@article{ 
author = {Reshadat, Vahideh and HoorAli, Maryam and Faili, Heshaam},  
title = {A New Method for Improving Computational Cost of Open Information Extraction Systems Using Log-Linear Model}, 
abstract ={Information extraction (IE) is a process of automatically providing a structured representation from an unstructured or semi-structured text. It is a long-standing challenge in natural language processing (NLP) which has been intensified by the increased volume of information and heterogeneity, and non-structured form of it. One of the core information extraction tasks is relation extraction which aims at extracting semantic relations among entities from natural language text. Traditional relation extraction techniques were relation-specific, producing new instances of relations determined a priori. While effective, this model is not applicable in cases where the relations are not defined a priori or when the number of relations is high. Open Relation Extraction (ORE) methods were developed to elicit instances of arbitrary relations while requiring fewer training examples. Since ORE systems are employed by the applications depended on large-scale relation extraction, high performance and low computational cost are major requirements for ORE methods. This is particularly important in the large scales such as the Web. Many OIE systems have been proposed in recent years. These approaches range from shallow (such as part-of-speech tagging) to deep (such as semantic role labeling), therefore they differ in their performance level and computational cost. In this paper, we use the state-of-the-art shallow NLP tools to extract instances of relations. A supervised log-linear model for OIE is presented which is based on using advantages of shallow NLP tools, as they are fast and lead to a low computational time. Extractor which is the main core of proposed approach integrates a high performance subset of the shallow NLP tools with the strength of the deep NLP tools by using a supervised log linear model and produces a high performance method that is scalable. This causes efficient use of time and therefore reduces computational cost and increases precision. Proposed approach achieves higher precision and recall than ReVerb, one of the most successful shallow OIE system.},  
Keywords = {Information Extraction, Open Information Extraction, Relation Extraction, Knowledge Discovery, Fact Extraction},
volume = {16},
Number = {1}, 
pages = {3-20}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.1.3},
url = {http://jsdp.rcisp.ac.ir/article-1-681-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-681-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Pouramini, Jafar and Minaei-Bidgoli, Behrouze and Esmaeili, Mahdi},  
title = {A Novel One Sided Feature Selection Method for Imbalanced Text Classification}, 
abstract ={The imbalance data can be seen in various areas such as text classification, credit card fraud detection, risk management, web page classification, image classification, medical diagnosis/monitoring, and biological data analysis. The classification algorithms have more tendencies to the large class and might even deal with the minority class data as the outlier data. The text data is one of the areas where the imbalance occurs. The amount of text information is rapidly increasing in the form of books, reports, and papers. The fast and precise processing of this amount of information requires efficient automatic methods. One of the key processing tools is the text classification. Also, one of the problems with text classification is the high dimensional data that lead to the impractical learning algorithms. The problem becomes larger when the text data are also imbalance. The imbalance data distribution reduces the performance of classifiers. The various solutions proposed for this problem are divided into several categories, where the sampling-based methods and algorithm-based methods are among the most important methods. Feature selection is also considered as one of the solutions to the imbalance problem. In this research, a new method of one-way feature selection is presented for the imbalance data classification. The proposed method calculates the indicator rate of the feature using the feature distribution. In the proposed method, the one-figure documents are divided in different parts, based on whether they contain a feature or not, and also if they belong to the positive-class or not. According to this classification, a new method is suggested for feature selection. In the proposed method, the following items are used. If a feature is repeated in most positive-class documents, this feature is a good indicator for the positive-class; therefore, this feature should have a high score for this class. This point can be shown as a proportion of positive-class documents that contain this feature. Besides, if most of the documents containing this feature are belonged to the positive-class, a high score should be considered for this feature as the class indicator. This point can be shown by a proportion of documents containing feature that belong to the positive-class. If most of the documents that do not contain a feature are not in the positive-class, a high score should be considered for this feature as the representative of this class. Moreover, if most of the documents that are not in the positive class do not contain this feature, a high score should be considered for this feature. Using the proposed method, the score of features is specified. Finally, the features are sorted in descending order based on score, and the necessary number of required features is selected from the beginning of the feature list. In order to evaluate the performance of the proposed method, different feature selection methods such as the Gini, DFS, MI and FAST were implemented. To assess the proposed method, the decision tree C4.5 and Naive Bayes were used. The results of tests on Reuters-21875 and WebKB figures per Micro F , Macro F and G-mean criteria show that the proposed method has considerably improved the efficiency of the classifiers than other methods.  },  
Keywords = {Feature selection, Imbalanced class, High dimensionality, Text classification},
volume = {16},
Number = {1}, 
pages = {21-40}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.1.21},
url = {http://jsdp.rcisp.ac.ir/article-1-728-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-728-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Kebriaei, Hamed and Kamalinejad, Howra and NadjarAraabi, Babak},  
title = {Short term load forecast by using Locally Linear Embedding manifold learning and a hybrid RBF-Fuzzy network}, 
abstract ={The aim of the short term load forecasting is to forecast the electric power load for unit commitment, evaluating the reliability of the system, economic dispatch, and so on. Short term load forecasting obviously plays an important role in traditional non-cooperative power systems. Moreover, in a restructured power system a generator company (GENCO) should predict the system demand and its corresponding price for efficient decision making. The task of a forecasting engine is to find the relation of the inputs and outputs of the system and also predicts the outputs for a given inputs. Therefore, the accuracy of forecasting is highly affected by the inputs of the forecasting engine. This effect can be studied from two points of view; First, extracting the more informative inputs and second, reducing the dimension of input space, both make it possible to learn the forecasting network via more simple models with more generalization. As a result, a reduced informative input space leads to lower prediction error. In many previous load forecasting methods, the inputs have been selected empirically. In this manner, the more correlative factors with the load in the forecasting day have been chosen as the inputs. They are generally a combination of load history and weather conditions. Several researches are focused on mathematical approaches of the input selection which are mainly based on principal component analysis (PCA) method as well as some intelligent algorithms. In this paper, a manifold learning method namely Locally Linear Embedding (LLE) is proposed, aiming to extract more informative inputs and to reduce the dimension of input space for short term load forecasting. Among all methods based on manifold learning, it can be seen that LLE performs very well in extracting the electric load curve features. The aim of this paper is to analyze the features of the load curve for estimating this curve in future. The extensive computational experiments show that the extracted features by LLE results in less prediction error than two other methods. Furthermore, LLE acts faster and makes input dimension lower than the two other methods. In the following section we will discuss the LLE method. The LLE method finds the nonlinear relationships among features by mapping a locally linear manifold in the feature space. Extracting the more informative inputs by extracting the combinational features by finding the nonlinear dependences of the features, results in reducing the dimension of input space. The resulted inputs from feature extraction and dimension reduction are utilized for load forecasting. To examine the effect of the proposed feature extraction method on load prediction error, a hybrid prediction system is proposed which is a combination of a radial basis function (RBF) network and a fuzzy system. The RBF network is the core of the prediction engine and works with historical load data as its inputs. The fuzzy inference system is combined with the RBF network to incorporate the impact of temperature on load. The case studies are carried out on the real data of electric power load of Mazandaran area in Iran. The efficiency of the proposed forecasting engine is compared with three benchmarks, the artificial neural network, time series and neuro-fuzzy methods. Furthermore, the proposed input selection method (LLE) is compared with principal component analysis (PCA) and empirical selection of inputs. Simulation results with statistical significance analysis show that the LLE method with the proposed forecasting engine is superior to other input selection methods and forecasting engines in sense of lower input dimension and lower prediction error.},  
Keywords = {Manifold learning, input selection, RBF network, fuzzy system, short term load forecasting. },
volume = {16},
Number = {1}, 
pages = {41-56}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.1.41},
url = {http://jsdp.rcisp.ac.ir/article-1-776-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-776-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Haji-Esmaeili, Mohammad Mahdi and Montazer, Gholamali},  
title = {Automatic Colorization of Grayscale Images Using Generative Adversarial Networks}, 
abstract ={Automatic colorization of gray scale images poses a unique challenge in Information Retrieval. The goal of this field is to colorize images which have lost some color channels (such as the RGB channels or the AB channels in the LAB color space) while only having the brightness channel available, which is usually the case in a vast array of old photos and portraits. Having the ability to colorize such images would give us a multitude of possibilities ranging from colorizing old and historic images to providing alternate colorizations for real images or artistic creations. Be that as it may, the progress in this field is trivial compared to what the professionals are able to do using special-purpose applications such as Photoshop or GIMP. On the other hand, losing the information stored in color channels and having only access to the primary brightness channel, makes this problem a unique challenge, since the main aim of automatic colorization is not to find the image’s “real” color but to colorize it in such a way that makes it “seem real” as the original color information is lost forever and the only way to colorize it, is to provide a somewhat “proper” estimation. In this research we propose a model to automatically colorize gray human portraits. We start by reviewing the methods used for the task of image colorization and provide an explanation as to why most of them collapse to a situation known as “Averaging”. To counteract this effect, we design our end-to-end model with two separate deep neural networks forming a Generative Adversarial Network (GAN), one to colorize the images and the other to evaluate the colorization of the first network and guide it towards the proper distribution. The results show improvements over other proposed methods in this field especially in the case of colorizing human portraits along faster train times. This method not only works on real human portraits but also on non-human and artistic portraits that can be leveraged to colorize hand-drawn images some of which may take minutes up to hours by hand.},  
Keywords = {colorization, gray scale images, deep neural networks, generative adversarial networks, image information retrieval},
volume = {16},
Number = {1}, 
pages = {57-74}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.1.57},
url = {http://jsdp.rcisp.ac.ir/article-1-789-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-789-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Amintoosi, Mahmoo},  
title = {Enhancement of Learning Based Image Matting Method with Different Background/Foreground Weights}, 
abstract ={The problem of accurate foreground estimation in images is called Image Matting. In image matting methods, a map is used as learning data, which is produced by those pixels that are definitely foreground, definitely background ,and unknown. This three-level pixel map is often referred to as a trimap, which is produced manually in alpha matte datasets. The true class of unknown pixels will be estimated by minimizing of an objective function. Several methods for image matting has been proposed. The learning–based method is one the pioneering works which is the basis of many other approaches in the field of image matting.  In this method it is assumed that each pixel’s alpha value is a linear combination of its associated neighboring pixels. A Laplacian matrix in the objective function shows the similarity of the pixels. The coefficients of the linear combination are estimated with a local learning process by minimizing a quadratic cost function. The method of Lagrange multiplier and ridge regression technique are used for estimation of alpha values. In this objective function the violation of the predefined training pixels’ alpha values from their true values is controlled by a penalty term. Considering this coefficient as infinity, forces the matte (alpha) value to be 1 for the labeled foreground pixels and 0 for background. The weight of this penalty term still was taken equal for all training samples. In this paper the performance of the matting method is increased by considering different weights for different learning pixels. The good performance of the proposed method is demonstrated in two applications. The first application is improving the quality of a text extraction method and the second application is enhancement of an eye retinal segmentation system. In the first application, a Persian text which is fused onto a textured background is extracted by a thresholding method. After that the segmented output is enhanced by the proposed matting method. In the second application, segmentation is done with an existing vessel extraction method. The edges’ pixels of detected vessels that may be classified inaccurately are classified by the proposed image matting method. Subjective and objective comparisons show the better performance of the proposed method.},  
Keywords = {Image Matting, Image Segmentation, Machine Learning, Text Extraction, Retinal Vessel Segmentation},
volume = {16},
Number = {1}, 
pages = {75-90}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.1.75},
url = {http://jsdp.rcisp.ac.ir/article-1-797-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-797-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Shahshahani, Mahsa Sadat and Mohseni, Mahdi and Shakery, Azadeh and Faili, Heshaam},  
title = {PAYMA: A Tagged Corpus of Persian Named Entities}, 
abstract ={The goal in the named entity recognition task is to classify proper nouns of a piece of text into classes such as person, location, and organization. Named entity recognition is an important preprocessing step in many natural language processing tasks such as question-answering and summarization. Although many research studies have been conducted in this area in English and the state-of-the-art NER systems have reached performances of higher than 90 percent in terms of F1 measure, there are very few research studies on this task in Persian. One of the main important reasons for this may be the lack of a standard Persian NER dataset to train and test the NER systems. In this research we create a standard tagged Persian NER dataset which will be distributed freely for research purposes. In order to construct this standard dataset, we studied the existing standard NER datasets in English and came to the conclusion that almost all of these datasets are constructed using news data. Thus we collected documents from ten news websites in Persian. In the next step, in order to provide the annotators with guidelines to tag these documents, we studied the guidelines used for constructing CoNLL and MUC English datasets and created our own guidelines considering the Persian linguistic rules. Using these guidelines, all words in documents can be labeled as person, location, organization, time, date, percent, currency, or other (words that are not in any of these 7 classes). We use IOB encoding for annotating named entities in documents, like most of the existing English NER datasets. Using this encoding, the first token of a named entity is labeled with B, and the next tokens (if exist) are labeled with I. The words that are not part of any named entity are labeled with O. The constructed corpus, named PAYMA, consists of 709 documents and includes 302530 tokens. 41148 tokens out of these tokens are labeled as named entities and the others are labeled as O. In order to determine the inter-annotator agreement, 160 documents were labeled by a second annotator. Kappa statistic was estimated as 95% using words that are labeled as named entities. After creating the dataset, we used the dataset to design a hybrid system for named entity recognition. We trained a statistical system based on the CRF algorithm, and used its output as a feature to train a bidirectional LSTM recurrent neural network. Moreover, we used the k-means word clustering method to cluster the words and fed the cluster number of each word to the LSTM neural network. This form of combining CRF with neural networks and using the cluster number for each word is the novelty of this research work. Experimental results show that the final model can reach an F1 score of 87% at word-level and 80% at phrase level.},  
Keywords = {Persian named entity corpus, named entity recognition, rule-based model, deep-learning based model, conditional random field’s method},
volume = {16},
Number = {1}, 
pages = {91-110}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.1.91},
url = {http://jsdp.rcisp.ac.ir/article-1-769-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-769-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {MostajerKheirkhah, Fateme and Asghari, Habibollah and Yazdani, Darab},  
title = {On the use of Textural Features and Neural Networks for Leaf Recognition}, 
abstract ={for recognizing various types of plants, so automatic image recognition algorithms can extract to classify plant species and apply these features. Fast and accurate recognition of plants can have a significant impact on biodiversity management and increasing the effectiveness of the studies in this regard. These automatic methods have involved the development of recognition techniques and digital image processing pattern.  Most of the previous studies on the classification and identification of plant species from leaf images are based on the shape, texture and color features. There were also different methods of data modeling which have been used to leave plant recognition. In this paper, we investigate a novel approach for the recognition of plant species using texture feature GIST to extract general features. In the classification step, Patternnet feed forward neural network algorithm has been applied. Essentially, the GIST feature has been designed to be employed for image classification. In this study, GIST feature vectors are considered as the basis of the leaves’ classification. The GIST descriptor of an image is computed by the first filtering of an image by a filter bank of Gabor filters, and then averaging the responses of filters in each block on a no overlapping grid. For evaluation of our approach, we have applied the algorithm on scan and pseudo-scan images of two famous different datasets Image CLEF2012 and Leaf snap with a high various. The results show that in comparison to some widely used algorithms, our approach outperforms in the case of time and also the accuracy of classification. Substantial results can be achieved when the image of the plants are aligned with one another and when we deal with pseudo scan images. The detection of combinations of leaves that have jagged edges is an important contribution of this study. In many of the previous algorithms, the computational complexity of this detection is high. While by using the GIST feature vector, these types of images are processed simply and precisely (above 90%).  precisely (above 90%).},  
Keywords = {Species recognition, GIST feature vector, Neural networks, Gabor filter},
volume = {16},
Number = {1}, 
pages = {111-124}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.1.111},
url = {http://jsdp.rcisp.ac.ir/article-1-792-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-792-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Mohebbi, javad and Moradi, Morteza and Salami, Bagher},  
title = {Proposed Feature Selection for Dynamic Thermal Management in Multicore Systems}, 
abstract ={Increasing the number of cores in order to the demand of more computing power has led to increasing the processor temperature of a multi-core system. One of the main approaches for reducing temperature is the dynamic thermal management techniques. These methods divided into two classes, reactive and proactive. Proactive methods manage the processor temperature, by forecasting the temperature before reaching the threshold temperature. In this paper, the effects of using proper features for processor thermal management have been considered. In this regard, three models have been proposed for temperature prediction, control response estimation, and thermal management, respectively. A multi-layered perceptron neural network is used to predict the temperature and to control the response. Also, an adaptive neuro-fuzzy inference system is utilized for controlling temperature. An appropriate data set, which includes a variety of processor temperature variations, has been created to train each model. Some features of the dataset are collected by monitoring the thermal sensors and performance counters. In addition, a number of features are created by proposing processes to increase the accuracy of each model . Then, the features of each model are selected by the proposed method. The evaluation of the proposed model for predicting and controlling the processor temperature for different time distances is below 0.6 ° C.},  
Keywords = {thermal prediction, control response, feature selection, multilayer perceptron, adaptive neuro-fuzzy inference system},
volume = {16},
Number = {1}, 
pages = {125-142}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.1.125},
url = {http://jsdp.rcisp.ac.ir/article-1-801-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-801-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Sajedi, Hedieh and Taslimi, Mahnaz},  
title = {Author gender identification from text using Bayesian Random Forest}, 
abstract ={Nowadays high usage of users from virtual environments and their connection via social networks like Facebook, Instagram, and Twitter shows the necessity of finding out shared subjects in this environment more than before. There are several applications that benefit from reliable methods for inferring age and gender of users in social media. Such applications exist across a wide area of fields, from personalized advertising to law enforcement of reputation management. Text posts represent a large portion of user generated content, and contain information which can be relevant to discovering undisclosed user attributes, or investigating the honesty of self-reported age and gender. Because the highest rate of information exchanges is in text format, author identification from the aspects like age, gender, political and religious opinions from these contents will seem more considerable. Gender identification  that could be useful in security and marketing, also answers the following question: given a short text document, can we identify if the author is a male or a female?  This question is motivated by recent events where people faked their gender on the Internet. In this paper, author gender identification in blog’s data is investigated. In this regard, four groups of features include syntactic features, word-based features, character-based features, and function words are employed. In addition, character n-gram features is used for improving the accuracy of classification. For evaluation of the proposed method, 3212 texts were collected from Technorati.com and blogger.com. Experimental results demonstrate that these types of features are practical. furthermore, a new classification method called "Bayesian Random Forest" is introduced. Each tree in Bayesian Random Forest  is a Bayes tree. The results of experiment show that this method attains noticeable results in comparison with other classification algorithms such as Naïve Bayes, Naïve Bayes Tree, and Random Forest and it increases accuracy of gender identification to 89.5%.  },  
Keywords = {Author gender identification, Random Forest, NBTree, Text mining, Classification},
volume = {16},
Number = {1}, 
pages = {143-157}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.1.143},
url = {http://jsdp.rcisp.ac.ir/article-1-429-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-429-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Imani, Maryam and Ghassemian, Hass},  
title = {Supervised Feature Extraction of Face Images for Improvement of Recognition Accuracy}, 
abstract ={Dimensionality reduction methods transform or select a low dimensional feature space to efficiently represent the original high dimensional feature space of data. Feature reduction techniques are an important step in many pattern recognition problems in different fields especially in analyzing of high dimensional data. Hyperspectral images are acquired by remote sensors and human face images are one of the high dimensional data types. Because of limitation in the number of training samples, feature reduction is the important preprocessing step for classification of these types of data. Face recognition is one of the main interesting studies in human computer interaction applications. Face is among the most significant biometric characteristics which are used for identification of individuals. Before face recognition, feature reduction is an important processing step. In this paper, we apply the new feature extraction methods, which have been firstly proposed for feature reduction of hyperspectral imagery remote sensing, on the face databases for the first time. In this research, we compare the performance of seven new feature extraction methods with four state-of-the-art feature extraction methods. The proposed methods are Nonparametric Supervised Feature Extraction (NSFE), Clustering Based Feature Extraction (CBFE), Feature Extraction Using Attraction Points (FEUAP), Cluster Space Linear Discriminant Analysis (CSLDA), Feature Space Discriminant Analysis (FSDA), Feature Extraction using Weighted Training samples (FEWT), and Discriminant Analysis- Principal Component 1 (DA-PC1). The experimental results on two face databases, Yale and ORL, show the better performance of some new feature extraction methods, from the recognition accuracy point of view compared to methods such as linear discriminant analysis (LDA), non-parametric weighted feature extraction (NWFE), median-mean line discriminant analysis (MMLDA), and supervised locality preserving projection (LPP).},  
Keywords = {Face recognition, Feature extraction, Classification, Hyperspectral},
volume = {16},
Number = {1}, 
pages = {158-172}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.1.158},
url = {http://jsdp.rcisp.ac.ir/article-1-804-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-804-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Behbahani, Fereshteh and Mehrdad, Vahid and Ebrahimnezhad, Hossei},  
title = {3D Models Recognition in Fourier Domain Using Compression of the Spherical Mesh up to the Models Surface}, 
abstract ={Representing 3D models in diverse fields have automatically paved the way of storing, indexing, classifying, and retrieving 3D objects. Classification and retrieval of 3D models demand that the 3D models represent in a way to capture the local and global shape specifications of the object. This requires establishing a 3D descriptor or signature that summarizes the pivotal shape properties of the object. Therefore, in this work, a new shape descriptor has been proposed to recognize 3D model utilizing global characteristics. To perform feature extraction in the proposed method, the bounding meshed sphere surrounding the 3D model and concentrated from the outside toward the center of the model. Then, the length of the path which the sphere's vertices travel from the beginning to the model’s surface will be measured. These values are exploited to compute the path function. The engendered function is robust against isometric variations and it is appropriate for recognizing non-rigid models. In the following, the Fourier transform of the path function is calculated as the features vector, and then the extracted features vector is utilized in SVM classifier. By exploiting the properties of the magnitude response of the Fourier transform of the real signals, the model can be analyzed in the lower space without losing the inherent characteristics, and no more pose normalization is needed. The simulation results based on the SVM classifier on the McGill data set show the proposed method has the highest accuracy (i.e. 79.7%) among the compared related methods. Moreover, the confusion matrix for performing 70% trained SVM classifier indicates the suitable distinguishing ability for similar models and does not have a high computational complexity of model processing in 3D space.},  
Keywords = {Feature Content base, Feature extraction, 3D Models Recognition, SVM Classifier, Discrete Fourier Transform},
volume = {16},
Number = {2}, 
pages = {3-18}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.2.3},
url = {http://jsdp.rcisp.ac.ir/article-1-633-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-633-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Momenian, Nayere and TorkLadani, Behrouz},  
title = {Reverse Engineering of Network Software Binary Codes for Identification of Syntax and Semantics of Protocol Messages}, 
abstract ={Reverse engineering of network applications especially from the security point of view is of high importance and interest. Many network applications use proprietary protocols which specifications are not publicly available. Reverse engineering of such applications could provide us with vital information to understand their embedded unknown protocols. This could facilitate many tasks including deep protocol inspection in next generation firewalls and analysis of suspicious binary codes. The goal of protocol reverse engineering is to extract the protocol format and the protocol state machine. The protocol format describes the structure of all messages in protocol and the protocol state machine describes the sequence of messages that the protocol accept. Recently, there has been rising interest in automatic protocol reverse engineering. These works are divided into activities that extract protocol format and activities that extract protocol state machine. They can also be divided into those uses as input network traffic and those uses as input program implements the protocol. However, although there are some researches in this field, they mostly focused on extracting syntactic structure of the protocol messages. In this paper, some new techniques are presented to improve extracting the format (both the syntax and semantics) of protocol messages via reverse engineering of binary codes of network applications. To do the research, an integration of dynamic and static binary code analysis are used. The field extraction approach first detects length fields and separators and then by applying rules based on compiler principles locates all the fields in the messages. The semantic extraction approach is based on the semantic information available in the program implements of the protocol and also information exists in the environment of the program. For evaluating the proposed approach, four different network applications including DNS, eDonkey, Modbus, and STUN were analyzed. Experimental results show that the proposed techniques not only could extract more complete syntactic structure of messages than similar works, but also it could extract a set of advantageous semantic information about the protocol messages that are not achievable in previous works.  },  
Keywords = {Reverse engineering, Protocol format extraction, Semantic information},
volume = {16},
Number = {2}, 
pages = {19-40}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.2.19},
url = {http://jsdp.rcisp.ac.ir/article-1-502-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-502-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Kiani, Vahid and Harati, Ahad and Vahedian, Abedi},  
title = {Planelet Transform: A New Geometrical Wavelet for Compression of Kinect-like Depth Images}, 
abstract ={With the advent of cheap indoor RGB-D sensors, proper representation of piecewise planar depth images is crucial toward an effective compression method. Although there exist geometrical wavelets for optimal representation of piecewise constant and piecewise linear images (i.e. wedgelets and platelets), an adaptation to piecewise linear fractional functions which correspond to depth variation over planar regions is still missing. Such planar regions constitute major portions of the indoor depth images and need to be well represented to allow for desirable rate-distortion trade-off. In this paper, second-order planelet transform is introduced as an optimal representation for piecewise planar depth images with sharp edges along smooth curves. Also, to speed up the computation of planelet approximation of depth images, an iterative estimation procedure is described based on non-linear least squares and discontinuity relaxation. The computed approximation is fed to a rate-distortion optimized quad-tree based encoder; and the pruned quadtree is encoded into the bit-stream. Spatial horizontal and vertical plane prediction modes are also introduced to further exploit geometric redundancy of depth images and increase the compression ratio. Performance of the proposed planelet-based coder is compared with wedgelets, platelets, and general image encoders on synthetic and real-world Kinect-like depth images. The synthetic images dataset consists of 30 depth images of different scenes which are manually selected from eight video sequences of ICL-NUIM RGBD Benchmark dataset. The dataset of real-world images also includes 30 depth images of indoor scenes selected from Washington RGBD Scenes V2 dataset captured by Kinect-like cameras. In contrast to former geometrical wavelets which approximate smooth regions of each image using constant and linear functions, planelet transform exploits a non-linear model based on linear fractional functions to approximate every smooth region. Visual comparisons by 3D surface reconstruction and visualization of the decoded depth images as surface plots revealed that at a specific bit-rate the planelets-based coder better preserves the geometric structure of the scene compared with the former geometric wavelets and the general images coders.  Numerical evaluations showed that compression of synthetic depth-images by planelets results in a considerable PSNR improvement of 0.83 dB and 6.92 dB over platelets and wedgelets, respectively. Due to absence of the noise, the plane prediction modes were very successful on synthetic images and boosted the PSNR gap over platelets and wedgelets to 5.73 dB and 11.82 dB, respectively. The proposed compression scheme also performed well on the real-world depth images. Compared with wedgelets, planelets-based coder with spatial prediction achieved noticeable quality improvement of 2.7 dB at the bit-rate of 0.03 bpp. It also led to 1.46 dB quality improvement over platelets at the same bit-rate. In this experiment, application of planelets-based coder led to 2.59 dB and 1.56 dB increase in PSNR over JPEG2000 and H.264 general image coders. Similar results are also achieved in terms of SSIM metric.  },  
Keywords = {depth-image compression, geometrical wavelets, planelet transform, linear fractional functions},
volume = {16},
Number = {2}, 
pages = {41-60}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.2.41},
url = {http://jsdp.rcisp.ac.ir/article-1-564-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-564-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Torkian, Amin and Moallem, Paym},  
title = {Multi-frame Super Resolution for Improving Vehicle Licence Plate Recognition}, 
abstract ={License plate recognition (LPR) by digital image processing, which is widely used in traffic monitor and control, is one of the most important goals in Intelligent Transportation System (ITS). In real ITS, the resolution of input images are not very high since technology challenges and cost of high resolution cameras. However, when the license plate image is taken at low resolution, the license plate cannot be readable; hence, the recognition algorithm could not work well. There are many reasons resulting in the degradation of captured license plate images, such as downsampling, blurring, warping, noising, and distance of car from camera. Many researchers try to enhance the quality of input images by image restoration algorithms to improve the LPR final accuracy. Recently, super-resolution (SR) techniques are widely used to construct a high-resolution (HR) image from several observed low-resolution (LR) images, thereby removing the degradations caused by the imaging of a low resolution camera. As mentioned, in real ITS, the resolution of input image is not high, but there are successive frames from a target, therefore multi-frame SR methods can be used to overcome the ITS resolution challenges. In this paper, an SR technique based on POCS (Projection onto Convex Sets) is used to reconstruct an HR license plate image from a set of registered LR images. The normalized convolution (NC) framework is used in POCS, in which the local signal is approximated through a projection onto a subspace. However, the window function of adaptive NC is adapted to local linear structures. This results in more samples of the same modality being fused for the reconstruction, which in turn reduces diffusion across discontinuities, that is very important factor in improving LPR accuracy. The first step in multi-frame SR is image registration which is necessary to improve quality of the reconstructed HR image, especially in LPR when the quality of the reconstructed edges of characters is very important. For simplicity, it is often supposed simple motions (usually translation) between successive frames in multi-frame SR, but changes in scale, rotation and translation in license plate successive images may happened. It means that the registration is one of the main challenges in SR used for LPR. This paper proposes use of a two-step image matching algorithm to improve the quality of registration stage. In the first step, Fourier-Mellin image matching is used for registration which overcomes the scale and rotation challenge, but the accuracy of registration is not suitable. After matching of the successive input images by Fourier-Mellin algorithm, the Keren or Vandewalle image matching is used to improve the quality of final registration. For real LR images, Fourier-Mellin plus Keren shows higher performance while for simulated LR images, Fourier-Mellin plus Vandewalle shows higher performance. In order to compare the results of two proposed SR algorithms for LPR application with the other methods, we prepare three real datasets of successive frames for Persian LPR, the first and the second one are captured HR and LR successive frames, respectively, while the third one is a downsampled LR version of HR frames. The output HR image of all compared methods is feed to a demo version of a Persian LPR software (www.farsiocr.ir), and the accuracy of each character and the accuracy each license are reported. Five SR methods are compared including: cubic interpolation, ASDS-AR (Adaptive Sparse Domain Selection and Adaptive Regularization), standard POCS, our first and second proposed SR method which both of them firstly use Fourier-Mellin registration, while the first one uses Keren, and the second one uses Vandewalle image matching for a fine registration. Moreover, to present the effectiveness of using SR methods before LPR, the LR images are also directly feed to LPR software. The results represent when the length of license is less than 50 pixels, using SR methods before LPR improves the recognition accuracy. Moreover, when the license plate length is less 35 pixels, SR methods could not improve the performances. Our investigations show that for LR downsampled images from HR ones, our proposed SR method with Fourier-Mellin plus Keren registration reaches to the highest performance, while for real LR images, which are captured by a low resolution camera, our proposed SR method with Fourier-Mellin plus Vandewalle registration reaches to the highest performance. On the other hand, since some Persian numerical characters, like 2 (2) and 3 (3) are very similar to each other, all of the compared methods may confuse between them in LPR step, therefore, the accuracy per license of all compared methods are not high. Among all previous compared methods, for LR images with length between 35 to 50 pixels, the standard PCOS shows the best results, while our proposed SR methods improve the accuracy per character around 25%, with respect to PCOS method.  },  
Keywords = {Super Resolution, Normalized Convolution, Images Registration, License Plate Recognition },
volume = {16},
Number = {2}, 
pages = {61-76}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.2.61},
url = {http://jsdp.rcisp.ac.ir/article-1-642-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-642-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {khatami, hosein and fadaei, hakime and faili, hesham},  
title = {A Hybrid Machine Translation System Based on a Monotone Decoder}, 
abstract ={In this paper, a hybrid Machine Translation (MT) system is proposed by combining the result of a rule-based machine translation (RBMT) system with a statistical approach. The RBMT uses a set of linguistic rules for translation, which leads to better translation results in terms of word ordering and syntactic structure. On the other hand, SMT works better in lexical choice. Therefore, in our system, an initial translation is generated using RBMT. Then the proper lexical for the resulted sentence is chosen by using a decoder algorithm which is inspired by SMT architecture. In the pure SMT approach, decoder is responsible for selecting proper final lexical during the translation procedure. Normally this method deals with lexical choice as well as reordering and required exponential order in time complexity. By fixing the word order in the output, a polynomial version of this method, named monotone decoding, is used in this paper. Monotone decoder algorithm selects the best lexical from a candidate list by maximizing the language model of resulted sentence. The candidate list is gathered from the outputs of both pure RBMT and pure SMT systems.  The experiments of proposed hybrid method on English-Persian language pair show significant improvements over both RBMT and SMT results. The results show that the proposed hybrid method gains an improvement of almost +5 units over RBMT and about one unit over SMT in BLEU score.  },  
Keywords = {Machine translation, hybrid architecture, monotone decoder, translation reordering, lexical choice},
volume = {16},
Number = {2}, 
pages = {77-90}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.2.77},
url = {http://jsdp.rcisp.ac.ir/article-1-662-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-662-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Merrikhi, Hanieh and Ebrahimnezhad, Hossei},  
title = {Synthesis of human facial expressions based on the distribution of elastic force applied by control points}, 
abstract ={Facial expressions play an essential role in delivering emotions. Thus facial expression synthesis gain interests in many fields such as computer vision and graphics. Facial actions are generated by contraction and relaxation of the muscles innervated by facial nerves. The combination of those muscle motions is numerous. therefore, facial expressions are often person specific. But in general, facial expressions can be divided into six groups: anger, disgust, fear, happiness, sadness, and surprise. Facial expression variations include both global facial feature motions (e.g. opening or closing of eyes or mouth) and local appearance deformations (e.g. facial wrinkles and furrows). Ghent and McDonald introduced the Facial Expression Shape model and Facial Expression Texture Model respectively for the synthesizing global and local changes. Zhang et al. published an elastic model to balance the local and global warping. Then, they added suitable illumination details to the warped face image with muscle-distribution-based model. The goal of facial expression synthesis is to create expressional face image of the subject with the availability of neutral face image of that subject. This paper proposes a new method for synthesis of human facial expressions, in which an elastic force is defined to simulate the displacement of facial points in various emotional expressions. The basis of this force is the presence of control points with specific coordinates and directions on the face image. In other words, each control point applies an elastic force into the points of the face and moves them in a certain direction. The force applied to each point is inversely proportional to the distance between that point and the control point. For several control points, the force applied to the points of the face is the result of the forces associated with all control points. To synthesize a specific expression, the location of the control points and parameters of the force are adjusted to achieve an expression face. Face detail is extracted with laplacian pyramid and added to the synthesized image. The proposed method was implemented on the KDEF and Cohn-Kanade (CK+) databases and the results were put on for comparison. Two happy and sad expressions were selected for synthesis. The proper location of the control points and elastic force parameters were determined on the neutral image of the target person based on the expressional images in the database. Then, the neutral image of the person was warped with the elastic forces. Facial expression details have been added with laplacian pyramid method to the warped image. Finally, the experimental results were compared with the photo-realistic and facial expression cloning methods which demonstrate the high visual quality and low computational complexity of the proposed method in synthesizing the face image.},  
Keywords = {Facial expression Synthesis, Face deformation, Face animation, Expression cloning},
volume = {16},
Number = {2}, 
pages = {91-104}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.2.91},
url = {http://jsdp.rcisp.ac.ir/article-1-726-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-726-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Pahlevanzadeh, Alireza and Niknafs, Aliakbar},  
title = {Improvement of density-based clustering algorithm using modifying the density definitions and input parameter}, 
abstract ={Clustering is one of the main tasks in data mining, which means grouping similar samples. In general, there is a wide variety of clustering algorithms. One of these categories is density-based clustering. Various algorithms have been proposed for this method; one of the most widely used algorithms called DBSCAN. DBSCAN can identify clusters of different shapes in the dataset and automatically identify the number of clusters. There are advantages and disadvantages in this algorithm. It is difficult to determine the input parameters of this algorithm by the user. Also, this algorithm is unable to detect clusters with different densities in the data set. ISB-DBSCAN algorithm is another example of density-based algorithms that eliminates the disadvantages of the DBSCAN algorithm. ISB-DBSCAN algorithm reduces the input parameters of DBSCAN algorithm and uses an input parameter k as the nearest neighbor's number. This method is also able to identify different density clusters, but according to the definition of the new core point, It is not able to identify some clusters in a different data set. This paper presents a method for improving ISB-DBSCAN algorithm. A proposed approach, such as ISB-DBSCAN, uses an input parameter k as the number of nearest neighbors and provides a new definition for core point. This method performs clustering in three steps, with the difference that, unlike ISB-DBSCAN algorithm, it can create a new cluster in the final stage. In the proposed method, a new criterion, such as the number of dataset dimensions used to detect noise in the used data set. Since the determination of the k parameter in the proposed method may be difficult for the user, a new method with genetic algorithm is also proposed for the automatic estimation of the k parameter. To evaluate the proposed methods, tests were carried out on 11 standard data sets and the accuracy of clustering in the methods was evaluated. The results showe that the proposed method is able to achieve better results in different data sets compare to other available methods. In the proposed method, the automatic determination of k parameter also obtained acceptable results.},  
Keywords = {Density-based clustering, neighborhood parameter, clustering with different density},
volume = {16},
Number = {2}, 
pages = {105-120}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.2.105},
url = {http://jsdp.rcisp.ac.ir/article-1-760-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-760-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Ghazi-Maghrebi, saeed and khordadpoor, arbay},  
title = {Using WPT as a New Method Instead of FFT for  ‌Improving the Performance of OFDM Modulation}, 
abstract ={Orthogonal frequency division multiplexing (OFDM) is used in order to provide immunity against very hostile multipath channels in many modern communication systems.. The OFDM technique divides the total available frequency bandwidth into several narrow bands. In conventional OFDM, FFT algorithm is used to provide orthogonal subcarriers. Intersymbol interference (ISI) and intercarrier interference (ICI) impairements are caused by time domain rectangular windowed sine and cosine basis functions. FFT-OFDM is a very popular multi–carrier modulation (MCM) technique. It has some interesting features such as low complex modulation/demodulation implementation, simple and fast frequency domain channel estimation/ equalization. Also, by transmitting data over different parallel frequencies, FFT-OFDM has spectrum efficiency due to overlapped sub-channels and immunity against fading channels. Unfortunately, FFT-OFDM has serious drawbacks i.e. high sensitivity to ISI and ICI which caused by time domain rectangular windowed sine and cosine basis functions and their high level side lobes in frequency domain. For this purpose, cyclic prefixes (CP) are added at the beginning of the OFDM symbols and this causes bandwidth and power inefficiencies. In order to provide more efficient MCM technique, besides preserving the advantages of conventional FFT-OFDM, discrete wavelet modulation (DWM) and wavelet packet modulation (WPM) have been introduced in recent years. Therefore, it is possible to use time domain equalization (TEQ) or overlap frequency domain equalization (overlap FEQ) to reduce the interferences effectively in the absence of CP. Although TEQ techniques are more complicate than FEQ in conventional OFDM, WPT-OFDM has bandwidth and power enhanced efficiencies and this makes it so appropriate for digital communication systems. In recent years, several studies have been done on the wavelet theory, wavelet and WPM modulation in comparison with FFT-OFDM. Because of the good performance of WPT, a number of studies are still on the performance of WPT in hostile channels with more details. Also, there are a number of studies about various kinds of FEQ and TEQ such as zero force (ZF) and minimum mean square error (MMSE) in the peresence of AWGN and some fading channels. These researches also contain the comparison of FEQ for FFT-OFDM and overlap FEQ for WPT-OFDM. Todays, 3GPP standard is spread in different domains like 3G, 4G and LTE-A technologhies. In this paper, all the parameters are chosen according to 3GPP standards. For demonstrating the benefits of discrete WPT, two OFDM modulation schemes, i.e. FFT-OFDM and WPT-OFDM with two applied channels i.e. 6-tap rural area (RA6) and 6-tap typical urban (TU6) channels are considered. The performance of  two systems are investigated by the measure of bit error rate (BER) in different SNRs(dB). Also, Wavelet families i.e. Haar, Daubechies6 , Symlet5 and Coiflet5 are compared with FFT in OFDM system with QPSK, 16-QAM and 64-QAM constellation mappings. In the receiver side, FEQ is used in FFT-OFDM and overlap FEQ is used in WPT-OFDM to equalize multipath fading channels. This is a comprehensive comparison between FFT-OFDM and WPT-OFDM with different constellations, a number of wavelet families, different equalizer with two applied channels in order to implement a real environment. The simulation results demonstrate performance improvement of the system using WPT-OFDM scheme. In order to evaluate the performance of these two OFDM techniques, the required SNRs for reaching BER =10-3 are extracted and compared for both systems. It was observed that one can obtain better performance by using Haar wavelets as orthogonal basis function rather than FFT in OFDM modulation.  We achieved better performance by using Haar wavelets rather than FFT in OFDM modulation. As a result, WPT-OFDM can be applied , with better performance, in different OFDM-based applied technologhies such as DAB( Digital Audio Broadcast), WiMAX( worldwide Interoperability for Microwave Access), DVB( Digital Video Broadcast).  },  
Keywords = {Multicarrier modulation, Fast Fourier Transform, Wavelet Packet Transform, 3GPP standard},
volume = {16},
Number = {2}, 
pages = {121-136}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.2.121},
url = {http://jsdp.rcisp.ac.ir/article-1-657-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-657-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Hosseini, Fatemeh and Mirzarezaee, Mitra and Sharifi, Arash},  
title = {Malware Detection using Classification of Variable-Length Sequences}, 
abstract ={In this paper, a novel method based on the graph is proposed to classify the sequence of variable length as feature extraction. The proposed method overcomes the problems of the traditional graph with variable length of data, without fixing length of sequences, by determining the most frequent instructions and insertion the rest of instructions on the set of “other”, save speed and memory. According to features and the similarities of them, a score is given to each sample and that is used for classification. To improve the results, the method is not used alone, but in the two approaches, this method is combined with other existing Technique to get better results. In the first approach, which can be considered as a feature extraction, extracted features from scoring techniques (Hidden Markov Model, simple substitution distance and similarity graph) on op-code sequences, hexadecimal sequences and system calls are combined at classifier input. The second approach consists of two steps, in the first step; the scores which obtained from each of the scoring Technique are given to the three support vector machine. The outcomes are combined according to the weight of each Technique and the final decision is taken based on the majority vote. Among the components of the support vector machine, when given a higher weight in the similarity graph method (the proposed method), the result is better, Because the similarity graph method is more accurate than the other two methods. Then, in the second section, considering the strengths and benefits of each classifier, classifier outputs are combined and the majority voting is used. Three methods have been tested for group combinations, including Ensemble Averaging, Bagging, and Boosting. Ensemble Averaging consisting of the combination of four classifiers of random forests, a support vector machine (as obtained in the previous section), K nearest neighbors and naive Bayes, and the final decision is taken based on the majority vote; therefore, it is used as the proposed method. The proposed approach could detect metamorphic malware from Vxheaven set and also determines categories of malware with accuracy of 97%, while the SSD and HMM methods under the same conditions could detect malware with an accuracy of 84% and 80% respectively.  },  
Keywords = {Malware Detection, Graph Techniques, Combining Classifiers, Variable Length Classification, Support vector machine},
volume = {16},
Number = {2}, 
pages = {137-146}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.2.137},
url = {http://jsdp.rcisp.ac.ir/article-1-666-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-666-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Khodadadi, Elnaz and Hosseini, Rahil and Mazinani, Mahdi},  
title = {Soft Computing Methods based on Fuzzy, Evolutionary and Swarm Intelligence for Analysis of Digital Mammography Images for Diagnosis of Breast Tumors}, 
abstract ={Soft computing models based on intelligent fuzzy systems have the capability of managing uncertainty in the image based practices of disease. Analysis of the breast tumors and their classification is critical for early diagnosis of breast cancer as a common cancer with a high mortality rate between women all around the world. Soft computing models based on fuzzy and evolutionary algorithms play an important role in advances obtained in computer aided detection (CAD) systems. Combination of the evolutionary nature of swarm intelligence algorithms in optimization along with the potential of fuzzy models to cope with uncertainty and complex environments. In this research, a fuzzy inference model has been proposed for managing uncertainty in input data. The main uncertainty issues for classification of the breast tumors were modeled through the linguistic terms, fuzzy variables and fuzzy reasoning processes in the fuzzy inference model. Fuzzy linguist terms and rule sets are valuable to have an intelligent model with the ability to interact with the clinicians. Furthermore, hybrid fuzzy-evolutionary models have been proposed for tuning fuzzy membership functions for diagnosis of malignant and benign breast tumors. The hybrid proposed evolutionary methods are: 1) Fuzzy-Genetic, 2) Fuzzy-Particle swarm intelligence, and 3) Fuzzy-biogeography models. Evolutionary nature inspired combination with the fuzzy inference model (FIM) improves the proficiency of the FIM by adaption to the environment through the tuning process using training and testing datasets. To achieve this, the Genetic Algorithm was applied as a base evolutionary method. Then, the potential of the Particle Swart intelligence algorithm in using local and global experiences of the solutions in the search space. Also, bio-geographical aspects of species in finding an optimum solution lands with the high suitability habitat index has been concentrated in optimization process of the FIM. Evolutionary algorithms perform tuning of the fuzzy membership functions to improve the accuracy of the fuzzy inference model while simplicity and interpretability of the FIM was kept. For performance evaluation, an ROC curve analysis was conducted which is a robust and reliable technique that represents the trades of between classification model benefits and costs. Also, for validation purpose, a 10-fold cross-validation technique was performed for partitioning the dataset into training and testing sets in the evolutionary optimization algorithms. The performance of the proposed methods were evaluated using a dataset including 295 images and extracted features from mammographic image analysis society (MIAS) dataset. The results reveal that the hybrid Fuzzy-biogeography model outperforms the other evolutionary models with an accuracy and area under the ROC curve (AUC) of 95.25%, and 91.43%, respectively. Performance comparison of the hybrid evolutionary models in this study with the related methods for classification of the breast tumors on the MIAS dataset reveals that the fuzzy-biogeography model outperforms the other methods in terms of trades-off between accuracy and interpretability with an area under the ROC curve of 95.25% with four extracted features. The Fuzzy-GA and Fuzzy-Swarm Intelligence models are competitive with the best results of counterpart methods with an accuracy of 93.9% and 94.58% in terms of the AUC, respectively. The proposed fuzzy-evolutionary models in this study are promising for diagnosis of the breast tumors in early stages of the disease and providing suitable treatment.  },  
Keywords = {Fuzzy Inference System, Soft Computing, Hybrid Evolutionary Algorithms, Breast Tumours},
volume = {16},
Number = {2}, 
pages = {147-165}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.2.147},
url = {http://jsdp.rcisp.ac.ir/article-1-687-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-687-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Zahedi, Siawash and Yousefi, Saleh and Solouk, Vahi},  
title = {Design and Evaluation of a Method for Partitioning and Offloading Web-based Applications in Mobile Systems with Bandwidth Constraints}, 
abstract ={Computation offloading is known to be among the effective solutions of running heavy applications on smart mobile devices. However, irregular changes of a mobile data rate have direct impacts on code partitioning when offloading is in progress. It is believed that once a rate-adaptive partitioning performed, the replication of such substantial processes due to bandwidth fluctuation can be avoided. Currently, a wide range of mobile applications are based on web services, which in turn influences the process of offloading and partitioning. As a result, mobile users are prone to face difficulties in data communications due to cost of preferences or connection quality. Taking into account the fluctuations of mobile connection bandwidth and thereby data rate constraints, the current paper proposes a method of adaptive partitioning and computation offloading in three forms. Accordingly, an optimization problem is primarily formulated to each of three main objectives under the investigation. These objectives include run time, energy consumption and the weighted composition of run time and energy consumption. Next, taking into consideration the time complexity of the optimization problems, a heuristic partitioning method based on Genetic Algorithm (GABP) is proposed to solve each of the three objectives and with the capability of acceptable performance maintenance in both dynamic and static partitionings. In order to evaluate and analyze the performance of the proposed approach, a simulation framework was built to run for random graphs of different sizes with the capability of setting specific bandwidth limits as target. The simulation results evidence improved performance against bandwidth fluctuations when compared to similar approaches. Moreover, it was also seen that once the problem circumstances are modified, the offloading can take place in the vicinity of the target node. Furthermore, we implemented the proposed method in form of an application on Android platform to conduct experiments on real applications. The experiments prove that those partitions of the applications requiring higher processing reqources rather than data rate are the best candidates for offloading.  },  
Keywords = {Computation offloading, partitioning, bandwidth adaptation, web service, data rate limitation},
volume = {16},
Number = {3}, 
pages = {22-3}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.3.22},
url = {http://jsdp.rcisp.ac.ir/article-1-819-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-819-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {sadeghzadeh, mohammadbagher and razzazi, mohammadreza and ghayoomi, Masoo},  
title = {Studying impressive parameters on the performance of Persian probabilistic context free grammar parser}, 
abstract ={In linguistics, a tree bank is a parsed text corpus that annotates syntactic or semantic sentence structure. The exploitation of tree bank data has been important ever since the first large-scale tree bank, The Penn Treebank, was published. However, although originating in computational linguistics, the value of tree bank is becoming more widely appreciated in linguistics research as a whole. For example, annotated tree bank data has been crucial in syntactic research to test linguistic theories of sentence structure against large quantities of naturally occurring examples. The natural language parser consists of two basic parts, POS tagger and the syntax parser. A Part-Of-Speech Tagger (POS Tagger) is a piece of software that reads text in some languages and assigns parts of speech to each word (and other token), such as noun, verb, adjective, etc., although generally computational applications use more fine-grained POS tags like 'noun-plural'. A natural language parser is a program that works out the grammatical structure of sentences, for instance, which groups of words go together (as "phrases") and which words are the subject or object of a verb. Probabilistic parsers use knowledge of language gained from hand-parsed sentences to try to produce the most likely analysis of new sentences. These statistical parsers still make some mistakes, but commonly work rather well. Inaccurate design of context-free grammars and using bad structures such as Chomsky normal form can reduce accuracy of probabilistic context-free grammar parser. Weak independence assumption is one of the problems related to CFG. We have tried to improve this problem with parent and child annotation, which copies the label of a parent node onto the labels of its children, and it can improve the performance of a PCFG. In grammar, a conjunction (conj) is a part of speech that connects words, phrases, or clauses that are called the conjuncts of the conjunctions. In this study, we examined the conjunction phrases in the Persian tree bank. The results of this study show that adding structural dependencies to grammars and modifying the basic rules can remove conjunction ambiguity and increase accuracy of probabilistic context-free grammar parser. When a part-of-speech (PoS) tagger assigns word class labels to tokens, it has to select from a set of possible labels whose size usually ranges from fifty to several hundred labels depending on the language. In this study, we have investigated the effect of fine and coarse grain POS tags and merging non-terminals on Persian PCFG parser.},  
Keywords = {Probabilistic context free grammar, parser, tree bank, conjunction phrases, parent annotation, child annotation, part of speech tags},
volume = {16},
Number = {3}, 
pages = {36-23}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.3.36},
url = {http://jsdp.rcisp.ac.ir/article-1-385-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-385-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {hosseini, mohammad mehdi and zahedi, Morteza and Hassanpour, hami},  
title = {A New Statistical Model for Evaluation Interactive Question Answering Systems Using Regression}, 
abstract ={The development of computer systems and extensive use of information technology in the everyday life of people have just made it more and more important for them to make quick access to information that has received great importance. Increasing the volume of information makes it difficult to manage or control. Thus, some instruments need to be provided to use this information. The QA system is an automated system for obtaining the correct answers to questions posed by the human in the natural language. In these systems, if the response is found, and if it is not the user's expected response or if it needs more information, there is no possibility of exchanging information between the system and the user to ask more questions and get answers related to it. To solve this problem, interactive Question answering (IQA) systems were created. Interactive question answering (IQA) systems are associated with linguistic ambiguous structures, so these systems are more accurate than QA systems. Regarding the probability of ambiguity (ambiguity in the user question or ambiguity in the answer provided by the system), the repetition is possible in these systems to obtain the clarity. No standard methods have been developed on IQA systems evaluation, and the existing evaluation methods have been developed based on the methods used in QA and dialogue systems. In evaluating IQA systems, in addition to quantitative evaluation, a qualitative evaluation is used. It requires users’ participation in the evaluation process to determine the success level of interaction between the system and the user. Evaluation plays an important role in the IQA systems. In the context of evaluating IQA systems, there is partially no specific methodology for evaluating these systems in general. The main problem with designing an assessment method for IQA systems lies in the rare possibility to predict the interaction part. To this end, human needs to be involved in the evaluation process. In this paper, an appropriate model is presented by introducing a set of built-in features for evaluating IQA systems. To conduct the evaluation process, four IQA systems were considered based on the conversation exchanged between users and systems. Moreover, 540 samples were considered as suitable data to create a test and training set. The statistical characteristics of each conversation were extracted after performing the preprocessing on them. Then a feature matrix was formed based on the obtained characteristics. Finally, using linear and nonlinear regression, human thinking was predicted. As a result, the nonlinear power regression with 0.13 Root Mean Square Error (RMSE) was the best model.},  
Keywords = {Evaluation, Interactive Question Answering Systems, Nonlinear Regression, Feature Extraction},
volume = {16},
Number = {3}, 
pages = {48-37}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.3.48},
url = {http://jsdp.rcisp.ac.ir/article-1-814-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-814-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {BaradaranHemmati, Navid and Tabibzadeh, Omi},  
title = {An annotation scheme for Persian based on Autonomous Phrases Theory and Universal Dependencies}, 
abstract ={A treebank is a corpus with linguistic annotations above the level of the parts of speech. During the first half of the present decade, three treebanks have been developed for Persian either originally or subsequently based on dependency grammar: Persian Treebank (PerTreeBank), Persian Syntactic Dependency Treebank, and Uppsala Persian Dependency Treebank (UPDT). The syntactic analysis of a sentence in these corpora involves a series of relations introducing each word in the sentence as a dependent of another, referred to as the head. Examination of head-dependent pairs extracted from similar contexts in the above treebanks reveals frequent, apparently systematic inconsistencies observed particularly in the cases of nominal and adjectival heads. This can be explained in terms of the failure to postulate valency structures for nouns and adjectives as well as for verbs, taking for granted that tokens receive the proper labels regardless of such an assumption. When the notion of valency was borrowed from chemistry to refer to the number of controlled arguments, it was meant to apply only to verbs. Later developments of dependency grammar included the proposal of nominal and adjectival valency as well. The significance of the idea seems to have been underestimated, though. It has been highly improbable, therefore, for developers of dependency treebanks to design their annotation schemes otherwise. As far as Persian is concerned, Uppsala Persian Dependency Treebank and Dependency Persian Treebank (DepPerTreeBank, the dependency version of PerTreeBank) have used the Stanford Typed Dependencies. The later version of the former treebank, Persian Universal Dependency Treebank, has used the Universal Dependencies. These are standard annotation schemes that do not recognize valency for nouns and adjectives. Furthermore, Persian Syntactic Dependency Treebank has used its own set of dependency relations, where little attention has been paid to the idea. This paper reported the design process of a scheme for annotation of Persian dependency structure as part of an ongoing project of developing a dependency treebank for Persian. The scheme was based on a comprehensive description of Persian syntax according to a theory introduced as the Autonomous Phrases Theory. The main idea is that the significance of phrases should be appreciated in dependency analyses due to their cognitive reality, and the notion of valency is also extended beyond verbs, on which basis every dependent of whatever head type is classified as either a complement or an adjunct. Moreover, to make the resulting annotation scheme reasonably intelligible to the target audience, the latest standard available annotation scheme, Universal Dependencies (UD), was adapted to suit the requirements of the adopted framework. The outcome was a tag set of fifty-three dependency relations, including fifteen original labels and the rest borrowed from the universal dependencies. Although it provides more detailed annotation than UD does by making finer distinctions, our scheme does not involve too many tags more than UD does, mainly because a large number of the additional relations are shared by two or three head types.  },  
Keywords = {annotation, Persian, treebank, Universal Dependencies, valency},
volume = {16},
Number = {3}, 
pages = {60-49}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.3.60},
url = {http://jsdp.rcisp.ac.ir/article-1-538-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-538-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {karimizarchi, faeze and derhami, vali and Latif, Alimohammad and ebrahimi, ali},  
title = {Fire detection using video sequences in urban out-door environment}, 
abstract ={Nowadays automated early warning systems are essential in human life. One of these systems is fire detection which plays an important role in surveillance and security systems because the fire can spread quickly and cause great damage to an area. Traditional fire detection methods usually are based on smoke and temperature detectors (sensors). These methods cannot work properly in large space and out-door environments. They have high false alarm rates, and to cover the entire area, many smoke or temperature fire detectors are required, that is expensive. Due to the rapid developments in CCTV (Closed Circuit Television) surveillance system in recent years and video processing techniques, there is a big trend to replace conventional fire detection techniques with computer vision-based systems. This new technology can provide more reliable information and can be more cost-effective. The main objective of fire detection systems is high detection accuracy, low error rate and reasonable time detect. The video fire detection technology uses CCD cameras to capture images of the observed scene, which provides abundant and intuitive information for fire detection using image processing algorithms. This paper presents an efficient fire detection system which detects fire areas by analyzing the videos that are acquired by surveillance cameras in urban out-door environment, especially in storage of Yazd Gas Company. Proposed method uses color, spatial and temporal information that makes a good distinction between the fire and objects which are similar to the fire.  The purpose is achieved using multi- filter. The first filter separates red color area as a primary fire candidate. The second filter operates based on the difference between fire candidate areas in the sequence of frames. In the last filter, variation of red channel in the candidate area is computed and compared with the threshold which is updating continuously. In the experiments, the performance of these filters are evaluated separately. The proposed final system is a combination of all filters. Experimental results show that the precision of the final proposed system in urban out-door environment is 100%, and our technique achieves the average detection rate of 87.35% which outperforms other base methods. },  
Keywords = {Fire Detection, Video Sequences, Image Processing, Detection Time},
volume = {16},
Number = {3}, 
pages = {78-61}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.3.78},
url = {http://jsdp.rcisp.ac.ir/article-1-605-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-605-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Baradaran, Razieh and Golpar-Raboki, Effat},  
title = {Feature Extraction and Efficiency Comparison Using Dimension Reduction Methods in Sentiment Analysis Context}, 
abstract ={Nowadays, users can share their ideas and opinions with widespread access to the Internet and especially social networks. On the other hand, the analysis of people's feelings and ideas can play a significant role in the decision making of organizations and producers. Hence, sentiment analysis or opinion mining is an important field in natural language processing. One of the most common ways to solve such problems is machine learning methods, which creates a model for mapping features to the desired output. One challenge of using machine learning methods in NLP fields is feature selection and extraction among a large number of early features to achieve models with high accuracy. In fact, the high number of features not only cause computational and temporal problems but also have undesirable effects on model accuracy. Studies show that different methods have been used for feature extraction or selection. Some of these methods are based on selecting important features from feature sets such as Principal Component Analysis (PCA) based methods. Some other methods map original features to new ones with less dimensions but with the same semantic relations like neural networks. For example, sparse feature vectors can be converted to dense embedding vectors using neural network-based methods. Some others use feature set clustering methods and extract less dimension features set like NMF based methods. In this paper, we compare the performance of three methods from these different classes in different dataset sizes. In this study, we use two compression methods using Singular Value Decomposition (SVD) that is based on selecting more important attributes and non-Negative Matrix Factorization (NMF) that is based on clustering early features and one Auto-Encoder based method which convert early features to new feature set with the same semantic relations. We compare these methods performance in extracting more effective and fewer features on sentiment analysis task in the Persian dataset. Also, the impact of the compression level and dataset size on the accuracy of the model has been evaluated. Studies show that compression not only reduces computational and time costs but can also increase the accuracy of the model. For experimental analysis, we use the Sentipers dataset that contains more than 19000 samples of user opinions about digital products and sample representation is done with bag-of-words vectors. The size of bag-of-words vectors or feature vectors is very large because it is the same as vocabulary size. We set up our experiment with 4 sub-datasets with different sizes and show the effect of different compression performance on various compression levels (feature count) based on the size of dataset size.  According to experiment results of classification with SVM, feature compression using the neural network from 7700 to 2000 features not only increases the speed of processing and reduces storage costs but also increases the accuracy of the model from 77.05% to 77.85% in the largest dataset contains about 19000 samples. Also in the small dataset, the SVD approach can generate better results and by 2000 features from 7700 original features can obtain 63.92 % accuracy compared to 63.57 % early accuracy. Furthermore, the results indicate that compression based on neural network in large dataset with low dimension feature sets is much better than other approaches, so that with only 100 features extracted by neural network-based auto-encoder, the system achieves acceptable 74.46% accuracy against SVD accuracy 67.15% and NMF accuracy 64.09% and the base model accuracy 77.05% with 7700 features.  },  
Keywords = {Natural Language Processing, Sentiment Analysis, Opinion Mining, Auto-Encoder, Singular Value Decomposition, Nonnegative Matrix Factorization},
volume = {16},
Number = {3}, 
pages = {88-79}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.3.88},
url = {http://jsdp.rcisp.ac.ir/article-1-698-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-698-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Rahmanian, Shahabuddin and Bateni, Mohammad Hossein and Fardad, Mohammad and Najafi, Majdeddi},  
title = {Fixed-point FPGA Implementation of a Kalman Filter for Range and Velocity Estimation of Moving Targets}, 
abstract ={Tracking filters are extensively used within object tracking systems in order to provide consecutive smooth estimations of position and velocity of the object with minimum error. Namely, Kalman filter and its numerous variants are widely known as simple yet effective linear tracking filters in many diverse applications. In this paper, an effective method is proposed for designing and implementation of a Kalman filter in an object tracking application. The considered tracking application implies the capability to produce a smooth and reliable output stream by the tracking filter, even in presence of different disturbing types of noise, including background or spontaneous noises, as well as disturbances with continues or discrete nature. The presented method includes a fixed-point implementation of the Kalman filter on FPGA, which targets the joint estimation of position-velocity pair of an intended object in heavy presence of noise. The execution speed of the Kalman algorithm is drastically enhanced in the proposed implementation. This enhancement is attained by emphasis on hardware implementation of every single computational block on the one hand, and    through appropriate parallelization and pipelining of independent tasks within the Kalman process on the other hand. After designing the filter parameters with respect to the requirements of a given tracking problem, a floating-point model and a fixed-point hardware model of the filter are implemented using MATLAB and Xilinx System Generator, respectively.   In order to evaluate the performance of the filter under realistic circumstances, a set of appropriately defined scenarios are carried out. The simulations are carefully designed in order to represent the extremely harsh scenarios in which the input measurements to the filter are deeply polluted by different kinds of noises. In each simulation the position-velocity data corresponding to a moving object is generated according to an appropriate model, quantized, and contaminated by noise and fed into the filter. Performances of the Kalman filter in software version (i.e. the floating point replica) and hardware version (i.e. the fixed-point replica) are quantitatively compared in the designed scenario. Our comparison employs NMSE and maximum error values as quantitative measures, verifying the competency of our proposed fixed-point hardware implementation. The results of our work show that, with adequate selection word length, the implemented filter is fast and efficient; it confines the algorithm execution time to 50 clock pulses, i.e. about 0.4 µs when a 125 MHz clock is used. It is also verified that our implementation reduces the position and velocity estimation errors by 11 dB and 1.2 dB, respectively. The implemented filter also confines the absolute values of maximum error in position and velocity to 10 meter and 0.7 meter/sec. in the considered scenario, which is almost resembles the performance of its floating point counterpart. The presented Kalman filter is finally implemented on Zc706 evaluation board and the amount of utilized hardware resource (FFs, LUTs, DSP48, etc.) are reported as well as the estimated power consumption of the implemented design. The paper is concluded through comparison of the proposed design with some recent works which confirms the efficacy of the presented implementation.},  
Keywords = {Kalman filter, FPGA implementation, Tracking, Distance estimation, Velocity estimation},
volume = {16},
Number = {3}, 
pages = {100-89}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.3.100},
url = {http://jsdp.rcisp.ac.ir/article-1-782-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-782-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Miri, Esmail and Razavi, Seyyed Mohammad and Mehrshad, Nasser},  
title = {Search Space Reduction for Farsi Printed Subwords Recognition by Position of the Points and Signs}, 
abstract ={In the field of the words recognition, three approaches of words isolation, the overall shape and combination of them are used. Most optical recognition methods recognize the word based on break the word into its letters and then recogniz them. This approach is faced some problems because of the letters isolation dificulties and its recognition accurcy in texts with a low image quality. Therefore, an approach based on none separating recognition could be useful in such cases. In methods based on the overall shapes for subword recognition after extraction of subword features usually these features are searched in the image dictionary created in the training phase. Therefore, by considering that we are faced with massive amounts of classes, proposing ways to limit the scope of the search are the main challenges in the overall shape methods. Thus, the information of the overall shape usually is used to reduce the scope search in a hierarchical form. In this paper, it is tried to reduce the search space of the subwords severely by using a simple and efficient method.  In training phase, training data is grouped based on the location of the points and signs, in the groups where have more than 10 subwords, to reduce the search space, according to the number of elements in the group, by extracting the simple features of horizontal and vertical profiles clustering takes place. In recognition phase, in the first step, by determining the width to height ratio of the subword (with signs and without signs) and the position code of the points and signs, the search scope is limited to subwords with this position code that are within the range of the ratios mentioned. This range would be accepted if the number of subwords in this phase is less than ten. Otherwise, in the next step, by extracting the simple features of the horizontal and vertical profiles of the subwords, the search space will be limited to a number of the closest clusters to this subword that also satisfies the width-to-height ratio. By using the proposed method of this paper, the search space has fallen to an acceptable level. In this study, a database of 12700 subwords with five Lotus, Zar, Nazanin, Mitra and Yaghut fonts scanned 400 dpi was used. The four Lotus, Zar, Nazanin and Mitra fonts were used in the training phase and in the test phase, Yaghut ​​font is used.},  
Keywords = {Recognition, Farsi Typed Subwords, Search Space Reduction, Position of the Points and Symbols},
volume = {16},
Number = {3}, 
pages = {116-101}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.3.116},
url = {http://jsdp.rcisp.ac.ir/article-1-803-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-803-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Dastgheib, M.B. and koleini, Sara and Fakhrahmad, S.M.},  
title = {Design and implementation of Persian spelling detection and correction system based on Semantic}, 
abstract ={Persian Language has a special feature (grapheme, homophone, and multi-shape clinging characters) in electronic devices. Furthermore, design and implementation of NLP tools for Persian are more challenging than other languages (e.g. English or German). Spelling tools are used widely for editing user texts like emails and text in editors.  Also developing Persian tools will provide Persian programs to check spell and reduce errors in electronic texts. In this work, we review the spelling detection and correction methods, especially for the Persian language. The proposed algorithm consists of two steps. The first step is non-word error detection and correction by intelligent scoring algorithm. The second step is read-word error detection and correction.  We propose a spelling system "Perspell” for Persian non-word and real-word errors using a hybrid scoring system and optimized language model by lexicon. This scoring system uses a combination of lexical and semantic features optimized by learning dataset. The weight of these features in scoring system is also optimized by learning phase. Perspell is compared with known Persian spellchecker systems and could overcome them in precision of detection and correction. Accordingly, the proposed Persian spell-checker system can also detect and correct real-word errors. This open challenge category of spelling is a complicated and time consuming task in Persian as well as, assessing the proposed method, the F-measure metric has improved significantly (about 10%) for detecting and correcting Persian words. In the proposed method, we used Persian language model with bootstrapping and smoothing to overcome data sparseness and lack of data. The bootstrapping is developed using a Persian dictionary and further we used word sense disambiguation to select the correct related replaced word.  },  
Keywords = {Spell Error Detection, Spell Error Correction, Persian spell Checker, NLP, Persian Language Model},
volume = {16},
Number = {3}, 
pages = {128-117}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.3.128},
url = {http://jsdp.rcisp.ac.ir/article-1-668-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-668-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Zandifar, Mozhdeh and Tahmoresnezhad, Jafar},  
title = {Sample-oriented Domain Adaptation for Image Classification}, 
abstract ={Image processing is a method to perform some operations on an image, in order to get an enhanced image or to extract some useful information from it. The conventional image processing algorithms cannot perform well in scenarios where the training images (source domain) that are used to learn the model have a different distribution with test images (target domain). Also, many real world applications suffer from a limited number of training labeled data and therefore benefit from the related available labeled datasets to train the model. In this way, since there is the distribution difference across the source and target domains (domain shift problem), the learned classifier on the training set might perform poorly on the test set. Transfer learning and domain adaptation are two outstanding solutions to tackle this challenge by employing available datasets, even with significant difference in distribution and properties, to transfer the knowledge from a related domain to the target domain. The main assumption in domain shift problem is that the marginal or the conditional distribution of the source and the target data is different. Distribution adaptation explicitly minimizes predefined distance measures to reduce the difference in the marginal distribution, conditional distribution, or both. In this paper, we address a challenging scenario in which the source and target domains are different in marginal distributions, and the target images have no labeled data. Most prior works have explored two following learning strategies independently for adapting domains: feature matching and instance reweighting. In the instance reweighting approach, samples in the source data are weighted individually so that the distribution of the weighted source data is aligned to that of the target data. Then, a classifier is trained on the weighted source data. This approach can effectively eliminate unrelated source samples to the target data, but it would reduce the number of samples in adapted source data, which results in an increase in generalization errors of the trained classifier. Conversely, the feature-transform approach creates a feature map such that distributions of both datasets are aligned while both datasets are well distributed in the transformed feature space. In this paper, we show that both strategies are important and inevitable when the domain difference is substantially large. Our proposed using sample-oriented Domain Adaptation for Image Classification (DAIC) aims to reduce the domain difference by jointly matching the features and reweighting the instances across images in a principled dimensionality reduction procedure, and construct new feature representation that is invariant to both the distribution difference and the irrelevant instances. We extend the nonlinear Bregman divergence to measure the difference in marginal, and integrate it with Fisher’s linear discriminant analysis (FLDA) to construct feature representation that is effective and robust for substantial distribution difference. DAIC benefits pseudo labels of target data in an iterative manner to converge the model. We consider three types of cross-domain image classification data, which are widely used to evaluate the visual domain adaptation algorithms: object (Office+Caltech- 256), face (PIE) and digit (USPS, MNIST). We use all three datasets prepared by and construct 34 cross-domain problems. The Office-Caltech-256 dataset is a benchmark dataset for cross-domain object recognition tasks, which contains 10 overlapping categories from following four domains: Amazon (A), Webcam (W), DSLR (D) and Caltech256 (C). Therefore 4 × 3 = 12 cross domain adaptation tasks are constructed, namely A → W, ..., C → D. USPS (U) and MNIST (M) datasets are widely used in computer vision and pattern recognition tasks. We conduct two handwriting recognition tasks, i.e., usps-mnist and mnist-usps. PIE is a benchmark dataset for face detection task and has 41,368 face images of size 3232 from 68 individuals. The images were taken by 13 synchronized cameras and 21 flashes, under varying poses, illuminations, and expressions. PIE dataset consists five subsets depending on the different poses as follows: PIE1 (C05, left pose), PIE2 (C07, upward pose), PIE3 (C09, downward pose), PIE4 (C27, frontal pose), PIE5 (C29, right pose). Thus, we can construct 20 cross domain problems, i.e., P1 → P2, P1 → P3, ..., P5 → P4. We compare our proposed DAIC with two baseline machine learning methods, i.e., NN, Fisher linear discriminant analysis (FLDA) and nine state-of-the-art domain adaptation methods for image classification problems (TSL, DAM, TJM, FIDOS and LRSR). Due to these methods are considered as dimensionality reduction approaches, we train a classifier on the labeled training data (e.g., NN classifier), and then apply it on test data to predict the labels of the unlabeled target data. DAIC efficiently preserves and utilizes the specific information among the samples from different domains. The obtained results indicate that DAIC outperforms several state of-the-art adaptation methods even if the distribution difference is substantially large.},  
Keywords = {Image processing, Transfer learning, Bregman divergence, Marginal distribution difference reduction, Dimensionality reduction},
volume = {16},
Number = {3}, 
pages = {148-129}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.3.148},
url = {http://jsdp.rcisp.ac.ir/article-1-847-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-847-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2019}  
}

@article{ 
author = {Gandomi, Mohammadreza and Hassanpour, Hami},  
title = {Feature Extraction to Identify Network Traffic with Considering Packet Loss Effects}, 
abstract ={There are huge petitions of network traffic coming from various applications on Internet. In dealing with this volume of network traffic, network management plays a crucial rule. Traffic classification is a basic technique which is used by Internet service providers (ISP) to manage network resources and to guarantee Internet security. In addition, growing bandwidth usage, at one hand, and limited physical capacity of communication lines, at the other hand, lead providers to improve utilization quality of network resources. In fact, classification or identification of network is a critical task in network processing for traffic management, anomaly detection, and also to improve network quality-of-service (QoS). Port and payload based methods are two classical techniques which are applicable under traditional network conditions. However, many Internet applications use dynamic port numbers for communications, which lead to difficulties in identifying traffic using port numbers. Also many applications encrypt the data before transmitting to avoid detection. Therefore, payload-based techniques are inefficient for these traffics. In recent years, statistical feature-based traffic flow identification methods (STFIM) have attracted the interest of many researchers. The most important part of a STFIM is the selection of efficient statistical features. Preliminary analysis shows that the problem of packet loss in data transmission is one of the major challenges in employing STFIM for network traffic identification. This affects the statistical characteristics of packets, such as the time interval between sending successive application packets, and in some cases significantly reduces the accuracy of traffic identification. The main goal of this paper is to examine the effects of packet loss on statistical features, and therefore the accuracy of identifying applications, as well as extracting appropriate features to overcome these effects. For this purpose, the behavior of four statistical features, including the packet size, the time interval between sending and receiving packets, the duration of the flows and the rate of sending packets, are investigated; then applications traffics are identified via considering characteristics of their distribution. We collected a database of network traffic flow from seven applications with different rates of packet loss. We used the extracted features in a multilayer neural network, as a classifier, to differentiate between different traffic applications. Experimental results show that the extracted features are robust against the packets loss, and the accuracy of the network traffic identification is close to the ideal state (traffic flow with no packet lost).  },  
Keywords = {Network Traffic, Network traffic Identification, Machine Learning, Packet Loss},
volume = {16},
Number = {4}, 
pages = {3-16}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.4.3},
url = {http://jsdp.rcisp.ac.ir/article-1-825-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-825-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2020}  
}

@article{ 
author = {Soleimany, Hadi and Mehrdad, Alireza and Sadeghi, Saeideh and Moazemi, Farokhlagh},  
title = {Novel Impossible Differential Cryptanalysis of Zorro Block Cipher}, 
abstract ={Impossible difference attack is a powerful tool for evaluating the security of block ciphers based on finding a differential characteristic with the probability of exactly zero. The linear layer diffusion rate of a cipher plays a fundamental role in the security of the algorithm against the impossible difference attack. In this paper, we show an efficient method, which is independent of the quality of the linear layer, can find impossible differential characteristics of Zorro block cipher. In other words, using the proposed method, we show that, independent of the linear layer feature and other internal elements of the algorithm, it is possible to achieve effective impossible differential characteristic for the 9-round Zorro algorithm. Also, based on represented 9-round impossible differential characteristic, we provide a key recovery attack on reduced 10-round Zorro algorithm. In this paper, we propose a robust and different method to find impossible difference characteristics for Zorro cipher, which is independent of the linear layer of the algorithm. The main observation in this method is that the number of possible differences in that which may occur in the middle of Zorro algorithm might be very limited. This is due to the different structure of Zorro. We show how this attribute can be used to construct impossible difference characteristics. Then, using the described method, we show that, independent of the features of the algorithm elements, it is possible to achieve efficient 9-round impossible differential characteristics of Zorro cipher. It is important to note that the best impossible differential characteristics of the AES encryption algorithm are only practicable for four rounds. So the best impossible differential characteristic of Zorro cipher is far more than the best characteristic of AES, while both algorithms use an equal linear layer. Also, the analysis presented in the article, in contrast to previous analyzes, can be applied to all ciphers with the same structure as Zorro, because our analysis is independent of the internal components of the algorithm. In particular, the method presented in this paper shows that for all Zorro modified versions, there are similarly impossible differential characteristics. Zorro cipher is a block cipher algorithm with 128-bit block size and 128-bit key size. Zorro consists of 6 different sections, each with 4 rounds (24 rounds in all). Zorro does not have any subkey production algorithm and the main key is simply added to the value of the beginning state of each section using the XOR operator. Internal rounds of one section do not use the key. Similar to AES, Zorro state matrix can be shown by a 4 × 4 matrix, which each of these 16 components represent one byte. One round of Zorro, consists of four functions, which are SB*, AC, SR, and MC, respectively. The SB* function is a nonlinear function applying only to the four bytes in the first row of the state matrix. Therefore, in the opposite of the AES, where the substitution box is applied to all bytes, the Zorro substitution box only applies to four bytes. The AC operator is to add a round constant. Finally, the two SR and MC transforms are applied to the state matrix, which is, respectively, the shift row and mixed column used in the AES standard algorithm. Since the analyzes presented in this article are independent of the substitution properties, we do not use the S-box definition used by Zorro. Our proposed model uses this Zorro property that the number of possible differences after limited rounds can be much less than the total number of possible differences. In this paper, we introduce features of the Zorro, which can provide a high bound for the number of possible values of an intermediate difference. We will then present a model for how to find Zorro impossible differential characteristics, based on the limitations of the intermediate differences and using the miss-in-the-middle attack. Finally, we show that based on the proposed method, it is possible to find an impossible differential characteristic for 9 rounds of algorithms with a Zorro-like structure and regardless of the linear layer properties. Also, it is possible to apply the key recovery attack on 10 rounds of the algorithm. So, regardless of the features of the used elements, it can be shown that this number of round of algorithms is not secure even by changing the linear layer.},  
Keywords = {block cipher, cryptanalysis, impossible difference attack, Zorro block cipher algorithm},
volume = {16},
Number = {4}, 
pages = {17-26}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.4.17},
url = {http://jsdp.rcisp.ac.ir/article-1-842-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-842-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2020}  
}

@article{ 
author = {Ejabati, Seyyed Masoud and Zahiri, Seyed Hami},  
title = {Optimization in Uncertain and Complex Dynamic Environments with Evolutionary Methods}, 
abstract ={In the real world, many of the optimization issues are dynamic, uncertain, and complex in which the objective function or constraints can be changed over time. Consequently, the optimum of these issues is changed nonlinearly. Therefore, the optimization algorithms not only should search the global optimum value in the space but also should follow the path of optimal change in dynamic environment. Accordingly, several researchers believe in the effectiveness of following a series of optimums compared to a global optimum. Therefore, when an environment is changed, following a global optimum in a series of best optimums is more efficient. Evolutionary algorithms (EA) were inspired by biological and natural evolution. Because of changing characteristic of nature, it can be a good option for dynamic optimization. In recent years, different methods have been proposed to improve EA of static environments. One of the most common methods is multi-population method. In this method, the whole space is divided into sub-spaces. Each sub-space covers some local optimums and represents a sub-population. The algorithm updates the particles of each sub-space and searches the best optimum. The most challenging issue of multi-population method is to create the desired number of sub-population and people to cover different sub-spaces in the search space. In the present study, in order to deal with the challenges, a new algorithm based on particle optimization algorithm, which is called decrement and increment particle optimization algorithm, was proposed. The algorithm is able to follow and find the number of time-varied optimum in an environment with invisible changes by increasing or decreasing the number of particles adaptively. Another challenging issue in dynamic optimization is the detection of environmental changes, due to the impossibility of this issue and failure of detection-based algorithms.  In the proposed method, there is no need to detect the environmental changes and it always adapts itself to the environment. Furthermore, the terms of focused search area were defined to emphasize on promising spaces to accelerate the local search process and prevent early convergence. The results of the proposed algorithm were evaluated on moving peaks and compared with several valid algorithms. The results showed the positive effect of decrement/increment mechanism of particles on finding and following time of many optimums compared to other multi-population based optimization algorithm.},  
Keywords = {Increase decrease particle, Dynamic optimization problems (DOPs), Multi-population approach, Particle swarm optimization},
volume = {16},
Number = {4}, 
pages = {27-44}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.4.27},
url = {http://jsdp.rcisp.ac.ir/article-1-812-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-812-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2020}  
}

@article{ 
author = {Eshaghpoor, Alireza and Salehi, Mostafa and Ranjbar, Vahi},  
title = {Providing a Link Prediction Model based on Structural and Homophily Similarity in Social Networks}, 
abstract ={In recent years, with the growing number of online social networks, these networks have become one of the best markets for advertising and commerce, so studying these networks is very important. Most online social networks are growing and changing with new communications (new edges). Forecasting new edges in online social networks can give us a better understanding of the growth of these networks. Link prediction has many important applications. These include predicting future social networking interactions, the ability to manage and design useful organizational communications, and predicting and preventing relationships in terrorist gangs. There have been many studies of link prediction in the field of engineering and humanities. Scientists attribute the existence of a new relationship between two individuals for two reasons: 1) Proximity to the graph (structure) 2) Similar properties of the two individuals (Homophile law). Based on the two approaches mentioned, many studies have been carried out and the researchers have presented different similarity metrics for each category. However, studying the impact of the two approaches working together to create new edges remains an open problem. Similarity metrics can also be divided into two categories; Neighborhood-based and path-based. Neighborhood-based metrics have the advantage that they do not need to access the whole graph to compute, whereas the whole graph must be available at the same time to calculate path-based metrics. So far, above the two theoretical approaches (proximity and homophile) have not been found together in the neighborhood-based metrics. In this paper, we first attempt to provide a solution to determine importance of the proximity to the graph and similar features in the connectivity of the graphs. Then obtained weights are assigned to both proximity and homophile. Then the best similarity metric in each approach are obtained. Finally, the selected metric of homophily similarity and structural similarity are combined with the obtained weights. The results of this study were evaluated on two datasets; Zanjan University Graduate School of Social Sciences and Pokec online Social Network. The first data set was collected for this study and then the questionnaires and data collection methods were filled out. Since this dataset is one of the few Iranian datasets that has been compiled with its users' specifications, it can be of great value. In this paper, we have been able to increase the accuracy of Neighborhood-based similarity metric by using two proximity in graph and homophily approaches.  },  
Keywords = {Link prediction, Homophily similarity, Network similarity, Social networks},
volume = {16},
Number = {4}, 
pages = {45-58}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.4.45},
url = {http://jsdp.rcisp.ac.ir/article-1-859-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-859-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2020}  
}

@article{ 
author = {Banitalebi-Dehkordi, Mehdi and Ebrahimi-moghadam, Abbas and Khademi, Morteza and Hadizadeh, Hadi},  
title = {Compressed-Sampling-Based Image Saliency Detection in the Wavelet Domain}, 
abstract ={When watching natural scenes, an overwhelming amount of information is delivered to the Human Visual System (HVS). The optic nerve is estimated to receive around 108 bits of information a second. This large amount of information can’t be processed right away through our neural system. Visual attention mechanism enables HVS to spend neural resources efficiently, only on the selected parts of the scene at order. This results in a better and faster perception of events. In order to perform saliency measurement on visual data, subjective eye-tracking experiments may be carried out. These experiments involve using devices to track eye movements of a number of subjects while they watch images or videos on a screen. That being said, such devices are not very suitable in practice due to hardship involved with carrying out experiments, such as need to have restricted test environment, being time consuming as well as expensive. Instead, researchers developed Computational Visual Attention Models (VAMs) in attempts to mimic the HVS saliency prediction process. Visual Attention Modelling has widely been used in various areas of image processing and understanding. Computational models of visual attention aim to predict the most interesting areas of an image to the observers. To this end, these models produce saliency maps, in which each pixel is assigned a likelihood value of being looked at. In other words, saliency maps highlight where the most likely for viewers  to look at in an image is. Knowing the Regions of Interests (ROIs) can be helpful in applications such as image and video compression, object recognition and detection, visual search, retargeting, retrieval, image matching, and segmentation. Saliency prediction is generally done in a bottom-up, top-down, or hybrid fashion. Bottom-up approaches exploit low-level attributes such as brightness, color, edges, texture, etc. Top-down approaches focus on context-dependent information from the scene such as appearance of humans, animals, text, etc. Hybrid methods combine the two streams. This paper proposes a new method of saliency prediction using sparse wavelet coefficients selected from low-level bottom-up saliency features. Wavelet based image methods are used widely in image processing algorithms as they are especially powerful in decomposing images into several scales of resolutions. In our method, first random compressive sampling is performed on wavelet coefficients in the Lab color space. Random sampling enables a reduction in computational complexity and provides a sparse representation of the coefficients. The number of decomposition levels is chosen based on the information diffusion property of the signal. In the proposed method, the sampling can be done at a rate different than the Nyquist rate, and based on the sparsity degree of the signal. It is shown that having the basis vectors of a sparse representation of the signal, can result in an accurate signal reconstruction. In this work, the sparsity degree and thus the sampling rate is computed empirically. Next, local and global saliency maps are generated from these random samples to account for small-scale and large-scale (scene-wide) saliency attributes. These maps are then combined to form an overall saliency map. The overall saliency map therefore includes both local, and global saliency attributes. The main contribution of this paper is the use of compressive sampling in creating a novel wavelet domain representation for image saliency prediction. Extensive performance evaluations show that the proposed method provides a promising saliency prediction performance while the computation complexity remains reasonable, thanks to the dimensionality reduction of compressive sampling. In particular, the proposed method demonstrated favorable precision, recall, and F-measure, when compared to state-of-the-art saliency detection methods, over large-scale datasets. We hope the proposed approach brings ideas to the saliency analysis research community.},  
Keywords = {Saliency map, visual attention, wavelet transform, sparsity, compressive sampling},
volume = {16},
Number = {4}, 
pages = {59-72}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.4.59},
url = {http://jsdp.rcisp.ac.ir/article-1-874-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-874-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2020}  
}

@article{ 
author = {Mozaffari, Reza and Mavaddati, Samir},  
title = {A Novel Image Denoising Method Based on Incoherent Dictionary Learning and Domain Adaptation Technique}, 
abstract ={In this paper, a new method for image denoising based on incoherent dictionary learning and domain transfer technique is proposed. The idea of using sparse representation concept is one of the most interesting areas for researchers. The goal of sparse coding is to approximately model the input data as a weighted linear combination of a small number of basis vectors. Two characteristics should be considered in the dictionary learning process: Atom-data coherence and mutual coherence between dictionary atoms. The first one determines the dependency between the dictionary atoms and training data frames. This criterion value should be high. Another parameter expresses the dependency between atoms defined as the maximum absolute value of the cross-correlations between them. Higher coherence to the data class and lower mutual coherence between atoms result in a small approximation error in sparse coding procedure. In the proposed dictionary learning process, a coherence criterion is employed to yield over complete dictionaries with the incoherent atoms. The purpose of learning dictionary with low mutual coherence value is to reduce the approximation error of sparse representation in the denoising process and also decrease the computing time. We utilize the least angle regression with coherence criterion (LARC) algorithm for sparse representation based on atom-data coherence in the first step of dictionary learning process. LARC sparse coding is an optimized generalization of the least angle regression algorithm with stopping condition based on a residual coherence. This approach is based on setting a variable cardinality value. Using atom-data coherence measure as stopping criteria in the sparse coding process yields the capability of balancing between source confusion and source distortion. A high value for the cardinality parameter or too dense coding results in the source confusion since the number of dictionary atoms is more than what is required for a proper representation. Source degradation occurs when the sparse coding is done with low cardinality parameter or too sparse coding. Therefore, the number of required atoms will not be enough and data cannot be coded exactly over these atoms. Therefore, the setting procedure of cardinality parameter must be performed precisely. The problem of finding a dictionary with low mutual coherence between its normalized atoms can be obtained by considering the Gram matrix. The mutual coherence is described by the maximum absolute value of the off-diagonal elements of this matrix. If all off-diagonal elements are the same, a dictionary with minimum self-coherence value is obtained. Also, we take advantage of domain adaptation technique to transfer a learned dictionary to an adapted dictionary in the denoising process. The initial atoms set randomly and are updated based on the selected patches of input noisy image using the proposed alternating optimization algorithm. According to these issues, the fitness function in dictionary learning problem includes three main sections: The first term is related to the minimization of approximation error. The next items are the incoherence criterion of dictionary atoms. The last one includes a transformation of initial atoms according to some patches of the noisy input data in the test step. We use limited-memory BFGS algorithm as an iterative solution for regular minimization of our objective function involved different terms. The simulation results show that the proposed method leads to significantly better results in comparison with the earlier methods in this context and the traditional procedures.},  
Keywords = {Image denoising, Dictionary learning, Coherence, Domain adaptation, Image processing},
volume = {16},
Number = {4}, 
pages = {73-92}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.4.73},
url = {http://jsdp.rcisp.ac.ir/article-1-823-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-823-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2020}  
}

@article{ 
author = {Momtazi, Saeedeh and Torabi, Farzaneh},  
title = {Named Entity Recognition in Persian Text  using Deep Learning}, 
abstract ={Named entities recognition is a fundamental task in the field of natural language processing. It is also known as a subset of information extraction. The process of recognizing named entities aims at finding proper nouns in the text and classifying them into predetermined classes such as names of people, organizations, and places. In this paper, we propose a named entity recognizer which benefits from neural network-based approaches for both word representation and entity tagging. In the word representation part of the proposed model, two different vector representations are used and compared: (1) the semantic representation of words based on their context using word2vec continues skip-gram model, and (2) the semantic representation of words based on their context as well as characters forming them using fasttext. While the former model captures the semantic concepts of words, the latter one considers the morphological similarity of words as well. For the entity identification, a deep Bidirectional Long Short Term Memory (BiLSTM) network is used. Using LSTM model helps to consider the history of text when predicting entities, while the BiLSTM model expands this idea by benefiting from the history from both sides of the context. Moreover, inline of the present research, an annotated corpus containing 3000 abstracts (90000 tokens) from the Persian Wikipedia is provided. In contrast to the available datasets in the field, which includes up to 7 label types, the new dataset contains 15 different labels, namely person individual, person group, organizations, locations, religions, books, magazines, movies, languages, nationalities, events, jobs, dates, fields, and other. Developing this dataset will be an important step in promoting future research in this field, especially for the tasks such as question answering that need wider range of entity types. The results of the proposed system show that by using the introduced model and the provided data, the system can achieve 72.92 F-measure.},  
Keywords = {Name entity recognition, natural language processing, word embedding, deep learning},
volume = {16},
Number = {4}, 
pages = {93-112}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.4.93},
url = {http://jsdp.rcisp.ac.ir/article-1-831-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-831-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2020}  
}

@article{ 
author = {Soltanymahboob, Amir and ZahiriMamaghani, Seyed Hami},  
title = {Role of Heuristic Methods with variable Lengths In ANFIS Networks Optimum Design and Training}, 
abstract ={ANFIS systems have been much considered due to their acceptable performance in terms of creation of fuzzy classifier and training. One main challenge in designing an ANFIS system is to achieve an efficient method with high accuracy and appropriate interpreting capability. Undoubtedly, type and location of membership functions and the way an ANFIS network is trained are of considerable effect on its performance. Up to present time, related researches have just found type and location of membership functions, and or suggested methods to train these networks. Main reason for lack of simultaneous determination of type and location of membership functions and training an ANFIS network is the length of standard versions of Heuristic methods being fixed. In this paper, a new version of optimization method of inclined planes will be introduced, primarily; while search factors could be variable. Then, achieved capability will be used for specifying type and location of membership functions and simultaneous training of a classifier based on adaptive neuro-fuzzy inference system (ANFIS). The proposed method on five benchmark datasets iris, Breast Cancer, Bupa Liver, Wine and Pima from the UCI database has been tested, which has different number of reference classes, different length of attribute vectors with appropriate complexity. Initially, the accuracy of the test dataset for each of the selected datasets was compared using the standard 10 folded cross validation method using the standardized version of the standard length.Then the same experiments were repeated by the proposed method and the results of applying the proposed method on the five aforementioned datasets were compared with the results of the heuristic methods with the standard length version. The comparative results show that the optimal and intelligent design of ANFIS classifier by variable length heuristics on five well-known datasets yields good and satisfactory results and in each of the five problems it has provided better answers than other design methods in the ANFIS classification system.},  
Keywords = {Pattern Recognition, Classifier, adaptive neuro fuzzy inference system, variable Length Inclined Planes System Optimization algorithm},
volume = {16},
Number = {4}, 
pages = {113-134}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.4.113},
url = {http://jsdp.rcisp.ac.ir/article-1-834-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-834-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2020}  
}

@article{ 
author = {sadeghi, Vahi},  
title = {Word segmentation in Persian continuous speech using F0 contour}, 
abstract ={Word segmentation in continuous speech is a complex cognitive process. Previous research on spoken word segmentation has revealed that in fixed-stress languages, listeners use acoustic cues to stress to de-segment speech into words. It has been further assumed that stress in non-final or non-initial position hinders the demarcative function of this prosodic factor. In Persian, stress is retracted to a non-final position in words containing enclitic affixes. The present research explores the question as to whether Persian listeners are able to identify word boundaries given the tonal structure of words in Persian phonology or not. The paper was also intended to investigate to what extent Persian native speakers use H peaks to identify word stress pattern. Two perceptual experiments were conducted in this regard. Given the tonal structure of words in utterance non-final position in Persian, it was hypothesized that listeners are likely to identify the end of a high plateau as a cue to word boundary. In addition, given that peaks in utterance non-final position are delayed, it was further hypothesized that perceived prominent is likely to be attributed to a syllable that precedes another syllable carrying a pitch peak. The basic stimulus for the first experiment was a nonsense sequence of nine “dA” syllables with equal duration ([dA1.dA2.dA3.dA4.dA5.dA6.dA7.dA8.dA9]) across the syllables. The peak was located at the beginning of the consonant in [dA4] in the stimulus. The duration of the H plateau following the H peak was varied continuously to create 6 different stimuli with varying temporal plateau. The stimuli were presented randomly to 10 native speakers of Persian. The participants were asked to chunk the sequence of identical syllables they hear into two parts as if they were two independent words. They were also asked to identify the most prominent syllable in a separate identification test. The results showed that the ending point of a high H plateau acts as a prosodic cue to word boundary detection in Persian. For example, when the end of the H plateau was located on the end of the vowel in dA4, listeners identified the end of dA4 as boundary between two hypothetical words. However, when the end of the plateau was located on the end of the vowel in dA5 or the beginning of the consonants in .dA6 listeners identified the end of dA5 as the word final boundary. The results of this experiment further revealed that listeners are sensitive to the position of H peaks to identify within-word position of prominence in Persian. Listeners consistently identified dA3 as the most prominent syllable as this syllable preceded dA4 on which the peak was located, and the rate of their identification was not affected by the duration of H plateau following the pitch peak. In the second experiment, listeners’ ability to use F0 contour as a cue to word boundary was tested on resynthesized speech in which the spectral properties of the signals were intentionally deformed. The results replicated the findings previously obtained for the first experiment, indicating that the end of a high plateau acts as a robust cue to word boundary detection in Persian.},  
Keywords = {word boundary, intonation, prosodic prominence, H plateau, position of H peaks},
volume = {16},
Number = {4}, 
pages = {135-150}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.4.135},
url = {http://jsdp.rcisp.ac.ir/article-1-813-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-813-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2020}  
}

@article{ 
author = {Rouhani, Saeed and Pezeshki, Tahereh and Sohrabi, Babak},  
title = {Design and Test of the Real-time Text mining dashboard for Twitter}, 
abstract ={One of today's major research trends in the field of information systems is the discovery of implicit knowledge hidden in dataset that is currently being produced at high speed, large volumes and with a wide variety of formats. Data with such features is called big data. Extracting, processing, and visualizing the huge amount of data, today has become one of the concerns of data science scholars. The impact of big data on information analysis can be traced to four different parts. The first part is data extraction and processing, the second part is data analysis, the third part is data storage, and finally the visualization of the data. In the field of big data processing, in various studies, different categories have been presented. For example, in the studies of Hashim et al., big data processing is divided into two categories. These two types are: batch and real time. These two categories of processing, which nowadays are standard in any comprehensive big data solution, also have been introduced in Abawajy studies: batch processing is related to offline processing, and real-time processing is usually used to analyze the streaming data without any need to storage of data on disk. As data flows from various sources, the data is analyzed and processed real time, for immediate insight. As today's world is rapidly changing and survival in today's competitive world requires instant decision-making based on flows of data, streaming data analysis is becoming increasingly important. On the other hand, one of the great valuable sources of streaming data is the data generated by social networks’ users such as Twitter. Social networks data sources are very rich sources for analysis as they come from the opinions and opinions of their users. As discussed earlier, and since previous studies such as Flash's studies have focused more on batch analysis (offline data), this study has attempted to investigate a variety of tools and infrastructures related to big streaming data, and finally design a real-time dashboard based on Twitter social network streaming data. The following article addresses two research questions: 1) How to design and implement a real-time dashboard based on social networks data? 2) Which different configurations are best suited for real-time dashboard analysis and visualization? In other words, the purpose of this article is to provide a solution for extracting and visualizing Twitter's social network streaming data by deleting databases, as an examples of big data real time analysis. In this research, we used Twitter streaming data as an input, Apache Storm as a processing platform and D3.js as a visualization tool. Finally, the designed dashboard was evaluated using Design of Experiment method and other statistical tests in various types of Apache Storm configurations and eventually it was proved that the dashboard is real time with an average response time for 1 minute and 30 seconds.},  
Keywords = {Big data, visualization, real time dashboard},
volume = {16},
Number = {4}, 
pages = {151-164}, 
publisher = {Research Center on Developing Advanced Technologies},

doi = {10.29252/jsdp.16.4.151},
url = {http://jsdp.rcisp.ac.ir/article-1-826-en.html},  
eprint = {http://jsdp.rcisp.ac.ir/article-1-826-en.pdf},  
journal = {Signal and Data Processing},  
issn = {2538-4201}, 
eissn = {2538-421X}, 
year = {2020}  
}