@article{ author = {Minaei-Bidgoli, Behrouz and Faili, Heshaam and Aminian, Maryam}, title = {Unsupervised Persian Verb Valency Induction}, abstract ={Valency is the key concept in dependency grammar. Among all word categories, verbs are the most important categories with a key role in syntax and semantics. Verb is the central role in a sentence and acts as the main semantic component in the dependency grammar. In this paper, after studying several methods for unsupervised discovery of Persian verb valency, the ambiguities are studied. Among all methods, EM gained the best results i.e. two time more F-score that binomial hypothesis testing}, Keywords = {Dependency grammar, verb valency, Persian language, unsupervised induction, EM algorithm}, volume = {9}, Number = {2}, pages = {3-12}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-102-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-102-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2013} } @article{ author = {}, title = {}, abstract ={}, Keywords = {}, volume = {9}, Number = {2}, pages = {13-22}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-97-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-97-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2013} } @article{ author = {Hourali, Maryam}, title = {An Intelligent Ontology Construction System Using Hybrid ART Neural Network and C-value Method}, abstract ={In recent years, many efforts have been done to design ontology learning methods and automate ontology construction process. The ontology construction process is a time-consuming and costly procedure for almost all domains/applications, so automating this process is a solution to overcome the knowledge acquisition bottleneck in information systems and reduce the construction cost. In this article a novel intelligent ontology learning method is proposed which can be used in many domains and applications. The proposed learning system has no need for initial common or specialized input ontologies or predefined semantic terms indeed, the initial database anonly consists of input texts sets. The proposed learning system could extract associated ontologies of various domains using combined methods. To do this, a combination of linguistic, statisticaland machine learning methods based on the C-value method, the TF-IDF one, the neural network, and co occurance analysis are applied. So, first domain-related documents were collected. Then natural language processing methods such as C-value method were implemented for extracting meaningful terms from documents. Next, ART (Adaptive Resonance Theory) neural network was used to cluster documents and associated weight of terms was calculated by TF–IDF method in order to find candidate keyword for each cluster. Finally, co-occurrence analysis was used to construct concept hierarchy and complete the ontology. Results show that the proposed ontology learning method has a high precision comparing to similar studies}, Keywords = {Ontology, ART Neural Network, TF-IDF, C-value }, volume = {9}, Number = {2}, pages = {23-36}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-130-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-130-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2013} } @article{ author = {Mehrnam, Amir hossein and MotiNasrabadi, Ali and Ghodousi, Mahrad and Mohamadian, Amin and Torabi, Shahl}, title = {Detection of Guilty Knowledge, Using Single Trial ERPs, and Based on Recurrence plots Nonlinear Method}, abstract ={In this study, Recurrence Plots (RPs) has been adapted as a nonlinear approach in order to detection of guilty subjects’ knowledge based on their single-trial ERPs. The dataset were acquired from 49 human subjects who were participated in a Concealed Information Test (CIT). According to the test protocol, guilty subjects denied their information about familiar faces, so the aim was to detect the concealed faces in these subjects. Recurrence quantifiers were employed in feature extraction stage. Chaotic dynamic of brain’s signals and figuring out the trajectories in phase space are two important issues that can be indicated in these quantifiers. Results demonstrate, that the appearance of P300 signals in guilty subjects (because of denying a familiar face), increase the determinism and predictability of their brain’s signals. Also using Genetic Algorithm (GA) in feature selection level together with Linear Discriminant Analysis (LDA) classifier and a new method named: “inconstant threshold detection”, we achieved an accuracy about 89.7% on combining information of Fz, Cz and Pz channels.}, Keywords = {Recurrence Plots Nonlinear Method, Guilty Knowledge Test, Single Trial ERPs }, volume = {9}, Number = {2}, pages = {37-48}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-75-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-75-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2013} } @article{ author = {KHALILZADEH, MOHAMAD ALI and SARAFAN, RASOOL and AZARNOOSH, MAHDI}, title = {Lie detector system based on PhotoPlethysmoGraph (PPG) and Galvanic Skin Response (GSR) signals by means of neural network}, abstract ={The aim of this article is to design a lie detector system using GSR and PPG.The data set was including of photoplethysmograph signals and galvanic skin response record through an inductive test and using classic polygraph device. Thenceforth, features of time and frequency were extracted. Consequently data were classified and accuracy coefficient was calculated by applying these features to linear Discriminant analysis LDA and MLP and Elman neural networks. 20 people participated in the study. The mean age of participants was 36 years. Finally determination of lie was done with accuracy coefficient of 87% by applying Elman neural network. According to the findings, the new method introduced in this study has while offering a more comfortable recording and less diagnostic costs. This new method can be suggested for use as a lie screening system}, Keywords = {Lie Detection, PhotoPlethysmoGraph, Galvanic Skin Response, Neural Network }, volume = {9}, Number = {2}, pages = {49-60}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-77-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-77-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2013} } @article{ author = {}, title = {Compression time variable information using Huffman code}, abstract ={Abstract: In this paper, we fit a function on probability density curve representing an information stream using artificial neural network . This methodology result is a specific function which represent a memorize able probability density curve . we then use the resulting function for information compression by Huffman algorithm . the difference between the proposed me then with the general methods is , using the Huffman algorithm in several times . In every time , the probability density function is fitted , estimated and then the information representing the function is added to end of the information stream . we next propose two different algorithms for information encoding and decoding using time variable estimation of probability density function . In order to evaluate the proposed algorithm , the percentage of the compression resulting our method has been compared with two popular methods named FDR code [4] and Golomb1 at the end}, Keywords = {variable time probability density function , neural network , compression information , memorize able information stream, Huffman code}, volume = {9}, Number = {2}, pages = {61-74}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-144-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-144-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2013} } @article{ author = {ebrahimnezhad, hossein and khademi, ghasem}, title = {Multi-view based 3D Human Pose Estimation by Fitting the Projection of 3D Articular Skeleton Model in Silhouette Images}, abstract ={Automatic capture and analysis of human motion, based on images or video is important issue in computer vision due to the vast number of applications in animation, surveillance, biomechanics, Human Computer Interaction, entertainment and game industry. In these applications, it is clear that 3D human pose estimation is an essential part. Therefore, its accuracy has a great effect on the performance of these applications. Because of the variation in appearance and articulations of human, self-occlusion and high dimensional state-space of human pose, 3D human pose estimation from image observations is a challenging problem. In this paper, a new method of 3D human pose estimation from multi-view video sequence is introduced. In the proposed method, instead of seeking directly over the high dimensional states-space of human pose and employing the complex inferring algorithms, a hierarchical search method with distinct objective function for each part of the body and direct optimization methods is employed. Advantages of the proposed method are: automatic initialization, labeling of parts of the body contour and using separate objective function for different parts of the body. Experimental results demonstrate that the proposed method can be effectively used as a marker-less system to estimate 3D human pose in a multi-view sequence.}, Keywords = {3D human pose estimation, human motion capture, articulated model, Optimization, Silhouette Images, 3D skeleton}, volume = {9}, Number = {1}, pages = {3-18}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-694-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-694-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2012} } @article{ author = {Faili, Heshaam and Ghader, Hamidreza and MortezaAnaloui, Mortez}, title = {A Bayesian Model for Supervised Grammar Induction}, abstract ={In this paper, we show that the problem of grammar induction could be modeled as a combination of several model selection problems. We use the infinite generalization of a Bayesian model of cognition to solve each model selection problem in our grammar induction model. This Bayesian model is capable of solving model selection problems, consistent with human cognition. We also show that using the notion of history-based grammars will increase the number and decrease the complexity of model selection problems in our grammar induction model. This results in the induction of a better grammar which leads to 9.1 points increase in F1 measure, for parsing the section 22 of Penn treebank in comparison with a similar model that does not use history-based grammar induction techniques.  }, Keywords = {Bayesian model of cognition, tree substitution grammars, Dirichlet process, Chinese restaurant process, history-based grammars}, volume = {9}, Number = {1}, pages = {19-34}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-696-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-696-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2012} } @article{ author = {mohammadnejad, hojat and vali, mansour}, title = {New Approach in Robust Speech Recognition Based on Missing Feature using Bidirectional Neural Network}, abstract ={Performance of speech recognition systems is greatly reduced when speech corrupted by noise. One common method for robust speech recognition systems is missing feature methods. In this way, the components in time - frequency representation of signal (Spectrogram) that present low signal to noise ratio (SNR), are tagged as missing and deleted then replaced by remained components and statistical information of clean speech. In this article a new approach of missing features method based on compensation are proposed. A Bidirectional Neural Network (BNN) was developed and implemented in order to modify unreliable components in input feature vectors and improve the overall recognition accuracy. Distorted components in feature vectors were estimated in accordance with the latent knowledge in the hidden layer of the neural network. This knowledge is obtained by training with clean and noisy speech, simultaneously and is mostly induced by reliable and less influenced components by the irrelevant variations in speech signal. In this approach, there is no need to identify missing components that is a challenging issue in the field of robust speech recognition based on missing feature method because reconstruction is done on all components (whether reliable or unreliable), in order to become more similar to the clean speech component. This point is a very significant advantage that has been achieved in this article. Comparing the results of these two methods shows that using Missing feature methods, 4.2% improvement were obtained in the accuracy of speech recognition for noisy signal by SNR=0dB, whereas improvement value increased to 8.5%, using bidirectional neural network for the same signal to noise ratio.}, Keywords = {Bidirectional Neural Network, Missing Feature Methods, Robust Speech Recognition, Vector Taylor Series}, volume = {9}, Number = {1}, pages = {35-48}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-692-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-692-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2012} } @article{ author = {yusefi, hamed and gardeshi, mahmud and sabzinejad, mohamm}, title = {asdasd}, abstract ={asdasdasdad}, Keywords = {asd}, volume = {9}, Number = {1}, pages = {49-58}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-697-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-697-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2012} } @article{ author = {mehralian, mohammad amin and kazemfouladi, kazem}, title = {The Recognition of Online Handwritten Persian Characters Based on their Main Bodies Using SVM}, abstract ={In this paper a new method for the online recognition of handwritten Persian characters has been proposed which uses a set of simple features and Support Vector Machine (SVM) as a classifier. The task of preprocessing allows us to equalize feature vectors from different characters. This algorithm is implemented in two steps. In the first step, input character is classified into one of eighteen groups of main strokes of characters and in the second step, position, number, and the shape of sub-strokes determine character type. For example to recognize the character ‘ت’, in the first step the character will be classified to group of letters ‘ب، پ، ت، ث’ based on main stroke shape and then classification is done using information of the sub-strokes. In the final step, post processing, we rectify previous step results employing unmatched conditions between main stroke and sub-strokes. Consider a main stroke «ل» with a point at the top of that in this situation post processing step will change result to letter «ن». The experimental results -which is based on Online-TMU database- show that the recognition rate of the main strokes of the characters is 94% which reaches to 98% using the information of sub-strokes.}, Keywords = {Online Persian Character Recognition, Handwriting Recognition, Support Vector Machine (SVM)}, volume = {9}, Number = {1}, pages = {59-68}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-693-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-693-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2012} } @article{ author = {mollaei, nima and abdolahzadeh, ahmad and shirazi, hossei}, title = {WI;CRF: A new approach to extract the required information from military documents}, abstract ={Military Information Extraction techniques are interested for military managers and commanders. But usual information extraction techniques cannot be used for that domain, because military corpus has special structure that differs from non-military corpus. In this paper the military documents structure is compared with non-military documents structure. Moreover a new classification is proposed for military documents. IE system effects are also surveyed for each class. Then a new composite approach is proposed according to the experimental results. The new approach is based on Wrapper Induction and CRF Model. Test bed is also prepared from battlefield reports to evaluate the proposed system. The improvement is shown based on tow metrics namely Recall and F-Measure. The usefulness of the proposed system is also demonstrates.  }, Keywords = {Military Document, Information Extraction (IE), Conditional Random Field (CRF), Wrapper Induction (WI)}, volume = {9}, Number = {1}, pages = {67-80}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-695-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-695-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2012} }