Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 12 3 2015 12 1 A real-world spell checker using context-sensitive features 3 14 FA Behzad Mirzababaei university of Tehran Heshaam Faili university of Tehran Nowadays, a large volume of documents is generated daily. These documents generated by different persons, thus, the documents contain spelling errors. These spelling errors cause quality of the documents are decrease. Therefore, existence of automatic writing assistance tools such as spell checker/corrector can help to improve their quality. Context-sensitive are misspelled words that have been wrongly converted into another word of the language. Thus, detection of real-word errors requires discourse analysis. In this paper, we propose a language independent discourse-aware discriminative ranker and use information of whole document and a log-linear model for ranking. To evaluate our method, we augment it into two context-sensitive spellchecker systems one is based on Statistical Machine Translation (SMT) and the other is based on language model. For more evaluation, we also use two different tests. Proposed method cause outperform about 17% over the SMT base approach with respect to detection and correction recall.

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 12 3 2015 12 1 A two step method for offline handwritten Farsi word recognition using adaptive division of gradient image 15 29 FA alireza ahmadifard hossein khosravi This paper presented a two step method for offline handwritten Farsi word recognition. In first step, in order to improve the recognition accuracy and speed, an algorithm proposed for initial eliminating lexicon entries unlikely to match the input image. For lexicon reduction, the words of lexicon are clustered using ISOCLUS and Hierarchal clustering algorithm. Clustering is based on the features that describe the shape of word generally. In second step, a new method proposed to extract histogram of gradient image which this showed well the correspondence between different samples of handwritten word images. The gradient feature vectors of input words are compared with gradient feature vectors of candidate words using K nearest neighbor classifications. The recognition result on handwritten words of IRANSHAR dataset showed that the lexicon reduction step and the new method of extracting gradient feature increased recognition accuracy and speed by removing classifier confusion.

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 12 3 2015 12 1 Blind Detection and Equalization in Chaotic Communication Systems Using Importance Sampling 31 41 FA Mohammad Farzan Sabahi In this paper an Importance Sampling technique is proposed to achieve blind equalizer and detector for chaotic communication systems. Chaotic signals are generated with dynamic nonlinear systems. These signals have wide applications in communication due to their important properties like randomness, large bandwidth and unpredictability for long time. Based on the different chaotic signals properties, different communication methods have proposed such as chaotic modulation, masking, and spread spectrum. In this article, chaos masking is assumed for transmitting modulated message symbols. In this case, channel estimation is a nonlinear problem. Several methods such as extended Kalman filter (EKF), particle filter (PF), minimum nonlinear prediction error (MNPE) and ... are previously presented for this problem. Here, a new approach based on Monte Carlo sampling is proposed to joint channel estimation and demodulation. At the receiver end, Importance Sampling is used to detect binary symbols according to maximum likelihood criteria. Simulation results show that the proposed method has better performance especially in low SNR

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 12 3 2015 12 1 Improving the performance of sparse representation-based classifier for EEG classification 43 55 FA Alireza Mirjalili Yazd University Vahid Abootalebi Yazd University Mohammad Taghi Sadeghi Yazd University In this paper, the problem of classification of motor imagery EEG signals using a sparse representation-based classifier is considered. Designing a powerful dictionary matrix, i.e. extracting proper features, is an important issue in such a classifier. Due to its high performance, the Common Spatial Patterns (CSP) algorithm is widely used for this purpose in the BCI systems. The main disadvantages of the CSP algorithm are its sensibility to noise and the over learning phenomena when the number of training samples is limited. In this study, to overcome these problems, two modified form of the CSP algorithms, namely the DLRCSP and GLRCSP have been used. Using the adopted methods, the average detection rate is increased by a factor of about 7.78 %. Also, a problem of the SRC classifier which uses the standard BP algorithm is the computational complexity of the BP algorithm. To overcome this weakness, we used a new algorithm which is called the SL0 algorithm. Our classification results show that using the SL0 algorithm, the classification process is highly speeded up. Moreover, it leads to an increase of about 1.61% in average correct detection compared to the basic standard algorithm.

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 12 3 2015 12 1 Adaptive and Smart Beamforming in Ad-hoc Microphone Arrays by Clustering and Ranking of the Microphones 57 68 FA Seyed Hamid Yazdani Yazd University Hamid Reza Abutalebi Yazd University Considering the existence of a many speech degradation factors, speech enhancement has become an important topic in the field of speech processing. Beamforming is one of the well-known methods for improving the speech quality that is conventionally applied using regular (classical) microphone arrays. Due to the restrictions in the regular arrangement of microphones, in recent years there has been an emerging trend toward the microphone arrays with irregular arrangement (or so-called Ad-hoc microphone arrays). Due to the lack of knowledge about the location and the arrangement of microphones, and spreading of the microphones throughout the environment, the idea of clustering has been considered in this paper. We propose a method for the clustering of microphones in directional noise fields. For this type of noise fields, we propose a new clustering method that works based on the energy of the received signals. We have tried that the proposed clustering method to be applicable in different directional noise fields. We also propose a modified structure for the GSC beamformer by considering different roles for microphone clusters. Our evaluations indicate that in some situations, employing a microphone cluster produces superior results compared to the usage of all microphones. This, in turn, shows that the performance of the speech enhancement system can been improved using the clustering process, while the computational load is also decreased (due the reduction in the number of employed microphones).

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 12 3 2015 12 1 69 80 FA Maryam Sattarpour Tarbiat Modares University Babak Mohammadzadeh Asl Tarbiat Modares University

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 12 3 2015 12 1 Design and evaluation of hybrid encoding schema for Covert Timing Channel on the Internet 81 97 FA Mehdi Dehghani Student Mahmoud Saleh IHU Covert channel means communicating information through covering of overt and authorized channel in a manner that existence of channel to be hidden. In network covert timing channels that use timing features of transmission packets to modulating covert information, the appropriate encoding schema is very important. In this paper, a hybrid encoding schema proposed through combining "the inter-packets gap" and "the reordering packets" encoding schemas, emphasizing on improvement of capacity and stealthiness of covert channel. The capacity of proposed channel have computed and stealthness and robustness of channel have evaluated in experimental manner. Our results show that selecting 3 to 5 packet in a codword in accordance to normal situation of network traffic, the capacity is increased from 10% to 300% and stealthness is boosted up to acceptable value, and robustness is high enough.

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 12 3 2015 12 1 A machine learning approach for correcting the errors of a Treebank 99 108 FA Farzaneh Zarei Hesham Faili Maryam Mirian The Treebank is one of the most useful resources for supervised or semi-supervised learning in many NLP tasks such as speech recognition, spoken language systems, parsing and machine translation. Treebank can be developded in different ways that could be, generally, categorized in manually and statistical approaches. While the resulted Treebank in each of these methods has the annotation error, one which accomplished by statistical method has much more errors than the other. Error in Treenabanks causes that they are not useful anymore. In this paper an statistical method is proposed which aims to correct the errors in a specific English LTAG-Treebank. The proposed method was applied to a automatically generated Treebank and an improvement from 68% to 79% respect to F-measure is retrieved.

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 12 3 2015 12 1 Confidence Estimation for Machine Translation using Novel Syntactic and Lexico-semantic Features 109 121 FA Marzieh Salehi alzahra university Shahram Khadivi amirkabir university Nooshin Riahi alzahra university Despite machine translation (MT) wide suc-cess over last years, this technology is still not able to exactly translate text so that except for some language pairs in certain domains, post editing its output may take longer time than human translation. Nevertheless by having an estimation of the output quality, users can manage imperfection of this tech-nology. It means we need to estimate the confidence of the output without having any references. Moreover, Confidence Estimation (CE) can be useful for some applications that their goal is to improve machine translation quality such as system combination, regener-ating, pruning, etc. but there is not yet any completely satisfactory method for CE task. We propose 5 groups of syntactic and lexico-semantic features. The results show that the lexico-semantic feature outperforms the best baseline system (2) by 9.63% in CER, 8.5% in F-measure and 5.1% in negative class F-measure. Also by combining proposed syn-tactic features together we reach 4.59% CER reduction, 4.1% F-measure improvement and 2% negative F-measure improvement.