@article{ author = {Lesani, Fatemeh Sadat and FotouhiGhazvini, Faranak and Dianat, Rouhollah}, title = {Lip Reading: a New Authentication Method in Android Mobile Phone’s Applications}, abstract ={Today, mobile phones are one of the first instruments every individual person interacts with. There are lots of mobile applications used by people to achieve their goals. One of the most-used applications is mobile banks. Security in m-bank applications is very important, therefore modern methods of authentication is required. Most of m-bank applications use text passwords which can be stolen by key-loggers. Key-loggers are hidden software to record the keys struck by users. To overcome the key-logging issue, One-Time Passwords are used. They are secure but require additional tools to be used, therefore they cannot be user-friend. Moreover, the voice-based passwords are not secure enough, since they can be heard by other people easily. In other hand, Image-based passwords cannot satisfy users, cause of screen limitation in mobile phones.  In this article, a new authentication method is introduced. The password is based on user lip’s motion which is received via a mobile cellphone camera.  The visual information extracted from the user’s lips movement forms the password. Then the lip motion is tracked to recognize the password by incorporating the lip reading algorithms. The algorithm is based on the Viola-Jones method. It combines the method with a pixel-based approach to segment lips and extract features. After segmenting the lips, some special points of Region of Interests are selected. The information extracted from lips are saved in order to act as algorithm’s features. In addition, some normalizing methods are considered to normalize the features and prepare them to enter classification phase. In classification step, some known algorithms like Support Vector Machine and K-Nearest Neighbor are applied on features to recognize password and authenticate people. Visual passwords prevent key-loggers from stealing passwords. However, the mobility of a mobile user causes ambient lights to vary in different environments. In this research, a solution is designed to tackle this challenge. Finally a mobile banking application is designed and developed to run on android mobile phones platform. It incorporates a lip reader which recognizes the passwords in offline mode.  The application is independent from the internet connection or a dedicated server. The implemented recognition method has achieved a 70% success rate. In this application a video capture of a letter with 10 frames could be processed in 3.8 seconds using 628 kilo bytes of memory.  These resources are easily available in today’s mobile phones. Some mobile bank users tested the application to feedback about lip reading password. Most of them were satisfied when using it. They believed the lip reader is more trustable than text passwords and voice-based passwords. In addition, the user-friendliness of it, is a bit more than text password which means that the method can satisfies a mobile bank application user.}, Keywords = {Mobile Phone Authentication, Automatic Lip Reading, Mobile Commerce, Lip Tracking, Android}, volume = {14}, Number = {1}, pages = {3-14}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.1.3}, url = {http://jsdp.rcisp.ac.ir/article-1-375-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-375-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {hajigolyazdi, elahe and abessi, masood and Fakhrzad, Mohammad bagher and Hoseininasab, Has}, title = {A Novel Approach for Exceptional Phenomena Knowledge Detection and Analysis by Data mining}, abstract ={Learning logic of exceptions is a substantial challenge in data mining and knowledge discovery. Exceptional phenomena detection takes place among huge records in a database which contains a large number of normal records and a few of exceptional ones. This is important to promote the confidence to a limited number of exceptional records for effective learning. In this study, a new approach based on the abnormality theory, information and information granulation theories are presented to detect exceptions and recognize their behavioral patterns. The efficiency of the proposed method was determined by using it to detect exceptional stocks from Iran stock market in a 30-month- period and learn their exceptional behavior. The proposed Enhanced-RISE algorithm (E-RISE) as a bottom-up learning approach was implemented to extract the knowledge of normal and exceptional behavior. The extracted knowledge was utilized to design an expert system based on the proposed abnormality theory to predict new exceptions from 6022 stocks. The superior findings show the results of this proposed approach in exceptional phenomena detection, is in accordance with experts' opinions.  }, Keywords = {Data mining, Exceptional phenomena, Abnormality theory, Bottom-Up learning approach, E-RISE Algorithm, Information theory.}, volume = {14}, Number = {1}, pages = {15-28}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.1.15}, url = {http://jsdp.rcisp.ac.ir/article-1-314-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-314-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Daneshpour, Negi}, title = {An Improved View Selection Algorithm in Data Warehouses by Finding Frequent Queries}, abstract ={A data warehouse is a source for storing historical data to support decision making. Usually analytic queries take much time. To solve response time problem it should be materialized some views to answer all queries in minimum response time. There are many solutions for view selection problems. The most appropriate solution for view selection is materializing frequent queries. Previously posed queries on the data warehouse have profitable information. These queries probably will be used in the future. So, previous queries are clustered using clustering algorithms. Then frequent queries are found using data mining algorithms. Therefore optimal queries are found in each cluster. In the last stage optimal queries are merged to produce one (query) view for each cluster, and materializes this view. This paper proposes an algorithm for materializing frequent queries. The algorithm finds profitable views using previously posed queries on the data warehouse. These views can answer the most of the queries being posed in the future. This paper uses Index-BittableFI algorithm for finding frequent views. Using this algorithm improves previous view selection algorithms and reduces the response time. The experiments show that the proposed algorithm has %23 improvement in response time and %50 improvement in storage space.  }, Keywords = {Data warehouse, Frequent queries, View materialization, Clustering }, volume = {14}, Number = {1}, pages = {29-40}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.1.29}, url = {http://jsdp.rcisp.ac.ir/article-1-402-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-402-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Goharian, Nazanin and Moghimi, Sahar and Kalani, Hadi}, title = {Application of an ANN-GA Method for Predicting the Biting Force Using Electromyogram Signals}, abstract ={Human mastication is a common rhythmic behavior and a complex biomechanical process which is hard to reproduce. Today, investigating the relation between electrical activity of muscles and force signals is of high importance in many applications including gait analysis, orthopedics, rehabilitation, ergonomic design, haptic technology, tele-presence surgery and human-machine interaction. Surface electrodes have many advantages over force sensors which are often expensive and of massive structure, two of which are less expensive and portable. Since the biting force is too difficult to be measured, in this paper, we aim to investigate the ability of a Multi-Layer Perceptron artificial neural network (MLPANN) and Radial Basis Function artificial neural network (RBFANN) to predict the biting force of incisor teeth based on surface electromyography (EMG) signals. RBFANN and MLPANN are two of the most widely used neural network architecture. These two methods are both known as universal approximates for nonlinear input-output mapping. To do this, biting force and EMG signals from the masticatory muscles were recorded and used as output and input of neural networks, respectively. Genetic algorithm was applied to find the best structure for ANNs and the appropriate total time-delay of EMGs. Results show that the EMG signals recorded from aforementioned muscles contain useful information about the biting force. Furthermore, they indicate that MLPANN and RBFANN can detect the dynamics of the system with good precision. The mean percentage error in the training and validation phase is %2.3 and %19.4 for MLPANN and %8.3 and %22.7 for RBFANN, sequentially. Also the variance analysis technique shows that there is no significant difference between results achieved through MLPANN and RBFANN. The provided analysis will aid researchers in characterizing and investigating the mastication process, through the specification of SEMG signal patterns and the observation of the resulting biting force. Such models can provide clinical insight into the development of more effective rehabilitation therapies, and can aid in assessing the effects of an intervention. This methodology can be applied to any tele-operated robot or orthotic device (exoskeleton), either for rehabilitation or extension of human ability.}, Keywords = { Electromyogram (EMG) signal, biting force, multi-Layer perceptron artificial neural networks (MLP), Radial basis function (RBF), Genetic algorithm.}, volume = {14}, Number = {1}, pages = {41-52}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.1.41}, url = {http://jsdp.rcisp.ac.ir/article-1-361-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-361-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {ZareBidoki, Tahereh and Sadeghi, Mohammad Taghi and Abutalebi, Hamid Rez}, title = {Semi Supervised Multiple Kernel Learning using Distance Metric Learning Techniques}, abstract ={Distance metric has a key role in many machine learning and computer vision algorithms so that choosing an appropriate distance metric has a direct effect on the performance of such algorithms. Recently, distance metric learning using labeled data or other available supervisory information has become a very active research area in machine learning applications. Studies in this area have shown that distance metric learning-based algorithms considerably outperform the commonly used distance metrics such as Euclidean distance. In the kernelized version of the metric learning algorithms, the data points are implicitly mapped into a new feature space using a non-linear kernel function. The associated distance metric is then learned in this new feature space. Utilizing kernel function improves the performance of pattern recognition algorithms, however choosing a proper kernel and tuning its parameter(s) are the main issues in such methods. Using of an appropriate composite kernel instead of a single kernel is one of the best solutions to this problem. In this research study, a multiple kernel is constructed using the weighted sum of a set of basis kernels. In this framework, we propose different learning approaches to determine the kernels weights. The proposed learning techniques arise from the distance metric learning concepts. These methods are performed within a semi supervised framework where different cost functions are considered and the learning process is performed using a limited amount of supervisory information. The supervisory information is in the form of a small set of similarity and/or dissimilarity pairs. We define four distance metric based cost functions in order to optimize the multiple kernel weight. In the first structure, the average distance between the similarity pairs is considered as the cost function. The cost function is minimized subject to maximizing of the average distance between the dissimilarity pairs.  This is in fact, a commonly used goal in the distance metric learning problem. In the next structure, it is tried to preserve the topological structure of the data by using of the idea of graph Laplacian. For this purpose, we add a penalty term to the cost function which preserves the topological structure of the data. This penalty term is also used in the other two structures. In the third arrangement, the effect of each dissimilarity pair is considered as an independent constraint. Finally, in the last structure, maximization of the distance between the dissimilarity pairs is considered within the cost function not as a constraint.  The proposed methods are examined in the clustering application using the kernel k-means clustering algorithm. Both synthetic (a XOR data set) and real data sets (the UCI data) used in the experiments and the performance of the clustering algorithm using single kernels, are considered as the baseline. Our experimental results confirm that using the multiple kernel not only improves the clustering result but also makes the algorithm independent of choosing the best kernel. The results also show that increasing of the number of constraints, as in the third structures, leads to instability of the algorithm which is expected.}, Keywords = {Distance Metric Learning, Multiple Kernel Learning, Similarity pairs, Dissimilarity pairs, Semi supervised}, volume = {14}, Number = {1}, pages = {53-70}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.1.53}, url = {http://jsdp.rcisp.ac.ir/article-1-362-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-362-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Imani, Maryam and Ghassemian, Hass}, title = {Feature reduction of hyperspectral data for increasing of class separability and preserving of data structure}, abstract ={Hyperspectral imaging with gathering hundreds spectral bands from the surface of the Earth allows us to separate materials with similar spectrum. Hyperspectral images can be used in many applications such as land chemical and physical parameter estimation, classification, target detection, unmixing, and so on. Among these applications, classification is especially interested. A hyperspectral image is a cube data containing two spatial dimensions and a spectral one. Generally, the Hughes phenomenon is occurred in the supervised classification of hyperspectral images due to the limited available labeled samples and the curse of dimensionality. So, feature reduction is an important preprocessing step for analysis and classification of hyperspectral data. Feature reduction methods are categorized into feature selection approaches and feature extraction ones. Our main focus in this paper is on feature extraction. The feature extraction methods are also divided into three main groups: supervised (with labeled samples), unsupervised (without labeled samples), and semi-supervised (with both labeled and unlabeled samples). The first group of feature extraction methods usually suffers from problems due to limited available training samples. These methods often consider the separability between classes, and so are efficient for classification applications. The second group has no need for training samples, but they often do not consider the separability between different classes and so, are not appropriate for classification. These methods are usually used for signal representation or preserving the local structure of data. The use of both labeled and unlabeled samples in the third group can increase the abilities of the feature extractor.  A feature extraction method is proposed in this paper which belongs to the third group. The proposed method increases the class separability and tries to preserves the structure of data. The proposed feature extraction method uses the ability of unlabeled samples in addition to available limited training samples to improve the classification performance. The experimental results on three real hyperspectral images show the better performance of proposed method compared to some popular feature extraction methods in terms of classification accuracy.}, Keywords = {high dimension, small training set, hyperspectral, classification, feature reduction. }, volume = {14}, Number = {1}, pages = {71-82}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.1.71}, url = {http://jsdp.rcisp.ac.ir/article-1-342-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-342-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Rajaeyan, Ali and Grailu, Hadi}, title = {Design and Hardware Implementation of a Driver Drowsiness Detection System Based on TMAS320C5505A DSP Processor}, abstract ={Every year, many people lose their lives in road traffic accidents while driving vehicles throughout the world. Providing secure driving conditions highly reduces road traffic accidents and their associated death rates. Fatigue and drowsiness are two major causes of death in these accidents; therefore, early detection of driver drowsiness can greatly reduce such accidents. Results of NTSB investigations into serious and dangerous accidents, where drivers had survived the crash, pinpointed intense driver fatigue and drowsiness as their two major causes [1]. This research study first developed a database including brain signals from ten male volunteers under certain conditions. A combination of Wavelet Transform (WT) and Support Vector Machine (SVM) classifier was then used to propose a drowsiness level detection method which used only two EEG signal channels. A hardware system was then adopted for practical implementation of the proposed method. The building blocks of this hardware system included a two-channel module for receiving and pre-processing EEG signals based on a TMS320C5509A digital signal processor. This processor was adopted in this study for the first time for detecting drowsiness level, and a real-time implementation of the SVM classifier revealed its functionality. This is a portable system backed by a battery for a 10-hour operation. Results from simulation and hardware implementation of the proposed method on ten volunteers indicated an up-to-100 percent accuracy. Works done on determining drowsiness level of drivers are two-fold: The first group uses shape and general conditions of the body with a focus on: Head movements Eye tracking Eye blink percent There are a few hardware systems developed for this group. The second group of research works use biometric signals (e.g. ECG and EEG) to detect drowsiness level in drivers [2-4]. EEG signals are the most applied biometric signals for drowsiness level determination purposed due to their low risk and high reliability [21, 28]. Accordingly, EEG Signals were used in this work for the same purpose. This research study first developed a database including brain signals from ten male volunteers under certain conditions. A combination of Wavelet Transform (WT) and Support Vector Machine (SVM) classifier was then used to propose a drowsiness level detection method which used only two EEG signal channels. A hardware system was then adopted for practical implementation of the proposed method. The building blocks of this hardware system included a two-channel module for receiving and pre-processing EEG signals based on a TMS320C5509A digital signal processor. This processor was adopted in this study for the first time for detecting drowsiness level, and a real-time implementation of the SVM classifier revealed its functionality. This is a portable system backed by a battery for a 10-hour operation. Results from simulation and hardware implementation of the proposed method on ten volunteers indicated an up-to-100 percent accuracy. A proper, valid, and accessible database with sufficient data entries plays an important role in the success rate of proposed approaches. On the other hand, available databases were either inaccessible or their data were in no good condition or were insufficient. Therefore, a new database including EEG signals of ten male volunteers with the mean age of 24 and at least two years road driving experience was first developed for the purpose of this study. EEG signals of volunteers were recorded in two alertness and drowsiness modes during driving simulation using a driving simulator and driving computer game. In most drowsiness level detection methods, more than two brain channels are usually used [20]; however, in this work, only two channels were used while maintaining the efficiency of drowsiness level determination. This made the system less cluttered for the driver, scaled down the processing workload for detecting and displaying the drowsiness level, reduced power consumption, and finally maximized the hardware system's operation time. Recorded signals were pre-processed to prepare them for the next stages including feature extraction and classification. Spectral features related to a number of bands (especially, Alpha and Theta) were the main features ever used for this purpose. So far, wavelet transform (WT) has been an important method for extracting these bands and computing their related features [7-9]. In addition, for this purpose, SVM and neural networks have been widely used as classifiers [15, 16, 18]. In this study, however, WT and the energy of some frequency bands were adopted for feature extraction whereas SVM was used for classification. Hardware-wise, very few studies have implemented their proposed approach. On the other hand, developments in applications of signal processors have raised their significance and also hope of using them in large scale processing algorithms, on a daily basis. Manufactured by Texas Instruments, TMS320C55xx family signal processors are an important and widely-used type [23]. Thanks to its low-consumption members, this family of processors is specialized for processing 1-D signals used in portable applications. Some of the main characteristics of this signal processors include low power consumption, fair prices, diverse functional peripherals (e.g. USB and McBSP), direct memory access (DMA), timer, LCD controller, supporting a number of major widely-used communication protocols, A/D converter, fast internal dual access memories, high operating frequency (typically 200 to 300 MHz), supporting dedicated signal processing instructions (such as the LMS and Viterbi algorithms), parallel execution of two commands. To the best of our knowledge, this signal processor has not been used for any drowsiness level detection applications. A major contribution of this paper was using a TMS320C5505A digital signal processor in a portable hardware system applied for drowsiness level detection of drivers. The frequency band of EEG signals usually ranges from 0.5 to 30 Hz that is partitioned into delta (0.5 to 4 Hz), theta (4 to 8 Hz), alpha (8 to 13 Hz) and beta (13 to 30 Hz) sub-bands. EEG signals' energy is raised in low frequency bands (e.g. delta and theta) during meditation, deep relaxation and the alertness-to-fatigue transition. With regards to these major sub-bands, an FIR band-pass filter with high and low cut-off frequencies set at 30 and 0.3 Hz, respectively, was designed using the windowing method. The developed hardware board had four inputs relating to two EEG signal channels (O1 and O2), a CZ reference channel and a ground signal. It had low power consumption (less than 25 mW) capable of operating for 10 hours with only two 3V CR2032 batteries. Using batteries with high A·h values would lead to longer circuit life. Signals from electrodes were pre-amplified and filtered in this board to remove noises outside the 0.5 to 30 Hz range. The electronic board designed and developed for EEG signal processing and alertness/drowsiness detection incorporated a TMS320C5509A digital signal processor made by Texas Instruments. For converting analog to digital signals, the TLV320AIC23B codec was used, and a TPS767D301 IC supplied power to the digital signal processor, both made by Texas Instruments. In the circuit's power supply section, a fuse and a Zener diode were placed consecutively in the path for supplying a 5V voltage to the power IC. These two items served as a protection circuit together. This protection circuit would automatically cut off the power once the current exceeds the 500 mA threshold, protecting the circuit against any damage. The 6.5V Zener diode prevents excessive supply of input voltage to the power IC. The power IC consisted of two inputs providing two output voltages (1.6V and 3.3V) for the switch, which distributed them throughout the circuit. The codec IC had one microphone input and one stereo input. The two received EEG signal channels entered the stereo input and exited the converter in a series arrangement. This IC included constants that should have been properly programmed before the conversion operation. This could be done by the I2C protocol using SDA and SCL pins connected to the processor.}, Keywords = {Drowsiness detection, EEG, DSP Processor, TMS3205509A, Wavelet Transform.}, volume = {14}, Number = {1}, pages = {83-98}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.1.83}, url = {http://jsdp.rcisp.ac.ir/article-1-345-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-345-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Fani, Davoud and Rezaei, Mehdi and SarhaddiAvval, Maryam}, title = {A GOP-Level Variable Bit Rate Control Algorithm for H.265 Video Coding Standard}, abstract ={A rate control algorithm at the group of picture (GOP) level is proposed in this paper for variable bit rate applications of the H.265/HEVC video coding standard with buffer constraint. Due to structural changes in the HEVC compared to the previous standards, new rate control algorithms are needed to be designed. In the proposed algorithm, quantization parameter (QP) of each GOP is obtained by modifying QP of previous GOP according to target bit rate and buffer status. Buffer status and target bit rate are input variables selected to expand a two dimensional lookup table. Output of the lookup table is provided in a way to allow short-term variations in bit rate, in order to reach better and more uniform visual quality of reconstructed video. In addition, a QP cascading technique is used for calculating QP of frames in each GOP that operates like a bit allocation scheme and causes suitable trade-off between quality and compression rate. Unlike conventional methods, proposed scheme uses a lookup table instead of using a rate-distortion model that significantly reduces the computational complexity. Several video sequences with completely different contents were used for experiments. Some short video sequences are concatenated to attain long video sequences which are closer to variable bit rate applications.  Lookup table based (LUT) proposed algorithm is implemented on HM reference software and compared with λ-domain rate control algorithm (λ-RC) and constant QP (CQP) case that defined as anchor. In almost the same average bit rate (CQP: 1527.97, LUT: 1520.92, λ-RC: 1529.41), average QP (28.09, 28.18, 29.91) and average peak signal to noise ratio (PSNR) (37.88, 37.87, 37.76) of LUT is closer to CQP than that of λ-RC. Average values of QP standard deviation (1.13, 2.28, 4.27) and PSNR standard deviation (1.37, 2.11, 2.15) of LUT is smaller than λ-RC and closer to CQP. From rate control point of view, minimum buffering delay on average for all video sequences resulted by LUT is the same with that of λ-RC which is one of the best rate controllers proposed for the HEVC (0.94, 0.36, 0.35). Consequently, experimental results show that not only bit rate is perfectly controlled according to buffer constraints, but also the quality of reconstructed video is well maintained.}, Keywords = {H.265/HEVC standard, Lookup table, Rate control algorithm, Variable bit rate, Video coding}, volume = {14}, Number = {1}, pages = {99-110}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.1.99}, url = {http://jsdp.rcisp.ac.ir/article-1-368-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-368-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {reza, shaghayegh and kabudian, jahanshah}, title = {A survey on spectral methods in spoken language identification}, abstract ={Identifying spoken language automatically is to identify a language from the speech signal. Language identification systems can be divided into two categories, spectral-based methods and phonetic-based methods. In the former, short-time characteristics of speech spectrum are extracted as a multi-dimensional vector. The statistical model of these features is then obtained for each language. The Gaussian mixture model is the most common statistical model in spectral-based language identification systems. On the other hand, in phonetic-based methods, speech signals are divided into a sequence of tokens using the hidden Markov model (HMM) and a language model is trained using the obtained sequence. Approaches like PRLM, PPRLM, and PR-SVM are some examples of phonetic-based methods. In research papers, usually a combination of phonetic-based and spectral-based systems are used to achieve a high quality language identification system. Spectral-based methods have been the focus of researchers, since they have no need for labeled data and usually achieve better results than phonetic approaches. Therefore, in this paper, these methods used for language identification and different spectral methods, are introduced, implemented, and compared with spoken language recognition. The basic spectral language identification method is Gaussian Mixture Model-Universal Background Model (GMM-UBM). In this paper, the MMI discrimination method is used to improve the Gaussian model of each language. Moreover, in order to model the language dynamically, GMM is replaced with the ergodic hidden Markov model (EHMM). GSV-SVM and GMM tokenizer methods are also implemented as two popular spectral approaches. In this paper, novel speaker and channel variation modeling methods are used as language identification approaches, including joint factor analysis (JFA), identity vector (i-Vector) and several variations compensation methods exploited to improve the results of i-Vector. Furthermore, in order to boost the performance of language recognition systems, different post-processing methods are applied. For post-processing, each element of raw score vector indicates the degree by which the spoken signal belongs to a language. Post-processing methods are applied to this vector as a classifier and allows making better language detection decisions by mapping the raw score vector to a space of desired languages. Different studies have employed different post-processing methods, including GMM, NN, SVM, and LLR. This study exploits several score post-processing methods to improve the quality of language recognition. The goal of the experiments in this article is to detect and distinguish Farsi, English, and Arabic, individually and simultaneously from other languages. The latter is also called open-set language identification. The signals considered in this paper include two-sided conversations, whose quality is usually not desirable due to strong noise signals, background noises of individuals or music, accents, etc. Gaussian mixture-universal model (GMM-UBM) was implemented as the basic method. In this approach, mean EER of the three target languages (Farsi, English, and Arabic) was 13.58. Experimental results indicated that training the GMM language identification system with the MMI discrimination training algorithm is more efficient than systems only trained by the ML algorithm. More specifically, the mean EER of the three target languages was reduced about 8 percent in comparison to GMM-UBM. The GMM tokenizer method was also tested as a novel spectral approach. Using this method, the mean EER of the three target languages was also about 5 percent better than GMM-UBM. In this study, the GSV-SVM discrimination method was also used for language recognition. The results of this method were considerably better than those of common spectral approaches, such that the mean EER of the three target languages was reduced by 11 percent in comparison to GMM-UBM. This study improves the low speed of this method using a model pushing method. This study also implemented two novel methods, JFA and i-Vector. According to the results, both of these methods provide better results than GMM-UBM, such that the mean EER values of the three target languages in JFA and i-Vector are respectively reduced by 1% and 12%. Generally, experimental results showed that i-Vector provides better results than other spectral language identification systems. This study is a result of a seven-year research in spoken language identification in the advanced technology development center of Khajeh Nasiredin Tousi. The ongoing research includes studying and implementing novel spectral language identification algorithms like PLDA and state-of-the-art phonetic language identification methods to combine the two spectral and phonetic systems and eventually, achieving a high quality language identification system.}, Keywords = {Automatic Spoken Language Recognition, Acoustic Approaches, Discriminative training, Channel compensation, Identity Vector.}, volume = {14}, Number = {1}, pages = {111-134}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.1.111}, url = {http://jsdp.rcisp.ac.ir/article-1-390-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-390-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Fallah, Ali and Geravanchizadeh, Masou}, title = {Binaural Microscopic Model Based on Modulation Filterbank for the Prediction of Speech Intelligibility in Normal-Hearing Listeners}, abstract ={In this study, a binaural microscopic model for the prediction of speech intelligibility based on the modulation filter bank is introduced. So far, the spectral criteria such as the STI and SII or other analytical methods have been used in the binaural models to determine the binaural intelligibility. In the proposed model, unlike all models of binaural intelligibility prediction, an automatic speech recognizer (ASR) is used in the back-end as the decision unit. One advantage of using this approach is the possibility of analyzing the recognition rate of small parts of speech such as phonemes and syllables. Another advantage of this model lies in the use of pre-processing that their existence in the human auditory system has been verified. Using the proposed feature matrix in the speech recognizer, this model has good predictions in the presence of one source of stationary speech-shaped noise. Comparing the results of the proposed model with those of listening tests show high correlations and low mean absolute error values. Also, the confusion matrices of the consonants represent high correlation between predictions and measurements. The predicted speech reception threshold by the proposed model has a smaller mean absolute error (0.6 dB) than the baseline model of BSIM.  }, Keywords = {Prediction of Speech Intelligibility, Binaural Models, Modulation Filter bank, Microscopic Models, Macroscopic Models.}, volume = {14}, Number = {1}, pages = {135-151}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.1.135}, url = {http://jsdp.rcisp.ac.ir/article-1-399-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-399-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Maskanati, Salman and Keshavarz, Ahm}, title = {Online Persian Hand Writing Recognition Using Language Model and Reduction of User Writing Rules}, abstract ={The Joint-up, cursive form of Persian words and immense variety of its scripts, also different figures of Persian letters depending on their sitting positions in the words, have turned the Persian handwritings recognition to an intense challenge. The major obstacle of the most often recognition ways, is their inattention to sentence contexture which causes utilizing of a word with correct appearance within an incorrect sentence, when an input word is misrecognized. Sketching a solution that provides suitable analysis of sentence contexture, requires huge linguistic resources to take place as a fine representative for the chosen language to be recognized. In this article, a new method for online recognition of Persian words is presented which tries to improve recognition process by using the term contexture. In this article, the vocabularies collection of Persian language is divided into two groups. The first category is the vocabulary with all of their sub-words being supported by the database of handwritten subclasses, while these vocabulary form 68.2% of the total vocabulary, and the assumptions being scored at the recognition stage, are members of these vocabularies. The second category is the vocabulary that is not supported by the database. Obviously, if the recognition system does not support this vocabulary, it cannot recognize more than 30 percentages of the language's words. At the recognition stage, the symptoms are detected and a symptom tag is produced. Also, at this stage, using the same label, the vocabulary is also selected as the sign with the input word. (These vocabularies are chosen from those were not supported at the recognition stage). Scoring for hypotheses was done by combining recognition scores and linguistic models. The certain fact in this section is that it is impossible to calculate recognition scores due to the absence of hypothetical subheadings. Therefore, the vocabulary score being recognized in the previous steps, is used. According to the studies, it was concluded that if the word is equivalent to a member's input from a supported vocabulary, even if the result of the recognition is incorrect, in most cases the correct term is in the first four hypotheses. Usually, scores of the first few hypotheses are close to each other, and the other assumptions are far from the correct hypothesis. Since the system operates online, unnecessary computations should be avoided. Therefore, if the number of hypotheses in the recognition section are more than four hypotheses, only the first four hypotheses are calculated for the language model. To calculate the recognition score for new hypotheses, if there are fewer than four hypotheses in the recognition section, the lowest hypothesis score and otherwise the hypothesis score are considered for the recognition score of the new hypotheses. Then, as with previous assumptions, for the new hypotheses, the linguistic score is calculated, and then the final score is obtained for each hypothesis. Finally, the assumption with the highest score is considered as the system output, and the rest of the assumptions are displayed in the output to the user. Experiments show that even in the event of a mistake, the correct word is often presented as a second hypothesis in most cases, and in some cases as a third hypothesis. Also, to reduce the limits and rules that gainers compel to submit. The method demonstrated in this article includes the symptoms and morphemes framework of input handwritten are segregated and the framework of each morpheme with its symptoms is specified at first, then the symptoms of morphemes are specified and based on them a collection of words is being considered as a hypothesis. Each hypothesis is given a score by measuring the similarity to input handwritten and according to taken scores, the likely hypotheses are indicated. Then, this procedure is led to achieve hypotheses more likely by lingual models. To totalize the scores of a hypothesis, for the differences in scale of taken scores, a method of score normalization is being offered. The results demonstrate that by utilizing of a language model with an online system of handwriting recognition, a significant reduction of words recognition error rate is being achieved. In addition to error rate reduction, by taking advantages of this language model, a technique is being offered that can handle the Persian vocabulary recognition entirely. By availing the offered manner, the recognition precision at initial stage of letters level up to 95.9% and so the language model recognition up to 99.3% improved. So, using huge linguistic resources for Persian language and utilizing a language model, can improve the accuracy of recognition. For further work, reinforcement learning algorithm is suggested to adapt the algorithm for users.  }, Keywords = {Online Recognition, Persian Handwriting, k-nearest Neighbor, Language Model, User Limitation }, volume = {14}, Number = {2}, pages = {3-24}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.2.3}, url = {http://jsdp.rcisp.ac.ir/article-1-428-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-428-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Ghasemi, Jamal and Kord, Somayeh and Gholami, Moham}, title = {Classification of Cardiac Arrhythmias based on combination of the results of Neural Networks using Dempster-Shefer Evidence Theory}, abstract ={Cardiac arrhythmias are one of the most common heart diseases that may cause the death of the patient. Therefore, it is extremely important to detect cardiac arrhythmias.  3 categories of arrhythmia, namely, PAC, PVC, and normal are considered in this paper based on classifier fusion using evidence theory. In this study, at first a sample is carrying out the ECG signal with 250 point.  Moreover, in each of the sampling, the maximum values will be obtained. Then, the average of the calculated values would be considered as adaptive thresholding and the total signals are multiplied by the inverse adaptive thresholding. After fixing the adaptive thresholding at number one, total resulting signal is becoming the power of 2. In this situation, the amounts smaller than one, are weakened and the larger than one amounts are reinforced. The smaller amount is removed and other amounts are held. Then, the maximum in each of the sampling is considered. In sampling areas that there is no peak, some maximum can be identified with zero value that these points should be removed from the set maximum. To find the maximum point where the maximum is close to the borders of sampling, two peaks may be placed in one field. This problem leads to removing one peak and non-recognition of the smaller peak. Some peaks near the border of sampling, for example the previous or next point on the border may be identified as the peak which eliminates the major peak and identifies the unrealistic peak. To solve this problem, the 80-point sampling is performed around each detected peak and the maximum value is obtained at the sampling areas. In this way, the correct peaks are identified and the wrong one will be deleted. In some parts, the peak signal is not quite sharp, and maybe two or more points that are adjacent to each other with the same value, will be considered as a peak. In other words, a closed peak is detected several times, which leads to detection of extra and incorrect peaks. In these circumstances, according to an amount that only belongs to one peak, just one of them should be considered and the other should be removed. After these steps, an obtained signal which includes peaks R, is compared with the original signal. To achieve the correct answer, it changes the number of sampling points and each time the result is compared with the previous values and with the original signal, too, until finally the major peaks will be identified. Then, HRV signal be will calculated. Linear properties contain root mean square of successive differences between normal intervals (RMSSD) and standard deviation of normal to normal intervals in a row (SDNN) and also heart rate (HR Mean) are calculated. Around each peak, 81 points window is inserted. These points for each peak is in one row. So resulting matrix (X) has 81 columns and its rows are the number of R peaks. SVD of matrix(X) is calculated. The obtained Matrix S will include the individual values. These singular signal values are non-linear features. If all used values are single, they can eclipse the linear features which will lead to the lack of features’ effect. Because of this reason, it is used only from the largest single value as a non-linear feature. The combination of linear and non-linear characteristics as input is applied to MLP, Cascade Feed Forward and RBF neural networks and every (single) answer is studied. The answers for each class have a level of probability that any classifier can independently be taken to the classification of cardiac arrhythmias. A class that has the greatest probability is allocated to the data. These probabilities show the uncertainty of the answers. Each of the classifiers is considered as a witness. All the possibilities for different classes of each witness uncertainties function are modeled and crime function is defined. In other words, belief structure is formed for evidence. At this stage, by combined Demster law, the mass functions will combine together. In this situation, the level of uncertainty is much reduced and the class with the highest crime will be selected as the answer. According to the survey results, the combination of linear and non-linear characteristics for training and testing the neural networks classifiers has increased the accuracy of the answer. In other words, the extraction of more features leads to better training the neural networks and increases the accuracy of the classifiers. It can be noted that the using classifiers uncertainty principle and combining them by using the evidence theory has increased the accuracy of the final classification. The results of this study show that the proposed method was able to classify cardiac arrhythmias in the presence of noise and provided an acceptable answer for the intended issue. In sum, the proposed method has been able to classify 3 categories of cardiac arrhythmia such as PVC, PAC and NORMAL with high accuracy. This is performed in the best situation with sensitivity greater than 0/98.  }, Keywords = {ECG signal, Classifier, Neural Networks, Evidence theory}, volume = {14}, Number = {2}, pages = {25-42}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.2.25}, url = {http://jsdp.rcisp.ac.ir/article-1-468-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-468-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Kianisarkaleh, Azadeh and Ghassemian, Mohammad Hass}, title = {Modified Nonparametric Discriminant Analysis for Classification of Hyperspectral Images with Limited Training Samples}, abstract ={Feature extraction performs an important role in improving hyperspectral image classification. Compared with parametric methods, nonparametric feature extraction methods have better performance when classes have no normal distribution. Besides, these methods can extract more features than what parametric feature extraction methods do. Nonparametric feature extraction methods use nonparametric scatter matrices to compute transformation matrix. Nonparametric Discriminant Analysis (NDA) is one of the nonparametric feature extraction methods in which, to form nonparametric scatter matrices, local means of samples and weight function are used. Local mean is calculated by k nearest neighbors of each sample and weight function emphasizes on boundary samples in between class scatter matrix formation. In this paper, modified NDA (MNDA) is proposed to improve NDA. In MNDA, the number of neighboring samples, when measuring local mean, are determined considering position of each sample in feature space. MNDA uses new weight functions in scatter matrix formation. Suggested weight functions emphasizes on boundary samples in between class scatter matrix formation and focus on samples close to class mean in within class scatter matrix formation. Moreover, within class scatter matrix is regularized to avoid singularity. Experimental results on Indian Pines and Salinas images show that MNDA has better performance compared to other parametric, nonparametric feature extraction methods. For Indian Pines data set, the maximum average classification accuracy is 80.34%, which is obtained by 18 training samples, support vector machine (SVM) classifier and 10 extracted features achieved by MNDA method. For Salinas data set, the maximum average classification accuracy is 94.31%, which is obtained by 18 training samples, SVM classifier and 9 extracted features achieved by MNDA method. Experiments show that using suggested weight functions and regularized within class scatter matrix, the proposed method obtained better results in hyperspectral image classification with limited training samples.  }, Keywords = {Hyperspectral images, Feature extraction, Supervised classification, Hughes Phenomenon, Limited training samples}, volume = {14}, Number = {2}, pages = {43-58}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.2.43}, url = {http://jsdp.rcisp.ac.ir/article-1-344-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-344-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Sajadi, Seyed mohamad bagher and Rashidi, Hassan and Minaeibidgoli, Behrooz}, title = {A New Approach for Extracting Named Entity in Classical Arabic}, abstract ={In Natural Language Processing (NLP) studies, developing resources and tools makes a contribution to extension and effectiveness of researches in each language. In recent years, Arabic Named Entity Recognition (ANER) has been considered by NLP researchers due to a significant impact on improving other NLP tasks such as Machine translation, Information retrieval, question answering, query result clustering, etc. While most of these researches are based on Modern Standard Arabic (MSA), in this paper, we focus on Classical Arabic (CA) literature. We propose a corpus called NoorCorp with 130k labeled words for research purposes which is annotated by expert human resources manually. This corpus is based on a Historic-Islamic book of 1200 years ago including 1843 sentences and 127550 words. We also collected about 18k proper names from old Hadith books as a gazetteer which is called NoorGazet used as a future. In this paper, we propose a new approach to extract named entities (NEs) including person, location, organization and time. We use hybrid approach benefiting from advantages of Rule based approach and Machine learning approach. We divided the NoorCorp into two parts of training and test sets containing 80% and 20% of the data set respectively. Prediction model, based on Boosting method, was developed in two steps which Adaboost.M1 is employed to identify NEs and Adaboost.M2 is employed to classify NEs. There are many methods using multiple classifiers as voters and summing up their results, among which, ensemble methods are those which generate multiple hypotheses using the same base learner. We developed an ensemble consisting of 50 members (classifiers) based on decision stump to implement the weak learner. Since only 17% of the text data is composed of name entity labels, we had to deepen the tree while restricting pruning. We exploited tokenizing, part of speech (POS) tagging, and base phrase chunking (BPC) to overcome linguistic obstacles in Arabic including Meaning ambiguity, Optional diacritics, Complex morphology and Nonstandard written text. Moreover, using a statistical technique, the most frequently used words extracted as key words. Results show that performance of the method is better than decision tree as the base classifier. An overall F-measure value of 86.85 obtained which is better than base line about 20% and CART decision tree about 12%. Since CA corpus consists of simpler linguistic patterns compared to MSA, we applied the proposed approach on ANERCorp as Modern Standard Arabic corpus. Results show that the proposed model outcome on CA corpus is about 19% better than MSA. This result is due to the fact that there are plenty of NEs entered to MSA from other languages. These proper names do not have specific patterns and do not exist in the gazetteer. In addition, many NE’s are not distributed uniformly in ANERcorp which considerably reduces the results accuracy.     }, Keywords = {Named entity recognition (NER), Ensemble learning, Boosting method, Classical Arabic Language}, volume = {14}, Number = {2}, pages = {59-74}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.2.59}, url = {http://jsdp.rcisp.ac.ir/article-1-295-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-295-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {SadatiTileboni, Seyyed Ali and Jazayeriy, Hamid and Valinataj, Mojtab}, title = {Genetic Algorithm with Intelligence Chaotic Algorithm and Heuristic Multi-Point Crossover for Graph Coloring Problem}, abstract ={Graph coloring is a way of coloring the vertices of a graph such that no two adjacent vertices have the same color. Graph coloring problem (GCP) is about finding the smallest number of colors needed to color a given graph. The smallest number of colors needed to color a graph G, is called its chromatic number. GCP is a well-known NP-hard problems and, therefore, heuristic algorithms are usually used to solve it. GCP has many applications such as: bandwidth allocation, register allocation, VLSI design, scheduling, Sudoku, map coloring and so on. We try genetic algorithm (GA) and chaos theory to solve GCP. We proposed a heuristic algorithm called CMHn to implement multi-point crossover operation in GA. To generate initial population, a fast greedy algorithm is used. In this algorithm, the degree of each node and the number colors in its neighbor is used to assign a color to each node. Mutation operation in GA is used to explore the search space and scape from the local optima. In this study, a chaotic mutation operation is presented to select some vertices and change their color.  The crossover and mutation parameters in the proposed algorithm is tuned based on some experiment. To evaluate the proposed algorithm, some experiment is conducted on DIMACS data set. Among DIMACS sample graphs, DSJ, Queen, Le450, Wap are well-known challenging samples for graph coloring. The proposed algorithm is executed 10 times on each sample and the best, worst and mean results are reported. Results show that the proposed algorithm can effectively solve GCP and have comparable outcome with the recent studies in this field. The proposed method outperforms other algorithms on very large graphs (Wap graphs).   }, Keywords = {Graph coloring problem, genetic algorithm, heuristics, multi-point crossover, chaotic mutation}, volume = {14}, Number = {2}, pages = {75-96}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.2.75}, url = {http://jsdp.rcisp.ac.ir/article-1-392-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-392-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Jamshidi, Ali and Yazdi, Mehran and Manafi, Maryam}, title = {Image Compression Based on Intelligent Information Removing and Inpainting Reconstruction Algorithms}, abstract ={Compression can be done by lossy or lossless methods. The lossy methods have been used more widely than the lossless compression. Although, many methods for image compression have been proposed yet, the methods using intelligent skipping proper to the visual models has not been considered in the literature. Image inpainting refers to the application of sophisticated algorithms to replace lost or corrupted parts of the data so that visual difference cannot be inferred from the reconstructed image. In this paper, first we review some of the image inpainting algorithms and some of the image compression techniques using the inpainting algorithms, we propose a new inpainting based image compression algorithm that can improve the compression rate considerably. We present image compression system based on the proposed parameter-assistant image inpainting method to more deeply exploit visual redundancy inherent in color images. We have shown that with carefully selected dropped regions and appropriately extracted parameters from them, dropped regions can be satisfactorily restored using the proposed PAI algorithm. Accordingly, our compression scheme has a higher coding performance compared with traditional methods in terms of the perceptual quality. To best represent the target region for inpainting, an effective region classifier is required. A generic solution is to study the distribution of each image region and find the best match among the candidates in the predefined model class. For simplicity, in our scheme, an entire image divided into three categories: gradated, structural, and non-featured, at non-overlapping block level of size S×S. The classification is performed based on edge content and color variance in each block. Simulation results show that our proposed method has reasonable visual quality in comparison with the other proposed image compression algorithms.    }, Keywords = {Image Inpainting, Image Compression, Intelligent Information Removing, Coding }, volume = {14}, Number = {2}, pages = {97-114}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.2.97}, url = {http://jsdp.rcisp.ac.ir/article-1-434-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-434-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {}, title = {A New Method for Classification of Nano-Structures based on Time Series Analysis and Fuzzy Logic}, abstract ={Dispersion of nanoparticles in nanostructures is one of the most important indicators designed to verify the effectiveness of proposed methods in the synthesis of nanomaterials. In the recent years, various methods have been suggested for the synthesis of nanostructures in which the Scanning Electron Microscopy (SEM) has been used to show the quality of the nanomaterial. The SEM images of nanoparticles contain structural, chemical and morphological information with high resolution in nanometer scale of nanomaterials. One of the challenges in the quality of dispersion’s nanostructures is detection of agglomeration degree. In some SEM images of nanoparticles, the particles have speeded uniformly and not aggregately. In some of the other SEM images, their particles are agglomerated. Also, there are a few SEM images of nanoparticles that their particles aren’t very aggregate or diffused. If the SEM images of nanoparticles with their particles speeded uniformly, are called good images, and the images with their aggregate particles are called bad images, and the images with their particle dispersion between good and bad images, are called average images, the nanomaterials could be classified in categories of good, average, and bad images. In this paper, a new algorithm has been provided to classify nanostructures using SEM images of nanoparticles. For this purpose, these images were transformed to time series at first (the time series extracted are unique for each SEM image of nanoparticles) and their specifications were investigated through time series analysis methods. Then, statistical specifications of these series were extracted. Six statistical specifications have been extracted for classification of nanostructures. These specifications are as follows: standard deviation, first and second kurtosis, interquartile range, the criterion of Pearson, and skewness. The extracted specifications were used as inputs of a fuzzy inference system for classifying microscopic images of nanostructures into three groups: good, average and bad. This algorithm has been tested on 65 nanoparticles microscopic images with identical size and resulted precision above 93 percent indicated validity of this algorithm.  }, Keywords = {SEM image of nanoparticles, Time series analyses, Statistical features, Fuzzy logic}, volume = {14}, Number = {2}, pages = {115-130}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.2.115}, url = {http://jsdp.rcisp.ac.ir/article-1-409-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-409-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Mikaeili, Mohammad and Najafi, foroogh}, title = {Performance Analysis of a Persian text input brain–computer interface (BCI) P300 Speller system with row/column paradigm (RCP)}, abstract ={As a Brain computer interface system, BCI P300 Speller tries to help disabled people and patients to regain some of their lost ability with allowing communication via typing. The ability of personalization is one of the most important features in a BCI system, so the typing language as a personalization factor is an important feature in a BCI speller. Most prior researches on P300 Speller has focused on displaying English alphabet and there were only few studies made on other languages such as Chinese. In this research, we present a P300 Speller system, based on RCP, for Persian (Farsi) character input. RCP (Row or Column Paradigm) was introduced by Farwell and Donchin at 1988, and since then it has been considered as a benchmark in P300 BCI speller research. As a result, in this study also, Row or column paradigm was selected as the base stimulation pattern in P300 speller system. In order to evaluate the Persian row or column paradigm performance, we recorded EEG signals from volunteered subjects while the stimulation pattern was being displayed. It should be noted that the test was explained to each subject before testing, and for more experience and in order to reduce the error, each subject participated in an experiment test before attending the main test. These EEG signals were recorded from 8 channels based on ‘‘Fz’’, ‘‘Cz’’, ‘‘P3’’, ‘‘Pz’’, ‘‘P4’’, ‘‘O1’’, ‘‘Oz’’ and ‘‘O2’’ site in accordance to the International 10–20 system electrode placement system and by using Science Beam co.’s EEG recording device. The sample rate was 1 KHz which was down sampled to 250Hz. After recording, the EEG signals were filtered using a band passed filter And for classification, Linear discriminate analysis was used in combination with K-fold validation method for classifier training. As performance determination, we calculated accuracy and bit rate for the mentioned system based on recorded data from volunteers and reached the average accuracy of 88.21% and bit rate of 6.74 (bits/minute) (we use Linear LDA classifier for classification and the total trial number was set to 15). Furthermore, in this research performance was measured for different trial number and final results demonstrated that this system can achieve high average accuracy of 80.06% and average bit rate of 42.43 (bits/minute) by using only 2 repetitions.  }, Keywords = {Brian computer interface systems, BCI P300 Speller, P300 wave, LDA classifier}, volume = {14}, Number = {2}, pages = {131-140}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.2.131}, url = {http://jsdp.rcisp.ac.ir/article-1-448-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-448-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {TolouBeidokhti, Mohammad Amin and Ahmadyfard, Alirez}, title = {Document Image Dewarping using geometrical information extracted from document lines}, abstract ={Document images produced by scanners or digital cameras usually have photometric and geometric distortions. If either of these effects distorts document, recognition of words from such a document image using OCR is subject to errors. In this paper we propose a novel approach to significantly remove geometric distortion from document images. In this method first we extract document lines from document using morphological operators. Then, extracted document lines are divided into a number of equal size column strips.  This allows to assume that each segment of line document is not curved. Each extracted document line segment is aligned horizontally. For this purpose, a segment line of document is rotated at different angels and for each rotation horizontal projection is obtained. The rotation angle with maximum peak at the corresponding projection signal is selected to align the line segment, horizontally. In order to estimate the geometrical distortion, for each document line a reference point is extracted from each line segment. These points indicate the position of a document line at starting column of line segments. Using reference points of a document line a polynomial function is fitted to each document line. At the end, geometric distortion for each part of the document is eliminated using a perspective transformation. This transformation is estimated based on the extracted polynomial function. To increase the stability of the proposed method for short text lines, the curve of adjacent text lines of longer length is used. A post processing stage is required after applying perspective transformation on document patches. Since this transformation is a continuous mapping but it is applied on digital images. To remove this distortion from the result, the consistency of each pixel value with the value of neighboring pixels are considered to correct the value of inconsistence pixels. The proposed method is implemented on Persian and English databases and has been compared with the existing methods. The results indicate the efficiency and accuracy of the proposed method in elimination of geometric distortions.  }, Keywords = {Geometric distortion, document processing, perspective Transformation, Optical character recognition (OCR)}, volume = {14}, Number = {2}, pages = {141-158}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.2.141}, url = {http://jsdp.rcisp.ac.ir/article-1-406-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-406-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Chaghari, Arash and Feizi-Derakhshi, Mohammad-Rez}, title = {Automatic Clustering Using Improved Imperialist Competitive Algorithm}, abstract ={Imperialist Competitive Algorithm (ICA) is considered as a prime meta-heuristic algorithm to find the general optimal solution in optimization problems. This paper presents a use of ICA for automatic clustering of huge unlabeled data sets. By using proper structure for each of the chromosomes and the ICA, at run time, the suggested method (ACICA) finds the optimum number of clusters while optimal clustering of the data simultaneously.To increase the accuracy and speed of convergence, the structure of ICA changes. As in different applications, there is a need for data clustering which the number of clusters is not known before it is necessary to have methods that can cluster data without knowing the correct prediction of the number of clusters. In the other words, the proposed algorithm requires no background knowledge to classify the data.  In addition, the proposed method is more accurate in comparison with other clustering methods based on evolutionary algorithms. In Imperialist Competitive Algorithm, firstly steps should be taken to increase search rates and explore possible solution while approaching to the global optimal response the steps should be reduced to ensure that the algorithm is not lost and it is not in the local optimal manner. For this purpose and improvement of imperialist competitive algorithm, mutation rate and revolution operator's operation rate are determined dynamically. DB and CS are cluster validity Indexes. In this paper, DB and CS cluster validity measurements are used as the objective function. To demonstrate the superiority of the proposed method, the average of fitness function and the number of clusters determined by the proposed method is compared with three automatic clustering algorithms based on evolutionary algorithms. The partitional clustering algorithms are based on three powerful well-known optimization algorithms, namely the genetic algorithm, the particle swarm optimization and differential evolutionary algorithm.}, Keywords = {Partitional Clustering, Automatic Clustering, Imperialist Competitive Algorithm (ICA)}, volume = {14}, Number = {2}, pages = {159-169}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.18869/acadpub.jsdp.14.2.159}, url = {http://jsdp.rcisp.ac.ir/article-1-453-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-453-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Safaei, Ali}, title = {Providing a Dynamic Technique for Answering Ad-hoc Continuous Aggregate}, abstract ={Data Streams are infinite, fast, time-stamp data elements which are received explosively. Generally, these elements need to be processed in an online, real-time way. So, algorithms to process data streams and answer queries on these streams are mostly one-pass. The execution of such algorithms has some challenges such as memory limitation, scheduling, and accuracy of answers. They will be more important and serious, chiefly if the queries are not predefined but Ad-hoc, and also should be executed after data stream tuples are gone. Countinous aggregate queries are types of queries with some special characteristics making it possible to perform more specific, efficient qeury processing techniques, specifiaclly beneficient for ad-hoc ones. In this paper, a dynamic efficient techinque is proposed for answering the ad-hoc continiues aggregate queries over data streams. The main idea of the proposed technique is to generate and handle an efficiet tree data structure as the synopse, in the form of  Dynamic Prefix Aggregate Tree. In general, the two following approaches can be used to calculate any function such as ; either implementation of an algorithm for the calculation of function f, or storing the answers of function f for all possible states. When the algorithm runtime is high, the second method strengthened by proper selection of indices can return a proper answer in a very short time (even ). But the major problem of the second method is the total number of possible answers which can be very high and also can be out of the possible storage capacity and processing potential within a certain acceptable time period. For example, suppose that the cardinality of each of the parameters of  is 10. In this case, the total number of possible states will be . As it is evident, the total number of states increases with the number of parameters and their cardinalities.When the total number of states is so great that generating answers with respect to consumed time and space is impossible, a more convenient, practical method should be employed. This more practical approach can be the storing of some of the answers (selectively) with respect to the following conditions: Obtaining un-stored answers from the set of stored answers. Higher probability of utilizing stored answers (i.e. higher probability of submitting requests from stored set). Eliminating (not storing) null answers. The same idea can be implemented for online and almost real time processing of queries, so that by receiving each tuple, all possible answers get obtained and stored. By doing so, in the time of need (when answering to an ad-hoc query) stored answers will be used instead of calculating each answer. Accordingly, some answers are stored in a tree structure to be used at the right time. In this paper, in order to answer ad-hoc continuous aggregate queries over data streams, a method is proposed that uses a tree structure for storing the aggregate results. The important point in this method is that all steps of the construction, maintenance and using of the tree must be online. For these purposes, it is enough to keep all possible answers. But to apply an online construction and maintenance of tree, we must keep some answers, according to the inherent features of data streams. In this way, the main goal is to choose the answers possessing the most overlap with responses answers of received ad-hoc queries. The proposed method, creates the tree structure and maintains it dynamically to answer ad-hoc aggregate continuous queries over data streams. For this purpose, queries at instant  are modeled as in form of , where  or  (when , the aggregate over the whole sliding window is returned) and  is the size of sliding window and  (when , the aggregate over the whole  is returned). In order to increase the overlapping, a statistical task is performed on a dimensions of the received queries. In this way, dimensions are determined with the highest, lowest request. When , means that there is no request for this dimension. Therefore, we select and store the answers related to the dimension with highest request, and ignore those with the lowest. Obviously, these answers should be obtained and presented using stored answers. As the request for dimensions may change, the tree structure must be dynamically constructed and maintenance that will be presented this dynamic structure in this paper. Experimental evaluattion of the proposed method shows that, using the proposed Dynamic Aggregate Tree for ansering countinous Ad-hoc aggregate queies is more cost-effective, in terms of response time and memory usage.}, Keywords = {Data Stream, Continuous ad-hoc aggregate queries, Dynamic Prefix Tree, Aggregate cell}, volume = {14}, Number = {3}, pages = {3-22}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.3.3}, url = {http://jsdp.rcisp.ac.ir/article-1-486-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-486-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Deypir, Mahmoo}, title = {RiskMeter: A Tool for Measuring Precise Security Risk Values of Mobile Device Applications}, abstract ={Nowadays smartphones and tablets are widely used due to their various capabilities and features for end users. In these devices, accessing a wide range of services and sensitive information including private personal data, contact list, geolocation, sending and receiving messages, accessing social networks and etc. are provided via numerous application programs. These types of accessibilities, functionalities, and facilities make privacy and security issues more critical. Therefore, traditional security mechanism including biometric authentication, data encryption, access control, and etc. are not adequate. Therefore, danger of installing and using malwares must be taken into account in order to provide practical security for end users. Installing new and unknown applications on these devices might lead to security threats. Recently, smartphones and tablets utilize powerful operating system in which security of application is provided by application permissions. Android and BlackBerry are two examples of operating systems which reduce attack surface by using application permissions. In these operating systems, in order to perform malicious activities, an attacker must deceive users to install a malicious app since other ways of intrusion are almost closed. Recent statistics show that Android is the most popular operating system. For installing an app, Android requires the user to grant privileges through the requested permissions. There is a large number of applications (Apps) developed for this operating system which require various permissions based on their functionalities and provided services. Therefore, measuring security risks of applications can help us to make better decision regarding to apps installation and removal. There exists some research regarding to enhance the Android security model and its security risk communication mechanism. In this mobile operating system, security risk values of applications can be computed using their requested permissions. In this study, a new software tool is designed and implemented to measure security risk values of mobile applications. This tool benefits from a new metric to compute the risk values. This risk metric exploits statistics of permission usages in known malwares and goodwares. However, they can be simply extended to other features of Android apps including static and dynamic ones. Moreover, we have attempted to give a better definition of permission criticality to aim users for making best decision in new apps installation or previously installed ones removal. In fact, we have designated a new formulation to assign higher risk values to permissions with a higher usage in malwares and very lower usage in benign apps. The idea is quite simple but produces interesting results. That is, the security risk of a permission is directly related to the difference of its usage in malicious and non-malicious apps. Given risk values of permissions, one can compute risk of an Android app based on its permission list. Since the proposed measurement compute the risk values of permissions according to simple statistics of known malwares and useful Android apps, they have good explainability. Users can be informed regarding to danger about approving risky permissions and they can make reasonable decisions based on total risk score of an app which can be simply computed using security risks of its requested permissions. In order to purpose the metric, we have analyzed requested permissions of large number of malicious and ordinary applications. Moreover, for realistic evaluations, we have constructed two new datasets of applications belonging to an Iranian market and new malwares. Experimental evaluations on real known malwares and benign apps reveal the superiority of the proposed criterion with respect to previously proposed method in terms of assigning higher risk values to malwares and lower risk values to the benign applications.    }, Keywords = {Security of mobile devices, Security risk, Malwares, Permissions, RiskMeter}, volume = {14}, Number = {3}, pages = {23-36}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.3.23}, url = {http://jsdp.rcisp.ac.ir/article-1-474-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-474-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {KhajehRayeni, Farshid and Ghassemian, Hass}, title = {Spectral Unmixing Using Improved HYCA Algorithm}, abstract ={Hyperspectral (HS) imaging is a significant tool in remote sensing applications. HS sensors measure the reflected light from the surface of objects in hundreds or thousands of spectral bands, called HS images. Increasing the number of these bands produces huge data, which have to be transmitted to a terrestrial station for further processing. In some applications, HS images have to be sent instantly to the station requiring a high bandwidth between the sensors and the station. Most of the time, the bandwidth between the satellite and the station is narrowed limiting the amount of data that can be transmitted, and brings the idea of Compressive Sensing (CS) into the minds. In addition to the large amount of data, in these images, mixed pixels are another issue to be considered. Despite of their high spectral resolution, their spatial resolution is low causing a mixture of spectra in each pixel, but not a pure spectrum. As a result, the analysis of mixed pixels or Spectral Unmixing (SU) technique has been introduced to decompose mixed pixels into a set of endmembers and abundance fraction maps. The endmembers are extracted from spectral signatures related to different materials, and the abundance fractions are the proportions of the endmembers in each pixel. In recent years, due to the large amount of data and consequently the difficulties of real-time signal processing, and also having the ability of image compression, methods of Compressive Sensing and Unmixing (CSU) have been introduced. Two assumptions have been considered in these methods: the finite number of elements in each pixel and the low variation of abundance fractions. HYCA algorithm is one of the methods trying to compress these kinds of data with their inherent features. One of the sensible characteristics of this algorithm is to utilize spatial information for better reconstruction of the data. In fact, HYCA algorithm splits the data cube into non-overlapping square windows and assumes that spectral vectors are similar inside each window. In this study, a real-time method is proposed, which uses the spectral information (non-neighborhood pixels) in addition to the spatial information. The proposed structure can be divided into two parts: transmitting information into the satellites and information recovery into the stations. In the satellites, firstly, to utilize the spectral information, a new real-time clustering method is proposed, wherein the similarity between the entire pixels is not restricted to any specific form such as square window. Figure 3 shows a segmented real HS image. It can be seen that the considering square form limits the capability of the HYCA algorithm and the similarity can be found in the both neighborhood and non-neighborhood pixels. Secondly, to utilize similarity in each cluster, different measurement matrices are used. By doing this, various samples can be achieved for each cluster and further information are extracted. On the other hand, usage of different measurement matrices may affect the system stability. As a matter of fact, generating the different measurement matrices is not simple and increases complexity into the transmitters. Therefore, it conflicts with the aim of CS theory, reducing complexity into the transmitters. As a result, in the proposed method, the number of the clusters is determined by the number of the producible measurement matrices. Figure 4 shows the schematic of the proposed structure in the satellites. In the stations, we follow HYCA procedure in equation 8 and 9, but the different similar pixels are applied to the both equations. By doing this, we reach to the improved HYCA algorithm. Finally, the proposed structure is shown in the Table 1. To evaluate the proposed method, both real and simulated data have been used in this article. In addition, normalized mean-square error is considered as an error criteria. For the simulated data, in constant measurement sizes, the effects of the additive noise, and for real data, the effects of measurement sizes have been investigated. Besides, the proposed method has been compared with HYCA and C-HYCA and some of the traditional CS based methods. The experimental results show the superiority of the proposed method in terms of signal to noise ratios and the measurement sizes, up to  in the simulated data and  in the real data, which makes it suitable in the real-world applications.  }, Keywords = {Compressive Sensing (CS), HYCA algorithm, hyperspectral imaging, spatial and spectral information, spectral unmixing}, volume = {14}, Number = {3}, pages = {37-50}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.3.37}, url = {http://jsdp.rcisp.ac.ir/article-1-369-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-369-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {mirzaee, elahe and esmaeilpour, mansour}, title = {A New Hybrid Method to Increase the Prediction in Data Reduced Using Rough Set and Swarm Intelligence Model}, abstract ={Designing a system with an emphasis on minimal human intervention helps users to explore information quickly. Adverting to methods of analyzing large data is compulsory as well. Hence, utilizing power of the data mining process to identify patterns and models become more essential from aspect of relationship between the various elements in the database and discover hidden knowledge. Therefore, Rough set theory can be used as a tool to explore data dependencies and reducing features outlined in a data set. The main purpose of the rough theory is to obtain approximate concepts of acquired data. This theory is a powerful mathematical tool for arguing in ambiguous and indeterminate terms that provides methods for remove and reduce unrelated or excessive knowledge information on the data sets. This process of data reduction is based on the main task of the system, and without losing the basic data of the data sets. Rough set theory can play a very effective role to support decision-making systems, but in some cases, with increasing data volumes, there are inconsistent or collisional results which using swarm intelligence-based methods can choose the best of the contradictory, effectless or dummy data. This will bring interesting, unexpected and valuable structures from within a wide range of data. Since the ant colony optimization compares all the exploratory paths generated by each ant and the best route is selected from the existing paths, so considering the improvement of the selecting the main features and improving the theory of the Rough set, paths are not eliminated from the possible paths. In this research, the combination of the ant colony optimization and rough set theory have been used to find the subset of the main features and to delete the inappropriate information with the loss of the minimum information. This research will improve the features reduction technique employment Rough set theory and ant colony optimization. The gist of this research is removing useless information with minimal information loss. The results on petroleum prices data evaluation demonstrate that the hybrid method is more efficient than recent methods.  }, Keywords = {Rough Set Theory, Swarm Intelligence, Ant Colony Optimization, Feature Reduction}, volume = {14}, Number = {3}, pages = {51-64}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.3.51}, url = {http://jsdp.rcisp.ac.ir/article-1-461-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-461-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Ahmadi, Ali}, title = {A Novel Text Mining Method for User Context Extraction to Improve Search Engine Results Ranking}, abstract ={Today, the importance of text processing and its usages is well known among researchers and students. The amount of textual, documental materials increase day by day. So we need useful ways to save them and retrieve information from these materials. For example, search engines such as Google, Yahoo, Bing and etc. need to read so many web documents and retrieve the most similar ones to the user query. In this example, necessity of real time ability should be mentioned. Keyphrase extraction and some other fields like Information extraction, natural language processing, text summarization, query understanding, machine translation, and text similarity are subsets of text processing. So many efforts in text processing have been established, but there are still many open problems, especially in semantically document understanding subjects. Although these subjects seem not to be very hard for humankind but they are very complex and confusing for a computer, because there is no standard structure to save documents so that computers be able to extract semantics and contents. Document understanding and keyphrase extraction are some of the most important text processing goals. Many statistical and linguistic approaches are proposed in order to address these complex goals. Some methods work based on multi documents and some others on single document which all are generally more difficult than multi documents methods. Some methods use learning algorithms with training data and some others do not. Using natural language processing tools or resources -like ontologies- are effective ways to improve results, but these tools are not reliable for all languages. There are some articles for keyphrase extraction based on co-occurrence and also some statistical methods. Moreover, sometimes it is an important feature for a method to make real time outputs. Based on these characteristics, many approaches have been proposed in the literature. In this paper, we present a new approach for keyphrase extraction from a single document. We present a language-independent approach based on combination of statistical information extracted from document and some logical rules named fundamental text rules. In this approach, there is no need to any natural language processing, nor to ontology and nor to any document corpus. We illustrate a real time method to understand each document focuses by extracting its phrases from segmented document without using any learning algorithm. Then, the Score for each phrase is calculated based on its occurrence and its related phrases occurrences. Then, fundamental text rules omit some phrases based on their scores and their places in text. Remained phrases shows the document focuses. Evaluation shows that our approach takes a high recall and precision in key phrase extraction with very good accuracy in text focuses understanding. These keyphrases extracted of a text presents the most important concepts of that text and it is used to retrieve documents in search engines more efficiently.  }, Keywords = {text mining, information retrieval, user context, search engine results ranking}, volume = {14}, Number = {3}, pages = {65-82}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.3.65}, url = {http://jsdp.rcisp.ac.ir/article-1-473-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-473-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {mirhaditafreshi, marm alsadat}, title = {Web Anomaly Detection by Using Access Log Usage Profile}, abstract ={Due to increasing in cyber-attacks, the need for web servers attack detection technique has drawn attentions today. Unfortunately, many available security solutions are inefficient in identifying web-based attacks. The main aim of this study is to detect abnormal web navigations based on web usage profiles. In this paper, comparing scrolling behavior of a normal user with an attacker, and simultaneous use of the access control policy alarms provided in web pages crawling with high access level, leads to an attacker to be detected among ordinary users. Indeed, the proposed method in this research includes two main steps: firstly web usage profiles are extracted as web main patterns of users’ behavior. In order to cluster similar web sessions we used a system inspired by artificial immune system. In the employed method, the rate at which a particular web page is visited as well as the time a user spends on the pages, is calculated so as to estimate how interesting a specific page is in a user’s session. Therefore, the similarity in the web page is defined based on the combination of the similarity of web pages URLs and that of the users’ level of interest in visiting them. Secondly, the difference between each current user session from the main profiles is calculated. Additionally, the access control logs are derived from corresponding sessions in this stage. Regarding the noisy nature of web server logs, a method was required so that a slight change in the data would not make a noticeable change in the results validity. Hence, a fuzzy neural network has been applied to distinguish normal and abnormal scrolling behavior in second step. Due to the lack of a standard data that contains both web pages scrolling and access control logs corresponding to it, providing such a data was required. At first, those intended logs were produced. To do so, an Apache web server was run on the platform of a Centos machine. In order to create the logs completely similar to a real server’s log, an e-commerce website was set up on Apache server. This website had about 160 different web pages to be visited by different users. At this point, a novel method is proposed to simulate the behavior of web users when they visit a website. Likewise, the abnormal data was generated by means of a large number of existing attack tools. It should also be noted that the access control policy has been used is SELinux and It has been added to Linux kernel. As mentioned, web server access log varies greatly with changing user behaviors, the stability of the proposed method against noise should be evaluated. For this reason, the results has been investigated on noisy profiles created by making random changes on the main profiles, and only the testing phase is conducted again. Subsequently, the distance from the profiles having noise is compared with the main ones. To demonstrate the ability of this method, the results have been compared with a Support Vector Machine (SVM). The carried out evaluations show that our approach performs efficiently in identifying normal and abnormal scrolling.  }, Keywords = {fuzzy neural networks, web usage profile, anomaly detection, access control}, volume = {14}, Number = {3}, pages = {83-96}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.3.83}, url = {http://jsdp.rcisp.ac.ir/article-1-418-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-418-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Hashemzadeh, Mahdi}, title = {A Vision Machine for Detecting Fertile Eggs and Performance Evaluation of Neural Networks and Support Vector Machines in This Machine}, abstract ={In this research, a system is proposed for detecting fertility of eggs. The system is composed of two parts: hardware and software. The fabricated hardware provides a platform to obtain accurate images from inner side of the eggs, without harming their embryos. The software part includes a set of image processing and machine vision processes, which is able to detect the fertility of eggs from captured images, without any sensitivities to different types of eggs (e.g. with different thickness of the eggshell). In order to classify the fertile and infertile eggs, two classifiers based on Artificial Neural Networks (ANN) and Support Vector Machines (SVM) are designed and tested. It means that, to have a fully automatic fertility detection machine, we design two machine learning approaches using SVMs and ANNs to classify fertile and infertile eggs. That is, instead of using a predefined threshold values for distinguishing fertile pixels of egg images from infertile ones, we try to train the machine to do the job automatically. After training the machine using both classification algorithms, the performance of them are accurately investigated and measured in order to select the appropriate one. To evaluate the system, an egg image dataset is provided including 1200 images captured from incubated eggs. Extensive experiments are performed using the provided dataset, which confirm the reliable performance of the system. Comparisons with other fertility detection approaches applying different methods and algorithms confirm that the proposed machine outperforms more complex systems. Performance evaluations of the two proposed classifiers confirm that the SVM based classifier, with average detection accuracy of 50.57% at day 1 of incubation, 83.67% at day 2, 94.20% at day 3, 98.03% at day 4, and 98.91% at day 5, performs better than ANN based classifier, and it is also less sensitive against the reductions in training samples, which can be a serious issue when we are not able to provide more training samples.  }, Keywords = {Machine Vision, Fertile Eggs, Classification, Neural Networks, Support Vector Machines}, volume = {14}, Number = {3}, pages = {97-112}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.3.97}, url = {http://jsdp.rcisp.ac.ir/article-1-488-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-488-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {KarimiMosadegh, Afifeh and Daneshpour, Negi}, title = {Increasing the Speed of Incremental View Maintenance Using the Cuckoo Algorithm}, abstract ={Data warehouse is a repository of integrated data that is collected from various sources. Data warehouse has a capability of maintaining data from various sources in its view form. So, the view should be maintained and updated during changes of sources. Since the increase in updates may cause costly overhead, it is necessary to update views with high accuracy. Optimal Delta Evaluation method is one of the incremental view maintenance method that can maintain materialized views efficiently in the data warehouse environment. This method is one of the incremental view maintenance grouping methods. In this method incremental maintenance expression is divided into groups, as a result access to some repeated relations is minimized. As a final result, Optimal Delta Evaluation method can minimize the total accesses to relations. The algorithm proposed in this paper, is the combination of optimal Delta Evaluation with Cuckoo heuristic Algorithm that reduces maintenance time of views and thus speeds up this process. Cuckoo optimization algorithm begins with an initial population. Trying to survive the Cuckoo makes the base to optimize the algorithm. The results show that the Cuckoo algorithm is faster in order to update its incremental views compared with previous methods.  }, Keywords = {data warehouse, Cuckoo algorithm, random search, optimization delta tree, incremental view maintenance}, volume = {14}, Number = {3}, pages = {113-126}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.3.113}, url = {http://jsdp.rcisp.ac.ir/article-1-460-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-460-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Hosseinnejad, Shadi and Shekofteh, Yasser and EmamiAzadi, Tahereh}, title = {A’laam Corpus: A Standard Corpus of Named Entity for Persian Language}, abstract ={Named entity recognition (NER) is a natural language processing (NLP) problem that is mainly used for text summarization, data mining, data retrieval, question and answering, machine translation, and document classification systems. A NER system is tasked with determining the border of each named entity, recognizing its type and classifying it into predefined categories. The categories of named entities include the names of persons, organizations, locations (e.g. city and country), expressions of times, quantities, monetary expressions, and percentages. In general, corpus-based NER approaches have been proved to be well suited for NER problem. Using a NER corpus, recognition of named entities can be done through ruled-based or machine-learning methods.       Corpus-based NER systems need standard and appropriate annotated corpora. However, such corpora mainly exist in languages such as English, and are rarely found in Persian/Farsi or limited in volume. So, this paper is dedicated to describe the producing procedure of a standard named entity (NE) corpus - A’laam corpus - for Persian language. A’laam corpus contains about 250,000 tokens tagged with 13 NE tags. This corpus has been developed in the Research Center for Development of Advanced Technologies (RCDAT). Tokens of A’laam corpus are a part of Farsi Text Corpus. The Farsi Text Corpus is a standard Farsi corpus. This corpus, containing more than 100 million Farsi words, has been developed by the Research Center of Intelligent Signal Processing (changed to the Research Center for Development of Advanced Technologies in 2013). The words of this corpus, selected from diverse written and spoken sources, was tokenized and corrected manually. In addition, a part of the Farsi Text Corpus with 8 million words has part-of-speech (POS) tags at word level. Totally, about 8,400 sentences of the Farsi Text Corpus have been randomly selected to obtain about 250,000 tokens of A’laam Corpus. This corpus included words, POS tags, and named entity tags.       To evaluate A’laam corpus, a Persian NER system was trained based on this corpus. This corpus was so divided into the train and test sections. The train section accounted for 90% of the corpus and the remaining 10% belonged to the test section. Using Conditional Random Fields (CRF) method, the Persian NER system resulted in a 92.94% Precision and 78.48% Recall.  }, Keywords = {Natural language Processing, Named Entity Recognition, Named Entity Corpus, Machine learning, Conditional Random Field}, volume = {14}, Number = {3}, pages = {127-142}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.3.127}, url = {http://jsdp.rcisp.ac.ir/article-1-477-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-477-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {Paknezhad, Meghdad and Rezaeian, Mehdi}, title = {Indoor Planar Modeling Using RGB-D Images}, abstract ={In robotic applications and especially 3D map generation of indoor environments, analyzing RGB-D images have become a key problem. The mapping problem is one of the most important problems in creating autonomous mobile robots. Autonomous mobile robots are used in mine excavation, rescue missions in collapsed buildings and even planets’ exploration. Furthermore, indoor mapping is beneficial in finding and rescuing missions. With recent advances, mobile robots are used in hazardous missions such as radioactive areas or collapsing buildings. Having the environment’s map beforehand can boost efficiency and effectiveness of the mission. In order to digitize the environment, several 3D scans are needed. However, these scans should be merged according to a global coordination system to create a correct, consistent model. This process is called image registration. If the robot with 3D scanner is able to accurately localize itself, the registration can be done directly by robots pose. However, due to imprecise robot sensors, self-localization is error prone. Therefore, the geometric structure of overlapping 3D scans is considered. In order to registering various points sets, Iterative Closest Point (ICP) algorithm is used. ICP is the most common approach to align point clouds in two consecutive image frames. This algorithm uses a point to point approach. RGB and depth images which are captured by Kinect are used in this study. In order to reducing data points and performing faster 3D map creation, depth images are converted to point clouds and then segmentation is done according to image planes. For this purpose RGB images are segmented by region growing segmentation algorithm. In this algorithm, the image was initially over segmented. This algorithm uses stack data structure and Euclidean distance in Lab color space to segment the image. Euclidean distance in Lab color space describes the resemblance of two colors to each other. In this algorithm, the aim is to label each pixel to a segment. To this end, each unlabeled pixels Euclidean distance to its neighboring mean color is checked to be within a threshold. For over-segmentation, if the distance satisfies the smaller threshold, the more pixels will be merged to the segment. Afterwards a plane was fit to each segment. After segmentation, each segment should be represented by a plane. Eventually, the segments were merged based on the product of normal vectors and plane fitting error criteria. After segmentation, planes were fit to the new segments again. A given number of points were generated on the plane. ICP algorithm was executed on these points and transfer and rotation matrices were obtained. Generating points on the plane results in fewer points. Therefore, the points were reduced and algorithms performance was increased. The results show that the proposed method increases the speed up to 55 and 91 percent in consecutive and non-consecutive frames on average, respectively.  }, Keywords = {Mapping Problem, RGB-D Images, Kinect sensor}, volume = {14}, Number = {3}, pages = {143-160}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.3.143}, url = {http://jsdp.rcisp.ac.ir/article-1-490-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-490-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2017} } @article{ author = {MahmoudiNasr, Payam and YazdianVarjani, Ali}, title = {An Access Management System to Mitigate Operational Threats in SCADA System}, abstract ={One of the most dangerous insider threats in a supervisory control and data acquisition (SCADA) system is the operational threat. An operational threat occurs when an authorized operator misuses the permissions, and brings catastrophic damages by sending legitimate control commands. Providing too many permissions may backfire, when an operator wrongly or deliberately abuses the privileges. Therefore, an access management system is required to provide necessary permissions and prevent malicious usage.  An operational threat on a critical infrastructure has the potential to cause large financial losses and irreparable damages at the national level. In this paper, we propose a new alarm-trust based access management system reducing the potential of operational threats in SCADA system.  In the proposed system, the accessibility of a remote substation will be determined based on the operator trust and the criticality level of the substation. The trust value of the operator is calculated using the performance of the operator, periodically or in emergencies, when an anomaly is detected. The criticality level of the substation is computed using its properties. Our system is able to detect anomalies that may result from the operational threats. The simulation results in the SCADA power system of Iran show effectiveness of our system.  }, Keywords = {Access control, trust, insider threat, anomaly detection, SCADA}, volume = {14}, Number = {4}, pages = {3-18}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.4.3}, url = {http://jsdp.rcisp.ac.ir/article-1-440-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-440-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2018} } @article{ author = {sadeghi, hamed and AkhavanBitaghsir, Amir}, title = {Signal Detection Based on GPU-Assisted Parallel Processing for Infrastructure-based Acoustical Sensor Networks}, abstract ={Nowadays, several infrastructure-based low-frequency acoustical sensor networks are employed in different applications to monitor the activity of diverse natural and man-made phenomena, such as avalanches, earthquakes, volcanic eruptions, severe storms, super-sonic aircraft flights, etc. Two signal detection methods are usually implemented in these networks for the purpose of event occurrence identification, which are the progressive multi-channel correlator (PMCC) and the so-called Fisher detector. But, the Fisher method is more important and applicable in low signal-to-noise (SNR) ratio conditions, which is of a special interest in acoustical monitoring networks. Unfortunately, an important disadvantage of this algorithm is its relative high detection-time; which limits its application for real-time detection scenarios. This disadvantage is fundamentally due to a beam forming process in Fisher algorithm, which requires doing complete search in a slowness-network, constructed from possible incoming wave front directions and speeds. To address this issue, we propose a method for implementation of this beam forming on a graphics processing unit (GPU), in order to realize a fast-computing and/or near real-time signal processing technique. In addition, we also propose a parallel-processing algorithm for further enhancement of the performance of this GPU-based Fisher detector. Simulation results confirm the performance improvement of Fisher detector, in terms of required processing time for acoustical signal detection applications.  }, Keywords = {Sensor network, array processing, beamforming, parallel processing, GPU}, volume = {14}, Number = {4}, pages = {19-30}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.4.19}, url = {http://jsdp.rcisp.ac.ir/article-1-424-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-424-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2018} } @article{ author = {Fazl-Ersi, Ehsan and KazemiNooghabi, Masou}, title = {Data Clustering Based On Key Identification}, abstract ={Clustering has been one of the main building blocks in the fields of machine learning and computer vision. Given a pair-wise distance measure, it is challenging to find a proper way to identify a subset of representative exemplars and its associated cluster structures. Recent trend on big data analysis poses a more demanding requirement on new clustering algorithm to be both scalable and accurate. A recent advance in graph-based clustering extends its ability to millions of data points by massive utility of engineering endeavor and parallel optimization. However, most other existing clustering algorithms, though promising in theory, are limited in the scalability issue. In this paper, a novel clustering method is proposed that is both accurate and scalable. Based on a simple criteria, ”key” items that are representative of the whole data set are iteratively selected and thus form associated cluster structures. Taking input of pairwise distance measure between data instances, the proposed method searches centers of clusters by identifying data items far away from selected keys, but representative of unselected data items. Inspired by hierarchical clustering, small clusters are iteratively merged until a desired number of clusters are obtained. To solve the scalability problem, a novel tracking table technique is designed to reduce the time complexity which is capable of clustering millions of data points within a few minutes. To assess the performance of the proposed method, several experiments are conducted. The first experiment tests the ability of our algorithm on different manifold structures and various number of clusters. It is observed that our clustering algorithm outperforms existing alternatives in capturing different shapes of data distributions. In the second experiment, the scalability of our algorithm to large scale data points is assessed by clustering up to one million data points with dimensions of up to 100. It is shown that, even with one million data points, the proposed method only takes a few minutes to perform clustering. The third experiment is conducted on the ORL database, which consists of 400 face images of 40 individuals. The proposed clustering method outperforms the compared alternatives in this experiment as well. In the final experiment, shape clustering is performed on the MPEG-7 dataset, which contains 1400 silhouette images from 70 classes, 20 different shapes for each class. The goal here is to cluster the data items (here the binary shapes) into 70 clusters, so that each cluster only includes shapes that belong to one class. The proposed method outperforms other alternative clustering algorithms on this dataset as well. Extensive empirical experiments demonstrate the superiority of the proposed method over existing alternatives, in terms of both effectiveness and efficiency. Furthermore, our algorithm is capable of large-scale data clustering where millions of data points can be clustered in a few seconds.  }, Keywords = {Clustering, Key Identification, Large Scale}, volume = {14}, Number = {4}, pages = {31-42}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.4.31}, url = {http://jsdp.rcisp.ac.ir/article-1-529-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-529-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2018} } @article{ author = {َAbdoos, mohammad and manaei, behrooz}, title = {Improving Named Entity Recognition Using Izafe in Farsi}, abstract ={Named entity recognition is a process in which the people’s names, name of places (cities, countries, seas, etc.) and organizations (public and private companies, international institutions, etc.), date, currency and percentages in a text are identified. Named entity recognition plays an important role in many NLP tasks such as semantic role labeling, question answering, summarization, machine translation, semantic search, and relation extraction and quotation recognition systems. Named entity recognition in the Persian language is far more complex and more difficult than English. In English texts usually proper nouns begin with capital letters and this feature makes it easy to identify named entities, but this feature is absent in Persian language texts. To create a named entity recognition system, generally three methods are being used which include rule-based, machine-learning-based and hybrid methods. Each of these methods has its own advantages and disadvantages. Lack of named entity labeled data is the greatest challenge in Persian text. Because of this problem usually rule-based methods used to extract entities. In this paper firstly, the dictionary of organizations, places and people were extracted from Wikipedia. Wikipedia is one of the best sources for extracting entities in which more than 200000 Farsi-named entities are known to exist. The proposed algorithm classify each Wikipedia article title by using its categories. Each of Wikipedia titles has several categories that can be used to partially identify the named entity type. Then named entity recognition accuracy (precision) was increased using the rules. These rules can be divided into 3 categories that include morphological rules, adjacency and text patterns. The most important rules are adjacency rules. By using these rules the type of entity with the word nearby each entity (like Mr, Mrs , …) can be identified. To evaluate the system, 42000 tokens of BijanKhan corpus were manually annotated (labeled). Early F-measure was calculated 78.79 percent. In continue, named entity recognition accuracy (precision) improved using izāfe which is one of the important Persian language features and 81.94 percent for F-measure was achieved. The results showed that using izāfe in named entity recognition systems significantly increases their accuracy.  }, Keywords = { Named Entity Recognition, Natural Language Processing, Rule Based, Wikipedia, Izafe}, volume = {14}, Number = {4}, pages = {43-54}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.4.43}, url = {http://jsdp.rcisp.ac.ir/article-1-495-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-495-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2018} } @article{ author = {rezaie, vahideh and mohammadpour, mahid and parvin, hamid and nejatian, sam}, title = {An Approach for Extraction of Keywords and Weighting Words for Improvement Farsi Documents Classification}, abstract ={Due to ever-increasing information expansion and existing huge amount of unstructured documents, usage of keywords plays a very important role in information retrieval. Because of a manually-extraction of keywords faces various challenges, their automated extraction seems inevitable. In this research, it has been tried to use a thesaurus, (a structured word-net) to automatically extract them. Authors claim that extraction of more meaningful keywords out of documents can be attained via employment of a thesaurus. The keywords extracted by applying thesaurus, can improve the document classification. The steps to be taken to increase the comprehensiveness of search should be such that in the first step the stop words are removed and the remaining words are stemmed. Then, with the help of a thesaurus are found words equivalent, hierarchical and dependent. Then, to determine the relative importance of words, a numerical weight is assigned to each word, which represents effect of the word on the subject matter and in comparison with other words used in the text. According to the steps above and with the help of a thesaurus, an accurate text classification is performed. In this method, the KNN algorithm is used for the classification. Due to the simplicity and effectiveness of this algorithm (KNN), there is a great deal of use in the classification of texts. The cornerstone of KNN is to compare with the text trained and text tested to determine their similarity between. The empirical results show the quality and accuracy of extracted keywords are satisfiable for users. They also confirm that the document classification has been enhanced. In this research, it has been tried to extract more meaningful keywords out of texts using thesaurus (which is a structured word-net) rather than not using it.  }, Keywords = {thesaurus, information retrieval, extraction of keywords, weight}, volume = {14}, Number = {4}, pages = {55-78}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.4.55}, url = {http://jsdp.rcisp.ac.ir/article-1-449-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-449-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2018} } @article{ author = {Pouramini, Ahmad and Ghayoomi, Masood and Naseri, Amine}, title = {Converting Dependency Treebank to Constituency Treebank for Persian}, abstract ={There are two major types of treebanks: dependency-based and constituency-based. Both of them have applications in natural language processing and computational linguistics. Several dependency treebanks have been developed for Persian. However, there is no available big size constituency treebank for this language. In this paper, we aim to propose an algorithm for automatic conversion of a dependency treebank to a constituency treebank for Persian. Our method is based on an existing method. However, we make modification to enhance its accuracy. The base algorithm constructs a constituency structure according to a set of conversion rules. Each rule maps a dependency relation to a constituency subtree. The constituency structure is built by combining these subtrees. We investigate the effects of the order in which dependency relations are processed on the output constituency structure. We show that the best order depends on the charactersitics of the target language. We also make modification in the algorithm for matching the conversion rules. To match a dependency relation to a conversion rule, we start with detailed infromation and if no match was found, we decrease the details and also change the method for matching. We also make modification in the algorithm used for combining the constituency subtrees. We use statistical data derived from a treebank to find a proper position for attaching a constituency subtree to the projection chain of the head. The expremental results show that these modifications provide an improvement of 16.48% in the accuracy of the conversion algorithm.    }, Keywords = {Natural language processing, Treebanks, Dependency structure, Phrase structure}, volume = {14}, Number = {4}, pages = {79-96}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.4.79}, url = {http://jsdp.rcisp.ac.ir/article-1-492-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-492-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2018} } @article{ author = {Zaremehrjardi, Maryam and Rezaeian, Mehdi}, title = {Using of Model Based Hand Poses Estimation for Imitation of User\'s Arm Movements by Robot Arm}, abstract ={Pose estimation is a process to identify how a human body and/or individual limbs are configured in a given scene. Hand pose estimation is an important research topic which has a variety of applications in human-computer interaction (HCI) scenarios, such as gesture recognition, animation synthesis and robot control. However, capturing the hand motion is quite a challenging task due to its high flexibility. Many sensor-based and vision-based methods have been proposed to fulfill the task. In sensor-based systems, specialized hardware is used for hand motion capture. Generally, vision-based hand pose estimation methods can be divided into two categories: appearance-based methods and model-based methods. In appearance-based approaches, various features are extracted from the input images to estimate the hand pose. Usually a lot of training samples are used to train a mapping function from the features to the hand poses in advance. Given the learned mapping function, the hand pose can be estimated efficiently. In model-based approaches the hand pose is estimated by aligning a projected 3D hand model to the extracted hand features in the inputs. Therefore, the desired information to be provided includes state at any time. These methods require a lot of calculations which are not possible in practice to implement them immediately. Hand pose estimation using (color/depth) images consist of three steps: Hand detection and its separation Feature extraction Setting the parameters of the model using extracted feature and updating the model To extract necessary features for pose estimation, depending on used model and usage of hand gesture analysis, features such as fingertips position, number of fingers, palm position and joint angles are extracted. In this paper a model-based markerless dynamic hand poses estimation scheme is presented.  Motion Capture is the process of recording a live motion event and translating it into usable mathematical terms by tracking a number of key points in space over time and combining them to obtain a single 3D representation of the performance. The sequence of depth images, color images and skeleton data obtained from Kinect (a new tool for markerless motion capture) at 30 frames per second are as inputs of this scheme. The proposed scheme exploits both temporal and spatial features of the input sequences, and focuses on index and thumb fingertips localization and joint angles of the robot arm to mimic the user's arm movements in 3D space in an uncontrolled environment. The RoboTECH II ST240 is used as a real robot arm model. Depth and skeleton data are used to determine the angles of the robot joints. Three approaches to identify the tip of the thumb and index fingers are presented using existing data, each with its own limitations. In these approaches, concepts such as thresholding, edge detection, making convex hull, skin modeling and background subtraction are used. Finally, by comparing tracked trajectories of the user's wrist and robot end effector, the graphs show an error about 0.43 degree in average which is an appropriate performance in this research. The key contribution of this work is hand pose estimation per every input frame and updating arm robot according to estimated pose. Thumb and index fingertips detection as part of feature vector resulted using presented approaches. User movements transmit to the corresponding Move instruction for robot. Necessary features for Move instruction are rotation values around joints in different directions and opening value of index and thumb fingers at each other.  }, Keywords = {pose estimation, depth data, markerless motion capture, Kinect, 3d model}, volume = {14}, Number = {4}, pages = {97-116}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.4.97}, url = {http://jsdp.rcisp.ac.ir/article-1-522-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-522-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2018} } @article{ author = {Mortazavi, Sayed Mohammad and NadimiShahraki, Mohammad Hossein and Mosakhani, Mostaf}, title = {Improving the accuracy of the author name disambiguation by using clustering ensemble}, abstract ={Today, digital libraries are important academic resources including millions of citations and bibliographic essential information such as titles, author's names and location of publications. From the view of knowledge accumulation management, the ability to search fast, accurate, desired contents, has a great importance. The complexity and similarity in these resources cause many challenges and ambiguities. One of the most of these challenges is the author name disambiguation which makes an extensive scope of research. Although many effective methods have been developed by using clustering techniques in disambiguation of the author's name, the accuracy of these methods is not acceptable and still there are some problems such as fragmentation and error in the produced results of these methods, since there is no uniform standard of citations, various combinations, and numerous, written, verbal patterns. In fact, experiences have shown that the use of a single method to disambiguate names does not provide results with a high accuracy despite concerns expressed above. In this paper, a new method is proposed to disambiguate author names in different formats and combinations with more accuracy. The proposed solution carries out the disambiguation in two steps; In the first step, agglomerative hierarchical clustering algorithm produces clusters using similar functions and different thresholds. In the second step, clusters produced by clustering ensemble technique in the previous stage are combined to provide more accurate clusters with less fragmentation. The proposed method is experimentally evaluated by conducted DBLP datasets with K criterion. The evaluation results show that the proposed method enhances the accuracy of disambiguation of author names in different formats.  }, Keywords = {Digital libraries, Author Name Disambiguation, Ambiguous name, Clustering Ensemble}, volume = {14}, Number = {4}, pages = {117-128}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.4.117}, url = {http://jsdp.rcisp.ac.ir/article-1-524-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-524-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2018} } @article{ author = {Pourmohammadi, Sara and Maleki, Ali}, title = {A Fuzzy C-means Clustering Approach for Continuous Stress Detection during Driving}, abstract ={Stress is one of the main causes of physical and mental disorders leading to various types of diseases. In recent two decades, stress level detection during driving to avoid accidents has attracted much of researchers’ attentions. However, the existing studies usually neglect this fact that stress level during driving varies due to irregular events. Contrary to the previous works, this paper demonstrates that to assume a fixed level of stress for a long period- e.g. while driving in highway- is unreasonable. According to the above assumption, a novel approach for continuous stress detection is proposed based on fuzzy c-means clustering and cluster labeling by the expert. Fuzzy c-means clustering is used to specify levels of stress instead of the former different classification and labeling methods. Concurrently, utilizing background knowledge of data and clustering results, the label of each cluster is obtained. Then, proper weights are assigned to labeled clusters.  By combining the membership values of clusters and weights associated with each cluster’s label, a score of stress is obtained in short time intervals. Stress in driving dataset provide stressful conditions during real driving. The experiments were performed on a specific route of open roads and where drivers traverse were limited to daily commutes. For each drive, Electrocardiogram (ECG), Electromyogram (EMG), foot and hand Galvanic skin response (GSR), respiration and marker signals were acquired from the sensors worn by the driver. Clearly, the more number of physiological signals are used, the more computational cost must be paid, so in this work, heart rate, EMG, foot GSR and hand GSR from mentioned dataset are selected. After that, six features consisting of the mean value of the heart rate, the mean value of EMG, the mean value of the hand GSR and the mean value of foot GSR in addition to mean absolute differences for hand and foot GSR are extracted for each 10 second window (100 second window with 90% overlap) of signals. Next step is to cluster via fuzzy c-means algorithm. In this study, the data is located in 5 clusters and according to the membership degree of each window, input signals and background data from dataset, an adequate label is assigned by the expert to each cluster. The labels of these five clusters are "very low", "low", "medium", “high" and "very high" stress, which are respectively the least stressed to the most stressful. Therefore, the base weight vector is obtained as . The weights assigned to the clusters will be a permutation of the mentioned base weight vector. After assigning the weight of clusters, in each window, the membership degree obtained by the Fuzzy c-means method is multiplied by the weight assigned to that cluster and the resulting numbers are accumulated for the 5 clusters. The calculated value scales to the range of 0 to 100, in order to quantifying the stress. For better representation, a collection of 100 different colors in the range of dark blue to dark red of the visible spectra will be defined by the use of “colormap” command in MATLAB. By taking the calculated value to the range of 0 to 100, one of the mentioned colors will be chosen. So the color will be associated to the stress value of the corresponding window. In this paper, in addition to the qualitative assessment of the results, the correlation between the determined stress and subjective rating scores is considered as a quantitative criterion. The results illustrate the effectiveness of the proposed method to improve both the precision and accuracy of stress detection. In fact, the stress in driving dataset have imprecise labels which the proposed systematic approach estimates the stress continuously utilizing the background knowledge of data. The results clearly represent valid, efficient criteria for stress during driving in each moment without using long time window, show the continues stress from the beginning of the experiment until the end of it, and exaggerate individual differs and unexpected hazards during the experiment.  }, Keywords = {Continuous stress detection, Stress during driving, Fuzzy c-means clustering}, volume = {14}, Number = {4}, pages = {129-142}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.4.129}, url = {http://jsdp.rcisp.ac.ir/article-1-383-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-383-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2018} } @article{ author = {Jafari, Hoda Sadat and homayounpour, mohammadmehdi}, title = {A comparison of machine learning techniques for Persian Extractive Speech to Speech Summarization without Transcript}, abstract ={In this paper, extractive speech summarization using different machine learning algorithms was investigated. The task of Speech summarization deals with extracting important and salient segments from speech in order to access, search, extract and browse speech files easier and in a less costly manner. In this paper, a new method for speech summarization without using automatic speech recognition system (ASR) is proposed. ASR systems usually have high error rates especially in adverse acoustic environment and for low resource languages. Our goal was to answer this question: is it possible to summarize a Persian speech without ASR using less or no training data? We have proposed a method which discovers salient parts directly from speech signal by using a semi-supervised algorithm. The proposed algorithm consists of three main stages, features extraction, identifying key patterns and selecting important sentences. First we have segmented speech voices manually into sentences to eliminate sentence segmentation errors. Therefore, we could have better comparison between different summarization methods. Then we have extracted some features from each sentence such as sentence duration, if the sentence is first or last sentence in the speech and so on. Also, repetitive patterns between each two sentence of speech are discovered directly from speech signal by using S-DTW algorithm. S-DTW algorithm can discover repetitive patterns between two speech signals by using MFCC features. By using these repetitive patterns between each pair of sentences we can make a similarity matrix. Therefore, we could measure the similarity distance between each pair of sentences and eliminate redundant sentences from summary without the need to use an ASR system After finding the similarity between each two speech segments and extracting some features from each segment, various machine learning algorithms including unsupervised (MMR, TextRank), supervised (SVM, Naïve Bayes) and semi-supervised algorithms (self-training, Co-training) are used in order to extract salient parts. Experiences are done in read Persian news. The results show that using semi-supervised co-training method and appropriate features, the performance of speech summarization system on read Persian news corpus can improve about 3% compared to selecting the first sentences and by 5% compared to longest sentences when ROUGE-3 is used as the evaluation measure.    }, Keywords = {Extractive speech summarization, speech signal, key patterns, S-DTW algorithm, machine learning}, volume = {14}, Number = {4}, pages = {143-157}, publisher = {Research Center on Developing Advanced Technologies}, doi = {10.29252/jsdp.14.4.143}, url = {http://jsdp.rcisp.ac.ir/article-1-491-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-491-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2018} }