per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-03 12 4 3 15 article Seyed Mojtaba Marvasti-Zadeh mojtaba.marvasti@stu.yazd.ac.ir 1 Hossein Ghanei yakhdan hghaneiy@yazd.ac.ir 2 Yazd University Yazd University Despite data resilient methods against error that are applied on video data in transmitter side, occurringerror along video data transferring for communication channels is inevitable. Error concealment is a useful method for improving the quality of damaged videos in receiver side. In this paper, a fast and hybrid boundary matching algorithm is presented for more accurate estimating of damaged motion vectors (MVs) from received video. The proposed algorithm performs the error concealment for each damaged macroblock (MB) according to the preference list of error concealment that it assigns. Then, boundary distortion for each candidate MBis calculated with classic and outer boundary matching criterionsfor each boundary pixel. After reconstructing of each damaged MB, the list of preference is updated. Moreover, depending on accuracy of each adjacent boundary from damaged MB, a special weight is given to them, through match process. Finally, the candidate MVwith the lowest boundary distortion is selected as MV of damaged MB. Experimental results show that the proposed algorithm increases the average of PSNR for different test sequences more than 1.8 dB in comparison with reference methods and without significant increasing in calculation time and with improving the quality of reconstructed videos. http://jsdp.rcisp.ac.ir/article-1-173-en.pdf Temporal Error Concealment Motion Vector Estimation Hybrid Boundary Matching Algorithm Macroblock per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-03 12 4 17 31 article Hamid Rajabi hamidrajabi2010@yahoo.com 1 Manoochehr Nahvi , nahvi@guilan.ac.ir 2 University of Guilan University of Guilan The population of elderly people has growing trend in the developed or developing countries. Since the elderly are mainly associated with disability, this group of people exposed to dangerous events such as falling down. It is therefore needed to take care of these people against dangerous events. Intelligent video monitoring is a approach that may be able to give quick notification to the caregivers. For this purpose, in this paper, an approach using a novel tracking method based on modified contour algorithm is presented. The new method is able to conduct tracking and falling down detection in a realistic conditions in the presence of multiple motions. Simulations indicate that the proposed algorithm is able to identify the fall-down event with high accuracy and speed. http://jsdp.rcisp.ac.ir/article-1-183-en.pdf fall detection algorithm contour machine vision tracking intelligent surveillance systems. per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-03 12 4 33 42 article Mohammad Sadegh Nemati Nia r.t1390razavie@chmail.ir 1 2 3 Guess and determine attacks are general attacks on stream ciphers. These attacks are classified into ad-hoc and Heuristic Guess and Determine (HGD) attacks. One of the Advantages of HGD attack algorithm over ad-hoc attack is that it is designed algorithmically for a large class of stream ciphers while being powerful. In this paper, we use auxiliary polynomials in addition to the original equations as the inputs to the HGD attack on TIPSY and SNOW 1.0 stream ciphers. Based on the concept of guessed basis, the number of guesses in both HGD attack and the improved one on TIPSY is six, however the attack complexity is reduced from O(2102)to O(296). This amount is equal to that of ad-hoc attack, but the size of the guessed basis is improved from seven to six. Also, the complexity of GD attack on SNOW 1.0 of heuristic one with the guessed basis of size 6 and ad-hoc attack with the guessed basis of size 7areO(2202) and O(2224), respectively. However, the complexity and the size of guessed basis of the improved HGD attack are reduced to O(2160) and 5, respectively. http://jsdp.rcisp.ac.ir/article-1-261-en.pdf Stream Cipher Guess and Determine attack TIPSY SNOW 1.0 Computational Complexity per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-03 12 4 43 52 article bahram@sharif.edu 1 2 3 4 In this paper, we will introduce an intelligent system to edit and spell check Persian texts. The goal is editing and preprocessing Persian texts for natural language processing tasks. This system is based on an expandable and engineering approach and is composed of three subsystems: Persian text editor, spell checker and stemmer. These parts interact with each other to edit texts. To do this, the stemmer subsystem process each word in the text if the subsystem could not find a stem in the lexicon, the word will be recognized as an incorrect word. Then, the spell checker provides a list of suggestions to correct the wrong word. Subsequently, the editor subsystem edits the text based on the standards of the Academy of Persian Language and Literature. Our evaluation shows nearly 92%, 95% and 96% precision numbers for editor, stemmer and spell checker subsystems, respectively. http://jsdp.rcisp.ac.ir/article-1-250-en.pdf Key words: Natural Language Processing automatic spell checking text editor stemmer per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-03 12 4 53 65 article Somayeh Ahmadkhani s.ahmadkhani@eng.ui.ac.ir 1 Peyman Adibi adibi@eng.ui.ac.ir 2 University of Isfahan University of Isfahan In this paper, we first proposed the supervised version of probabilistic principal component analysis mixture model. Then, we consider a learning predictive model with projection penalties, as an approach for dimensionality reduction without loss of information for face recognition. In the proposed method, first a local linear underlying manifold of data samples is obtained using the supervised probabilistic principal component analysis mixture model. Then, a support vector machine classifier with projection penalty is trained as a predictive model using this local linear manifold. Thus, the predictive model benefits from dimensionality reduction, while it loses minimum amount of useful information. To evaluate the proposed method, we used well-known face recognition databases. Gabor feature extraction method have been applied to these images. The experimental results show that the proposed method has a higher classification accuracy than many of the traditional methods which use predictive models after dimensionality reduction. It also works better than the projection penalty method with linear or nonlinear based dimensionality reduction models. http://jsdp.rcisp.ac.ir/article-1-259-en.pdf Lossless Dimensionality Reduction Mixture Model Probabilistic Principal Component Analysis Supervised Projection Penalty per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-03 12 4 67 81 article Foruzan Fasahat ffesahat@yahoo.com 1 Pedram Payvandy peivandi@yazd.ac.ir 2 Flexibility of woven fabric structure has caused many errors in yarn location detection using customary methods of image processing. On this line, proposing an adaptive method with fabric image properties is concentrated to extract its parameters. In this regards, using meta-heuristic algorithms seems applicable to correspond extraction algorithm of structural parameters to the image conditions. In this study, a new method is proposed for woven fabric image preprocessing and structural texture detection applying compound methods of signal processing, fuzzy clustering and genetic algorithm. Results indicate that proposed method is capable of detecting exact yarn location with mean precision of more than 73 percent in double-layered fabric images with uneven color pattern. In one-layered fabric images with low density weave and invariable color pattern, the mean precision is more than 84 percent. http://jsdp.rcisp.ac.ir/article-1-262-en.pdf Genetic Algorithm Wavelet Transform Fuzzy c-means (FCM) clustering Image Processing Fabric Image Yarn Location. per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-03 12 4 83 94 article meh_mor2003@yahoo.com 1 bahrani@sharif.edu 2 Gigantic amount of textual data being transfers in web everyday. like other communities,cyberspace is vulnerable to attacks, false information and deception.it becomes increasingly important to design an efficient method to trace identity in this community.to investigate the problem of gender identification,we propose 48 feature,and design three machine learning algorithms.the results of study showed that ADtree classifier had accuracy up to 73.8%. http://jsdp.rcisp.ac.ir/article-1-104-en.pdf gender identification author identification text mining per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-03 12 4 95 115 article Fatemeh Soltanzadeh fatemeh.slt@gmail.com 1 Mohammad Bahrani bahrani@sharif.edu 2 Moharram Eslami meslami@znu.ac.ir 3 Sharif University of technology Sharif University of technology University of Zanjan In this paper, an automatic method in converting a dependency parse tree into an equivalent phrase structure one, is introduced for the Persian language. In first step, a rule-based algorithm was designed. Then, Persian specific dependency-to-phrase structure conversion rules merged to the algorithm. Subsequently, the Persian dependency treebank with about 30,000 sentences was used as an input for the algorithm and an equivalent phrase structure treebank was extracted. Finally, the statistical Stanford parser was trained using the developed treebank. Experimental results show a F1 of 96.05% for the conversion algorithm and an F1 of 86.01% for Persian factored model parser. http://jsdp.rcisp.ac.ir/article-1-272-en.pdf Conversion Dependency Grammar Phrase Structure Grammar Natural Language Processing Treebank Persian. per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-03 12 4 117 125 article babakmasoudi282@yahoo.com 1 saeid rahati ghochani RahatiMshdiau.ac.ir 2 Word sense disambiguation is the task of identifying the correct sense for the word in a given context among a finite set of possible sense. In this paper a model for farsi word sense disambiguation is presented. The model use two group of features: first, all word and stop words around target word and topic models as second features. We extract topics from a farsi corpus with Latent Dirichlet Allocation (LDA) model. The system with a maximum entropy model achieved 97.67% precision for 4 high frequently farsi homograph words http://jsdp.rcisp.ac.ir/article-1-58-en.pdf Latent Dirichlet Allocation(LDA) Topic Model Maximum Entropy Word Sense Disambiguation