the main challenges in forecasting financial time series, in recent decades. This challenge has increasingly attracted researchers from different scientific branches such as computer science, statistics, mathematics, and etc. Despite a good deal of research in this area, the achieved success is far from ideal. Due to the intrinsic complexity of financial data in stock market, designing a practical model for this prediction is a difficult task. This difficulty increases when a wide variety of financial factors affect the stock market index. In this paper, we attempt to investigate this problem and propose an effective model to solve this challenge. Tehran’s stock market has been chosen as a real-world case study for this purpose. Concretely, we train a regression model by several features such as first and second market index in the last five years, as well as other influential features including US dollar price, universal gold price, petroleum price, industry index and floating currency index. Then, we use the trained system to predict the stock market index value of the following day. The proposed approach can be used by stockbrokers-trading companies that buy and sell shares for their clients to predict the stock market value. In the proposed method, intelligent nonlinear systems such as Artificial Neural Networks (ANNs) and Adaptive Network-based Fuzzy Inference System (ANFIS) have been exploited to predict the daily stock  market value of Tehran’s stock market. At the end, the performance of these models have been measured and compared with the linear classical models, namely, ARIMA and SARIMA. In the comparison phase, these time series data are imposed to non-linear ANN and ANFIS models; then, feature selection is applied on data to extract the more influencing features, by using mutual information (MI) and correlation coefficient (CC) criteria. As a result, those features with greater impact on prediction are selected to predict the stock market value. This task eliminates irrelevant data and minimizes the error rate. Finally, all models are compared with each other based on common evaluation criteria to provide a big picture of the exploited models. The obtained results approve that the feature selection by MI and CC methods in both ANFIS and ANN models increases the accuracy of stock market prediction up to 55 percentage points. Furthermore, ANFIS could outperform ANN in all five evaluation criteria.}, Keywords = {ARIMA, ANFIS, ANN, CC, MI, SARIMA, Stock Modelling}, volume = {17}, Number = {4}, pages = {89-102}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {مدل‌سازی بازار سهام با استفاده از مدل‌های هوش مصنوعی و مقایسه با مدل‌های کلاسیک خطی}, abstract_fa ={پیش‌بینی قیمت سهام به‌عنوان یک فعالیت چالش برانگیز در پیش­بینی سری­‌های زمانی مالی درنظر گرفته می‌­شود. پیش‌بینی صحیح قیمت سهام می­‌تواند سود زیادی را برای سرمایه­‌گذاران به بار آورد. با وجود تلاش‎های فراوانی که تا کنون برای این منظور انجام گرفته، موفقیت چندانی در این زمینه به‌دست نیامده است. با توجه به پیچیدگی داده­‌های بازار بورس، توسعه مدل­‌های کارآمد برای این پیش‌بینی بسیار دشوار است. در این مقاله، سعی در بررسی دقیق این مسأله و ارائه روشی کارآمد برای آن داریم. برای ارزیابی روش پیشنهادی در این مقاله، بازار سهام تهران به‌عنوان یک بازار واقعی موردبررسی قرار گرفته ‌است. برای پیش‌بینی شاخص کل سهام تهران، از سامانه‌های هوشمند غیرخطی همچون شبکه‌های عصبی مصنوعی(ANN[1]) و شبکه‌­های عصبی فازی(ANFIS[2]) استفاده و سپس کارایی این مدل­‌ها با مدل‌های کلاسیک خطی(ARIMA[3] و SARIMA[4]) بررسی شده و همچنین علاوه‌بر داده­‌های شاخص کل، داده­‌های تأثیرگذار دیگری شامل قیمت دلار آمریکا، قیمت طلا، قیمت نفت، شاخص صنعت، شاخص ارز شناور، شاخص بازار اول و دوم در طول حدود پنج سال اخیر نیز در نظر گرفته شده ‌است. داده‌­های این پژوهش به‌صورت هدفمند به‌عنوان ورودی به مدل­‌های غیرخطی ANN و ANFIS داده می­شوند. به‌عبارت دیگر، عمل انتخاب ویژگی توسط معیار تابع اطلاعات مشترک(MI[5]) و ضریب همبستگی خطی(CC[6]) انجام می­‌گیرد؛ در‌نهایت، ویژگی­‌هایی انتخاب می‌­شوند که تأثیر بیشتری روی شاخص کل دارند. این عمل باعث می­شود که داده‌­های نامرتبط از مدل‌­سازی حذف شوند که این کار، تأثیر به‌سزایی در نتایج مدل‌­سازی خواهد داشت. در‌نهایت؛ همه مدل‌­ها براساس معیار­های رایج نیکویی برازش با همدیگر مقایسه می­‌شوند تا بتوان به دید جامعی در مورد توانایی مدل­‌های مورد نظر دست یافت. نتایج مدل‌سازی، بیان‌گر این است که انتخاب ویژگی‌ها با روش‌های MI و  CCدر هر دو مدل ANFIS و ANN دقت پیش‌بینی شاخص را از منظر معیار ارزیابی Nash-Sutcliffe تا 55% افزایش می دهد. همچنین در تمامی پنج معیار ارزیابی، عملکرد ANFIS بر ANN برتری دارد. [1] Artificial Neural Networks [2] Adaptive Neural Fuzzy Inference System [3] Auto Regressive Integrated Moving Average [4] Seasonal Auto Regressive Integrated Moving Average [5] Mutual Information [6] Correlation Coefficient}, keywords_fa = {شاخص بازار بورس, شبکه عصبی فازی, شبکه عصبی مصنوعی, ضریب همبستگی خطی, مدل آریما و مدل ساریما}, doi = {10.29252/jsdp.17.4.89}, url = {http://jsdp.rcisp.ac.ir/article-1-939-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-939-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2021} } @article{ author = {najafi, fatemeh and parvin, hamid and mirzaei, kamal and nejatiyan, samad and rezaie, seyede vahideh}, title = {A new ensemble clustering method based on fuzzy cmeans clustering while maintaining diversity in ensemble}, abstract ={An ensemble clustering has been considered as one of the research approaches in data mining, pattern recognition, machine learning and artificial intelligence over the last decade. In clustering, the combination first produces several bases clustering, and then, for their aggregation, a function is used to create a final cluster that is as similar as possible to all the cluster bundles. The input of this function is all base clusters and its output is a clustering called clustering agreement. This function is called an agreement function. Ensemble clustering has been proposed to increase efficiency, strong, reliability and clustering stability. Because of the lack of cluster monitoring, and the inadequacy of general-purpose base clustering algorithms on the other, a new approach called an ensemble clustering has been proposed in which it has been attempted to find an agreed cluster with the highest Consensus and agreement. In fact, ensemble clustering techniques with this slogan, the combination of several poorer models, is better than a strong model. However, this claim is correct if certain conditions (such as the diversity between the members in the consensus and their quality) are met. This article presents an ensemble clustering method. This paper uses the weak clustering method of fuzzy cmeans as a base cluster. Also, by adopting some measures, the diversity of consensus has increased. The proposed hybrid clustering method has the benefits of the clustering algorithm of fuzzy cmeans that has its speed, as well as the major weaknesses of the inability to detect non-spherical and non-uniform clusters. In the experimental results, we have tested the proposed ensemble clustering algorithm with different, up-to-date and robust clustering algorithms on the different data sets. Experimental results indicate the superiority of the proposed ensemble clustering method compared to other clustering algorithms to up-to-date and strong.}, Keywords = {Ensemble Learning, Ensemble Clustering, Fuzzy Cmeans Clustering Algorithm, Data Validity}, volume = {17}, Number = {4}, pages = {103-122}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {یک روش خوشه‌بندی ترکیبی جدید مبتنی بر خوشه‌بند cmeans فازی با حفظ تنوع در اجماع}, abstract_fa ={به‌­علت بدون‌ناظر‌بودن مسأله خوشه‌بندی، انتخاب یک الگوریتم خاص جهت خوشه‌بندی یک مجموعه ناشناس امری پر‌خطر و به‌طورمعمول شکست‌خورده است. به‌خاطر پیچیدگی مسأله و ضعف روش‌های خوشه‌بندی پایه، امروزه بیش‌تر مطالعات به سمت روش‌های خوشه‌بندی ترکیبی هدایت شده است. در خوشه‌­بندی ترکیبی ابتدا چندین خوشه‌بندی پایه تولید و سپس برای تجمیع آن­ها، از یک تابع توافقی جهت ایجاد یک خوشه‌بندی نهایی استفاده می­شود که بیشینه شباهت را به خوشه­بندی­های پایه داشته باشد. خوشه‌بندی توافقی تولید‌شده باید با استفاده از بیشترین اجماع و توافق به‌دست آمده باشد. ورودی تابع یادشده همه خوشه‌بندی­‌های پایه و خروجی آن یک خوشه‌­بندی به­نام خوشه‌بندی توافقی است. در‌حقیقت روش‌­های خوشه‌بندی ترکیبی با این شعار که ترکیب چندین مدل ضعیف بهتر از یک مدل قوی است، به میدان آمده‌­اند. با این‌­وجود، این ادعا درصورتی درست است که برخی شرایط  همانند تنوع بین اعضای موجود در اجماع و کیفیت آن­ها رعایت شده باشند. این مقاله یک روش خوشه‌بندی ترکیبی را ارائه داده که از روش خوشه­‌بندی پایه ضعیف cmeans فازی به‌­عنوان خوشه‌بند پایه استفاده کرده است. همچنین با اتخاذ برخی تمهیدات، تنوع اجماع را بالا برده است. روش خوشه‌بندی ترکیبی پیشنهادی مزیت الگوریتم خوشه­بندی cmeans فازی را که سرعت آن است، دارد و همچنین ضعف‌­های عمده آن را که عدم قابلیت کشف خوشه‌های غیر‌کروی و غیر‌یکنواخت است، ندارد. در بخش مطالعات تجربی الگوریتم خوشه‌بندی ترکیبی پیشنهادی با سایر الگوریتم‌­های خوشه‌بندی مختلف به‌روز و قوی بر روی مجموعه داده‌­های مختلف آزموده­ و با یکدیگر مقایسه شده است. نتایج تجربی حاکی از برتری کارایی روش پیشنهادی نسبت به سایر الگوریتم­‌های خوشه‌بندی به‌­روز و قوی است.}, keywords_fa = {یادگیری ترکیبی, خوشه‌بندی ترکیبی, الگوریتم خوشه‌بندی cmeans فازی, اعتبار داده‌ها}, doi = {10.29252/jsdp.17.4.103}, url = {http://jsdp.rcisp.ac.ir/article-1-976-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-976-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2021} } @article{ author = {soleimanian, Azam and Khazaei, Shahram}, title = {Fuzzy retrieval of encrypted data by multi-purpose data-structures}, abstract ={The growing amount of information that has arisen from emerging technologies has caused organizations to face challenges in maintaining and managing their information. Expanding hardware, human resources, outsourcing data management, and maintenance an external organization in the form of cloud storage services, are two common approaches to overcome these challenges; The first approach costs of the organization is only a temporary solution. By contrast, the cloud storage services approach allows the organization to pay only a small fee for the space actually in use (rather than the total reserved capacity) and always has access to the data and management tools with the most up-to-date mechanisms available. Despite the benefits of cloud storage services, security challenges arise because the organization's data is stored and managed outside of the most important organization’s supervision. One challenge is confidentiality protection of outsourced data. Data encryption before outsourcing can overcome this challenge, but common encryption schemes may fail to support various functionalities in the cloud storage service. One of the most widely used functionalities in cloud storage services is secure keyword search on the encrypted documents collection. Searchable encryption schemes, enable users to securely search over encrypted data. Based on the users’ needs, derivatives of this functionality have recently been considered by researchers. One of these derivatives is ranked search that allows the server to extract results based on their similarity to the searched keyword. This functionality reduces the communication overheads between the cloud server and the owner organization, as well as the response time for the search. In this paper, we focus on the ranked symmetric searchable encryption schemes. In this regard, we review structures proposed in the symmetric searchable encryption schemes, and show that these two data structures have capabilities beyond their original design goal. More precisely, we show that by making the data structures, it is possible to support secure ranked search efficiently. In addition, by small changes on these data, we present two ranked symmetric searchable encryption schemes for single keyword search and Boolean structures which introduced-keyword search based on the data.}, Keywords = {Searchable encryption, Ranked search, Linked list, Lookup table, Fuzzy retrieval, Boolean query}, volume = {17}, Number = {4}, pages = {123-138}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {بازیابی فازی داده‌های رمز‌شده با استفاده از داده‌ساختارهای چند‌منظوره}, abstract_fa ={با گسترش روزافزون سرویس‌های ابری، افراد حقیقی و حقوقی بیشتری تمایل به برون‌سپاری داده‌های خود روی این سرویس‌ها دارند؛ اما به‌دلایل امنیتی ترجیح می‌دهند قبل از برون‌سپاری داده آن را رمز کنند. رمز‌کردن داده به روش‌های معمول می‌تواند موجب ایجاد اختلال در عملکرد سرویس ابری، مانند عملکرد جستجو شود. روش‌های رمزگذاری جستجوپذیر به‌عنوان ابزاری مناسب، امکان جستجو روی داده رمز‌شده را فراهم می‌سازند. با توجه به نیازهای متنوع کاربران، توسعه عملکردهایی که این روش‌ها قادر به پشتیبانی آن‌ها هستند مورد توجه قرار گرفته است. یکی از این عملکردها جستجوی رتبه‌بندی‌شده است که نتایج را با توجه به میزان ارتباطی که با واژه مورد جستجو دارند، به‌صورت رتبه‌بندی‌شده در اختیار کاربر قرار می‌دهد؛ بنابراین تنها با ارسال اسناد مرتبط‌تر می‌توان ترافیک شبکه را کاهش داد. داده‌ساختارها به عنوان بلوک‌های سازنده‌ در رمزگذاری جستجوپذیر متقارن محسوب می‌شوند و تنوع در این داده‌ساختارها منجر به دست‌یابی به سطوح متنوع از امنیت، کارایی و عملکرد می‌شود. از سوی دیگر، برای رتبه‌بندی اسناد معیارهای متفاوتی وجود دارد. در این مقاله، معیار بازیابی فازی اسناد در نظر گرفته شده است که با وجود کارایی بالا و سادگی، تا کنون در مبحث جستجو روی داده رمز‌شده به‌کار گرفته نشده است. برای این منظور، به بررسی داده‌ساختارهایی می‌پردازیم که امکان دستیابی به عملکرد جستجوی رتبه‌بندی‌شده را فراهم می‌سازند. ترکیب داده‌ساختار ارائه‌شده با معیار بازیابی فازی، روش جستجوی رتبه‌بندی شده‌ای را فراهم می‌آورد که علاوه‌بر کارایی، امنیت داده را نیز تضمین می‌کند.}, keywords_fa = {رمز‌گذاری جستجو‌پذیر, جستجوی رتبه‌بندی‌شده, ساختمان داده, بازیابی فازی, پرسمان بولی}, doi = {10.29252/jsdp.17.4.123}, url = {http://jsdp.rcisp.ac.ir/article-1-901-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-901-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2021} } @article{ author = {Momeny, Mohammad and Sarram, Mehdi Agha and Latif, AliMohammad and Sheikhpour, Razieh}, title = {A Convolutional Neural Network based on Adaptive Pooling for Classification of Noisy Images}, abstract ={Convolutional neural network is one of the effective methods for classifying images that performs learning using convolutional, pooling and fully-connected layers. All kinds of noise disrupt the operation of this network. Noise images reduce classification accuracy and increase convolutional neural network training time. Noise is an unwanted signal that destroys the original signal. Noise changes the output values of a system, just as the value recorded in the output differs from its actual value. In the process of image encoding and transmission, when the image is passed through noisy transmission channel, the impulse noise with positive and negative pulses causes the image to be destroyed. A positive pulse in the form of white and a negative pulse in the form of black affect the image. The purpose of this paper is to introduce dynamic pooling which make the convolutional neural network stronger against the noisy image. The proposed method classifies noise images by weighting the values in the dynamic pooling region. In this research, a new method for modifying the pooling operator is presented in order to increase the accuracy of convolutional neural network in noise image classification. To remove noise in the dynamic pooling layer, it is sufficient to prevent the noise pixel processing by the dynamic pooling operator. Preventing noise pixel processing in the dynamic pooling layer prevents selecting the amount of noise to be applied to subsequent CNN layers. This increases the accuracy of the classification. There is a possibility of destroying the pixels of the entire window in the image. Due to the fact that the dynamic pooling operator is repeated several times in the layers of the convolutional neural network, the proposed method for merging noise pixels can be used many times. In the proposed dynamic pooling layer, pixels with a probability of p being destroyed by noise are not included in the dynamic pooling operation with the same probability. In other words, the participation of a pixel in the dynamic pooling layer depends on the health of that pixel value. If a pixel is likely to be noisy, it will not be processed in the proposed dynamic pooling layer with the same probability. To compare the proposed method, the trained VGG-Net model with medium and slow architecture has been used. Five convolutional layers and three fully connected layers are the components of the proposed model. The proposed method with 26% error for images corrupted with impulse noise with a density of 5% has a better performance than the compared methods. Increased efficiency and speed of convolutional neural network based on dynamic pooling layer modification for noise image classification is seen in the simulation results.}, Keywords = {Convolutional neural network, Noise, Image classification, weighted pooling}, volume = {17}, Number = {4}, pages = {139-154}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {ارائه یک شبکه عصبی کانولوشنال مبتنی بر ادغام تطبیقی پویا برای طبقه‌بندی تصاویر نوفه‌ای}, abstract_fa ={طبقه‌بندی تصاویر مبتنی بر شبکه عصبی کانولوشن (CNN) به‌صورت گسترده در حوزه بینایی ماشین مورد مطالعه قرار گرفته است. تصاویر نوفه‌ای در نتایج خروجی CNN تأثیر مستقیم دارند که باعث کاهش دقت خروجی و افزایش زمان فرآیند آموزش شبکه می‌شوند. همچنین تصاویر تخریب‌شده‌ای که در مرحله پیش‌پردازش بهبود یافته‌اند، ممکن است به‌دلیل عدم بهبود کافی، اثر نامطلوب در فرآیند آموزش CNN داشته باشند. هدف این مقاله، اصلاح معماری شبکه عصبی کانولوشنال جهت مقاوم‌سازی در برابر تصاویر آغشته به نوفه ضربه، تصاویر با پیکسل‌های فاقد مقدار، تلفات پیکسل‌های تصاویر در ارسال و انتقال بسته‌ها، تصاویر تخریب‌شده با داده‌های پرت و تصاویر دست‌کاری‌شده است. از آنجا که پیش‌پردازش جهت حذف نوفه و بهبود کیفیت تصاویر نوفه‌ای به‌طورمعمول زمان‌بر و پرهزینه است، روش پیشنهادی با کاهش عملیات مورد نیاز در مرحله پیش‌پردازش، به طبقه‌بندی و تشخیص اشیا تصاویر نوفه‌ای را انجام می‌دهد. لایه‌ ادغام، لایه کانولوشن و تابع هزینه برای مقاوم‌سازی CNN در برابر نوفه اصلاح می‌شوند. نتایج شبیه‌سازی نشان می‌دهد که به‌کارگیریی NR-CNN برای طبقه‌بندی تصاویر نوفه‌ای، دقت و سرعت آموزش شبکه CNN را افزایش می‌دهد. روش پیشنهادی با میانگین خطای 24% در مقایسه با روش VGG-Net نتیجه بهتری در طبقه‌بندی تصاویر موجود در پایگاه داده  PascalVOC دارد؛ بنابراین می‌توان نتیجه گرفت که NR-CNN می‌‌تواند برای طبقه‌بندی و تشخیص شیء در تصاویر نوفه‌ای سودمند باشد.}, keywords_fa = {شبکه‌ عصبی کانولوشنال, نوفه, طبقه‌بندی تصویر, ادغام تطبیقی, ادغام وزن‌دار}, doi = {10.29252/jsdp.17.4.139}, url = {http://jsdp.rcisp.ac.ir/article-1-938-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-938-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2021} } @article{ author = {BabaAli, Bagher and Rekabdar, Babak}, title = {Off-line Arabic Handwritten Recognition Using a Novel Hybrid HMM-DNN Model}, abstract ={In order to facilitate the entry of data into the computer and its digitalization, automatic recognition of printed texts and manuscripts is one of the considerable aid to many applications. Research on automatic document recognition started decades ago with the recognition of isolated digits and letters, and today, due to advancements in machine learning methods, efforts are being made to identify a sequence of handwritten words. Generally, based on the type of text, document recognition is divided into two main categories: printed and handwritten. Due to the limited number of fonts relative to the diversity of handwriting of different writers, it is much easier to recognize printed texts than handwritten text; thus, the technology of recognizing printed texts has matured and has been marketed in the form of a product. Handwritting recognition task is usually done in two ways: online and offline; offline handwriting recognition involves the automated translation of text in image format to letters that can be used in computer and text-processing applications. Most of the research in the field of handwriting recognition has been conducted on Latin script, and a variety of tools and resources have been gathered for this script. This article focuses on the application of the latest methods in the field of speech recognition for the recognition of Arabic handwriting. The task of handwritten text modeling and recognizing is very similar to the task of speech modeling and recognition. For this reason, it is possible to apply the approaches used for the speech recognition with a slight change for the handwriting recognition. With the expansion of HMM-DNN hybrid approaches and the use of sequential objective functions such as MMI, significant improvements have been made in the accuracy of speech recognition system.  This paper presents a pipeline for the offline Arabic handwritten text recognition using the open source KALDI toolkit, which is very well-known in the community of speech recognition, as well as the use of the latest hybrid models presented in it and data augmentation techniques. This research has been conducted on the Arabic KHATT database, which achieved 7.32% absolute reduction in word recognition error (WER) rate.}, Keywords = {Arabic Handwritten Recognition, Deep Neural Networks, Hidden Markov Model, Kaldi Toolkit}, volume = {17}, Number = {4}, pages = {155-168}, publisher = {Research Center on Developing Advanced Technologies}, title_fa = {بازشناسی دست‌نوشته برون‌خط عربی بر مبنای یک رویکرد تلفیقی جدید از مدل مخفی مارکوف و شبکه‌های عصبی ژرف}, abstract_fa ={مسأله مدل­‌سازی و بازشناسی دست­نوشته شباهت بسیار زیادی به مسأله مدل‌­سازی و بازشناسی گفتار دارد. به همین علت می‌­توان از رویکردهای به‌کار گرفته‌شده برای مسأله بازشناسی گفتار با اندکی تغییر در مراحل ابتدایی آن مانند استخراج ویژگی، برای بازشناسی دست‌­نوشته نیز بهره برد. با گسترش رویکردهای ترکیبی HMM-DNN و استفاده از توابع هدف دنباله‌­ای مانند MMI پیشرفت‌­های قابل توجهی در حوزه بازشناسی گفتار حاصل شده است. این مقاله با استفاده از نرم­‌افزار متن­باز KALDI، که شهرت اصلی آن در حوزه بازشناسی گفتار و همچنین به‌کارگیری آخرین مدل­‌های ترکیبی ارائه‌شده در آن، به‌کمک روش افزایش داده مدلی برای بازشناسی دست‌­نوشته عربی ارائه داده است. این پژوهش بر روی دادگان KHATT انجام شده که نرخ خطای بازشناسی واژه را بر روی این دادگان به میزان 32/7 درصد مطلق کاهش داده است.}, keywords_fa = {بازشناسی دست‌نوشته عربی, شبکه‌های عصبی ژرف, مدل مخفی مارکوف, نرم‌افزار متن‌باز KALDI}, doi = {10.29252/jsdp.17.4.155}, url = {http://jsdp.rcisp.ac.ir/article-1-975-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-975-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2021} }