per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-06 13 1 3 14 article zmehrnahad@gmail.com 1 alatif@yazd.ac.ir 2 In this paper, a new structure for image encryption using recursive cellular automatais presented. The image encryption contains three recursive cellular automata in three steps, individually. At the first step, the image is blocked and the pixels are substituted. In the next step, pixels are scrambledby the second cellular automata and at the last step, the blocks are attachedtogether and the pixels substitute by the third cellular automata. Due to reversibility of cellular automata, the decryption of the image is possible by doing the steps reversely. The experimental results show that the encrypted image is not comprehend visually, also this algorithmhas satisfactory performance in terms of quantitative assessment from some other schemes. http://jsdp.rcisp.ac.ir/article-1-266-en.pdf Cryptography Cellular Automata Recursive Cellular Automata per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-06 13 1 15 25 article majid khorashadizadeh smkh1985@gmail.com 1 ali mohammad latif alatif@yazduni.ac.ir 2 yazd university yazd university In this paper a new efficient method for detecting the impulse noise from the corrupted image using extreme learning machine (ELM) is proposed. An improved version of the standard median filter is suggested to remove the detected noisy pixel. The performance of proposed detector is evaluated using classification accuracy. The results show that our detector is robust even at higher noise density. Results illustrate that proposed filter provides better performance in terms of PSNR than many other median filter variants for Salt and pepper noise. . The suggested technique yields significantly good results both in objective and subjective judgments of image quality. http://jsdp.rcisp.ac.ir/article-1-294-en.pdf per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-06 13 1 27 38 article Morteza Rezaei Sharifabadi mrezaeis@mehr.sharif.edu 1 Parvaneh Khosravizadeh khosravizadeh@sharif.edu 2 Sharif University of Technology Sharif University of Technology Automatic identification of words with semantic roles (such as Agent, Patient, Source, etc.) in sentences and attaching correct semantic roles to them, may lead to improvement in many natural language processing tasks including information extraction, question answering, text summarization and machine translation. Semantic role labeling systems usually take advantage of syntactic parsing and therefor the syntactic representation chosen affects the overall performance of the system. In this research, we present a semantic role labeling system based on full syntactic parsing. For this purpose, we use a dependency parser and machine learning methods. In our system, we have made an effort to overcome the problems of previous semantic role labelers for Persian, which all are based on shallow syntactic parsing. The outcome of the system is promising. http://jsdp.rcisp.ac.ir/article-1-279-en.pdf semantic role labeling shallow semantic parsing dependency grammar Persian language natural language processing computational linguistics per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-06 13 1 39 56 article Zohreh Ansari z_ansari@aut.ac.ir 1 Ali Seyyedsalehi ssalehi@aut.ac.ir 2 Amirkabir University of Technology Amirkabir University of Technology In this article, growable deep modular neural networks for continuous speech recognition are introduced. These networks can be grown to implement the spatio-temporal information of the frame sequences at their input layer as well as their labels at the output layer at the same time. The trained neural network with such double spatio-temporal association structure can learn the phonetic sequence subspace. Therefore, it can filter out invalid phonetic sequences in its own structure and output valid sequences. To evaluate the performance of these growable neural networks, we used FARSDAT and BIG FARSDAT datasets. Experimental results on FARSDAT show that deep modular neural networks outperform the phone accuracy rate of GMM-HMM models with an absolute improvement of 2.7%. Moreover, developing deep modular neural networks to a double spatio-temporal association structure improves their result by 5.1%. As there is no phonetic labeling for BIG FARSDAT, a semi-supervised learning algorithm is proposed to fine-tune the neural network with double spatio-temporal structure on this dataset, which achieves a comparable result with HMMs. http://jsdp.rcisp.ac.ir/article-1-277-en.pdf Deep neural networks Modular neural networks Pre-training Semi-supervised learning Continuous speech recognition per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-06 13 1 57 70 article Yasser Shekofteh y_shekofteh@yahoo.com 1 Hasan Gholipor y_shekofteh 2 M.Mohsen Goodarzi y_shekofteh 3 Jahanshah kabudian y_shekofteh 4 Farshad Almasganj y_shekofteh 5 Shaghayegh Reza y_shekofteh 6 Iman Sarraf y_shekofteh 7 rcdat rcdat rcdat rcdat rcdat rcdat rcdat The performance of automatic speech recognition (ASR) systems is adversely affected by the variations in speakers, audio channels and environmental conditions. Making these systems robust to these variations is still a big challenge. One of the main sources of variations in the speakers is the differences between their Vocal Tract Length (VTL). Vocal Tract Length Normalization (VTLN) is an effective method introduced to cope with this variation. In this method, the speech spectrum of each speaker is frequency warped according to a specific warping factor of that speaker. In this paper, we first developed the common search-based method to obtain the appropriate warping factor over a HMM-based Persian continuous speech recognition system. Then pointing out the computational cost of search-based method, we proposed a linear regression process for estimating warping factor based on the scores generated by our gender detection system. Experimental results over a Persian conversational speech database shown an improvement about 0.54 percent in word recognition accuracy as well as a significant reduction in computational cost of estimating warping factor, compared to search-based approach. http://jsdp.rcisp.ac.ir/article-1-254-en.pdf speech recognition Vocal Tract Length Normalization gender detection linear regression warping factor per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-06 13 1 71 85 article Hamid Ahangarbahan 1 Gholam Ali Montazer montazer@modares.ac.ir 2 Tarbiat Modares University Tarbiat Modares University Today, there are many documents on Internet, such that users can generate new documents by coping them and existing Plagiarism Detection systems (PDS) couldn't detect all kind of plagiarism. The main challenge is finding a suitable algorithm to improving the amount of similar documents and their assessing time. It’s difficult to do assessing similarity in Persian texts that different characteristics affect on it and also many of them are ambiguous. For this reason Dempster - Shefer (Evidence) theory has been used in this paper. The proposed system will assess in a two-level and in the first stage, sentences will divide in general and expert terms and then assessing by suitable measures and domain ontology. These results will be delivered to first level as "basic belief" and will be integrated by using a Dempster combination rule to create one of the second level inputs. In second level, the previous level result and another similarity measures will be weighted and combined belief and plausibility functions for final assessment will be distinguished. This system has been used for real data assessment and compared the actual results shows that the precision between the system results and actual results is about 90%, which implies that the system can be used as Plagiarism Detection System. http://jsdp.rcisp.ac.ir/article-1-276-en.pdf Plagiarism Data fusion Evidence theory Similarity Measures Semantic Similarity per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-06 13 1 87 100 article parvin@iust.ac.ir 1 Persian words in writing with a diverse and cover all modes of grammatical words with the recruitment of a series of specific rules because it is impossible to extract keywords automatically from Persian texts difficult and complex. This thesis has attempted to use linguistic information and thesaurus, keywords Mnatry be provided. Using the symbol system is structured network can be keywords, including the exchange of words, words and words with hierarchical relationships complete the package has increased. Therefore the agreement between users and search keywords text search and recall is increased. In the first stage non-important words are removed and the public. Supervision in the text are words and more words to clarify the relative importance of using a blower numerical weight is assigned to each word that indicates the effectiveness of the word in connection with the subject and compared with the other words used in the text. Particularly complex operation that makes use of thesaurus keywords are extracted Mnytry that kind of hierarchical category scientific literature in the field of information retrieval is indicated. Test results on different topics several text accurately represents the proposed method and the ability to extract the keywords in accordance with user demand. http://jsdp.rcisp.ac.ir/article-1-139-en.pdf Keyword Extraction Thesaurus Computational Linguistic Information Retrieval per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-06 13 1 101 114 article Fardin Ahmadizar f.ahmadizar@uok.ac.ir 1 Khabat Soltanian 2 Fardin AkhlaghianTab 3 Application of artificial neural networks (ANN) in areas such as classification of images and audio signals shows the ability of this artificial intelligence technique for solving practical problems. Construction and training of ANNs is usually a time-consuming and hard process. A suitable neural model must be able to learn the training data and also have the generalization ability. In this paper, multiple parallel populations are used for construction of ANN and evolution strategy for its training, so that in each population a particular ANN architecture is evolved. By using a bi-criteria selection method based on error and complexity of ANNs, the proposed algorithm can produce simple ANNs that have high generalization ability. To assess the performance of the algorithm, 7 benchmark classification problems have been used. It has then been compared against the existing evolutionary algorithms that train and/or construct ANNs. Experimental results show the efficiency and robustness of the proposed algorithm compared to the other methods. In this paper, the impact of parallel populations, the bi-criteria selection method, and the crossover operator on the algorithm performance has been analyzed. A key advantage of the proposed algorithm is the use of parallel computing by means of multiple populations. http://jsdp.rcisp.ac.ir/article-1-110-en.pdf Artificial Neural Networks Evolution Strategy Parallel Populations per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-06 13 1 115 125 article hamid_dehyahoo.com 1 ahmad.madanchi@gmail.com 2 The capability of the matter identification is developed considerably in hyperspectral images. The spectral reflectance of surfaces in these imaging systems in the visible and near infrared range of the electromagnetic spectrum is recorded in extremely narrow and continuous bands. But for some reasons, such as existence the mixed pixels and low spatial resolution of these images, is difficult to land cover accurate position identify. The soft classification methods provide the estimation of the membership value of various classes within mixed pixels. But, by using these methods, the matter information extraction is possible only and position information extraction in sub-pixel level is impossible. In recent years, in order to solve this problem, some methods that are called SRM, have been developed for positioning the extracted membership values by soft classification process in sub-pixels for producing a higher spatial resolution land use map. In this paper, pixel-swapping method is used as the latest SRM algorithms, and with repetition the binary case of this algorithm for each class, this algorithm has been generalized and developed for multi-class. Another main point in sub-pixel classification is the performance evaluation of these classifiers. Because of the influence of various parameters in the sub-pixel classification, the evaluation of this process is very complex. Hence, as a main and innovative activity in this paper, the Influence of the neighborhood level and the zoom factor as two important parameters in the extension pixel-swapping method has been simulated and analyzed. For this purpose, in this paper a framework for evaluating the sub-pixel classification performance based on dependent on and independent on soft classification error is proposed. http://jsdp.rcisp.ac.ir/article-1-30-en.pdf Hyperspectral image Sub-pixel classification Sub-pixel classification evaluation Pixel-swapping method SRM algorithm per Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 2016-06 13 1 127 138 article Mohsen Zardadi zardadi@birjand.ac.ir 1 Naser Mehrshad nmehrshad@birjand.ac.ir 2 Faculty of Engineering In this paper, a new unsupervised algorithm for automatic retinal blood vessel extraction is presented. A pre-processing step is introduced to eliminating optic disk and back ground noise. Blood vessel highlighting is prepared by a new method inspired by simple cells in human visual system. An adaptive threshold is introduced as an activation function of simple cells. Post-processing step is used as a final stage at the output of simple cells to eliminating exudates which is detected as blood vessels. The results on DRIVE database demonstrate that the performance of the proposed algorithm is comparable with state-of-the-art techniques in terms of execution time and extracted vessels. http://jsdp.rcisp.ac.ir/article-1-230-en.pdf retinal vessel segmentation medical assistance systems retinal simple cell model DRIVE database