Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 13 3 2016 12 1 Hyper-Spectral Data Feature Extraction Using Rational Function Curve Fitting 3 16 FA Hassan Ghassemian Tarbiat Modares University ghassemi@modares.ac.ir Y Seyed Abolfazl Hosseini Tarbiat Modares University universizen@yahoo.com N 10.18869/acadpub.jsdp.13.3.3 In this paper, with due respect to the original data and based on the extraction of new features by smaller dimensions, a new feature reduction technique is proposed for Hyper-Spectral data classification. For each pixel of a Hyper-Spectral image, a specific rational function approximation is developed to fit its own spectral response curve (SRC) and the coefficients of the numerator and denominator polynomials of this function are considered as new extracted features. The method focuses on geometrical nature of SRCs and relies on the fact that the sequence discipline - ordinance of reflectance coefficients in spectral response curve - contains some information which has not been addressed by many other existing methods based on the statistical analysis of data.  Maximum likelihood classification results demonstrate that our method provides better classification accuracies in comparison with many competing feature extraction algorithms. In addition, the proposed algorithm has the possibility  of being  applied to all pixels of image individually and simultaneously as well.  http://jsdp.rcisp.ac.ir/article-1-346-en.html http://jsdp.rcisp.ac.ir/article-1-346-en.pdf

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 13 3 2016 12 1 Precisely chaotic models survey with Qualitative Bifurcation Diagram 17 34 FA Ghasem Sadeghi Bajestani g.sadeghi@imamreza.ac.ir Y Abbas Monzavi abas_monzavi@yahoo.com N Seyed Mohamad Reza Hashemi Golpaygani hashemi_g@morva.net N 10.18869/acadpub.jsdp.13.3.17 The most important method  for behavior recognition of recurrent maps is to plot bifurcation diagram. In conventional method used for plotting bifurcation diagram,  a couple of time series for different values of model parameter have been generated and these points have been plotted with due respect to it after transient state. It does not have enough accuracy necessary for period detection and essential for discrimination between long periodic behaviors from chaotic behaviors; on the other hand because of being 2-dimensinal, it will not be possible to investigate the effect if the initial condition is in the basin of attraction. In this research, a new bifurcation diagram is presented which is called: Qualitative Bifurcation Diagram (QBD). QBD provides accurate determination of periodicity. Results of our algorithm implementation on logistic map, represents its ability on determining long periods and period windows. Bifurcation diagram of logistic map does not obey mosaic tiling patterns (patterns that are created by arrangement not interaction) as a disciplinein addition to having the dynamic order. Some benefits of QBD are: long period discrimination, period window detection, computation time reduction, period presentation instead of amplitude show. In the  following we have an analytical survey to Lyapunov exponent – as a usual measurement tool for chaotic behavior – and important notes are expressed. Finally, Recurrent Quantification Analysis (RQA) and QBD are compared.   Bifurcation diagram, Chaos, Logistic Map, Lyapunov Exponent, Recurrent Quantification Analysis http://jsdp.rcisp.ac.ir/article-1-309-en.html http://jsdp.rcisp.ac.ir/article-1-309-en.pdf

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 13 3 2016 12 1 Shape based object retrieval using descriptors extracted from growing contour process 35 50 FA Khadijeh Mahdikhanlou Sahand University of Technology kh_mahdikhanlou@sut.ac.ir N Hossein Ebrahimnezhad Sahand University of Technology ebrahimnezhad@sut.ac.ir Y 10.18869/acadpub.jsdp.13.3.35 In this paper, a novel shape descriptor for shape-based object retrieval is proposed. A growing process is introduced in which a contour is reconstructed from the bounding circle of the shape. In this growing process, circle points move toward the shape in normal direction until they  get to the shape contour. Three different shape descriptors are extracted from this process: the first descriptor is defined as the number of steps that every circle point should pass which is called Growing Steps. The second descriptor is considered as the boundary distance of the circle points at the end of the growing process. The third descriptor is the curvature of the growing lines created by moving points. Invariance to translation is the intrinsic property of these features. By selecting a fixed starting point and tracing the boundary in a fixed direction (clock-wise or  counter clock-wise), a set of descriptors  could be collected invariant to rotation. Finally, normalizing the descriptors makes them invariant to scale. Support vector machines based on one-shot score are applied in the retrieval stage. Experimental results show that the suggested method has high performance for shape retrieval. It achieves 89.16% retrieval rate on MPEG-7 CE-Shape-1 dataset. Shape retrieval, Growing points, Growing steps, Boundary distance, Curvature of growing lines, SVM-OSS. http://jsdp.rcisp.ac.ir/article-1-358-en.html http://jsdp.rcisp.ac.ir/article-1-358-en.pdf

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 13 3 2016 12 1 51 62 FA Bagher BabaAli University of Tehran bagher.babaali@gmail.com Y 10.18869/acadpub.jsdp.13.3.51 Although researches in the field of Persian speech recognition  claim  a  thirty-year-old  history in Iran  which has achieved considerable progresses, due to the lack of well-defined experimental framework, outcomes from many of these researches are not comparable to each other and their accurate assessment won’t be possible. The experimental framework includes ASR toolkit and speech database which consists of training, development and test datasets. In recent years,   as a state-of-the-art open-source ASR toolkit; Kaldi has been very well-received and welcomed in the community of the world-ranked speech researchers around the world. considering all aspects, Kaldi is the best option among all of the other ASR toolkits to establish a framework to do research in all languages, including Persian. In this paper, we chose Fardat as the speech database which is the counterpart of TIMIT for Persian language because not only it has got a standard form  but it’s also accessible for all researchers around the world. Similar to the recipe on TIMIT database, we defined these three sets on the Farsdat: Training, Development and Test sets. After a survey on Kaldi’s components and features, we applied most of state-of-the-art ASR techniques in the Kaldi on the Farsdat based on three sets definition. The best phone error rate on development and test set have been 20.3% and 19.8%. All of the codes and the recipe that was written by author have been submitted to Kaldi repository and they are accessible  for free, so all the reported results  will be easily replicable if you have access to Farsdat database. Persian Continuous Speech Recognition, FarsDat Database, Kaldi Toolkit http://jsdp.rcisp.ac.ir/article-1-348-en.html http://jsdp.rcisp.ac.ir/article-1-348-en.pdf

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 13 3 2016 12 1 A Dynamic Skin Detection Method Using the Fusion of 2-D Histogram-Based Features 63 78 FA Bahare Moradi Babol Noshirvani University of Technology b.moradi@stu.nit.ac.ir N Mehdi Ezoji Babol Noshirvani University of Technology m.ezoji@nit.ac.ir Y 10.18869/acadpub.jsdp.13.3.63 This paper presents a dynamic approach to Skin Detection- to separate the skin pixels from non-skin pixels- in colored images. The static methods which use a fixed skin color model, will fail if there are illumination variations or different skin colors in an image. Because of contextual information the proposed algorithm will be less sensitive to the uncontrolled illumination conditions. In addition, the selection of discriminant features and the fusion of them and Bayesian classification increase the accuracy of the proposed method in comparison to the reference methods. Skin Detection, Skin Dynamic model, 2-D Histogram, Bayesian Rule http://jsdp.rcisp.ac.ir/article-1-325-en.html http://jsdp.rcisp.ac.ir/article-1-325-en.pdf

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 13 3 2016 12 1 Robust method of changes of light to detect and track vehicles in traffic scenes 79 98 FA zahra hanifelou faculty of computer engineering, university of isfahan hanifelo@eng.ui.ac.ir Y Amir Hassan Monadjemi faculty of computer engineering, university of isfahan monadjemi@eng.ui.ac.ir N peyman moallem Faculty of Engineering,Department of Electrical Engineering,university of isfahan p_moallem@eng.ui.ac.ir N 10.18869/acadpub.jsdp.13.3.79 In this paper, according to the detection and tracking of the moving vehicles at junctions, a rapid method is proposed which is based on intelligent image processing. In the detection part, the Gaussian mixture model has been used to obtain the moving parts. Then, the targets have been detected using HOG features extracted from training images, Ada-boost Cascade Classifier and the trained SVM. At the tracking part, a number of key points on the image of the vehicle were identified at first. The center of mass of the object and the edges were used to obtain these key points because these points are primarily important and more common in tracking rigid bodies. Then, these points were tracked in consecutive frames using definitive adaptive procedures. Also, the Kalman filter has been used to estimate new locations when the detector  is not able to detect the targets. The major advantage of this method  in comparison with the previous methods is its resistance against vehicle's overlapping and changes in Illuminations, so that the detection accuracy is 90.80% on overloaded traffic scenes and 88.75% on the tracking vehicles. Detection, Tracking, Ada-boost, Kalman Filter, Vehicle tracking, Deterministic Methods Corresponding, Cost Function http://jsdp.rcisp.ac.ir/article-1-510-en.html http://jsdp.rcisp.ac.ir/article-1-510-en.pdf

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 13 3 2016 12 1 Question Classification using Ensemble Classifiers 99 112 FA hadi ghaemi Ferdowsi University of Mashhad (FUM) hadi.qaemi@gmail.com Y mohesn kahani Ferdowsi University of Mashhad (FUM) kahani@um.ac.ir N 10.18869/acadpub.jsdp.13.3.99 Question answering systems are produced and developed to provide exact answers to the question posted in natural language. One of the most important parts of question answering systems is question classification. The purpose of question classification is predicting the kind of answer needed for the question in natural language. The  literature works can be categorized as rule-based and learning-based methods. This paper proposes a novel architecture for hybrid classification of questions. The results of the classifiers were combined by five methods of Weighted Voting, Behavior Knowledge space, Naive Bayes, Decision Template and Dempster-Shafer. The method uses a combination of two classifiers based on machine learning (Support Vector Machine and Sparse Representation) and one rule-based classifier. The learning-based classification uses the set of features extracted from the questions. The features are extracted on the basis of the lexical and syntactic structure of the questions. The results from the classifiers were combined by the methods that are common in the combination of one-class classifiers and the Obtained results indicate the improvement of the classification operations in comparison with the present methods.  Question classification, Rule-based, Learning-based, Sparse Representation, Support Vector Machine, Question answering. http://jsdp.rcisp.ac.ir/article-1-270-en.html http://jsdp.rcisp.ac.ir/article-1-270-en.pdf

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 13 3 2016 12 1 Automatic credibility assessment screening using discriminate analysis of skin conductance response and photoplethysmograph signals 113 128 FA Maryam Saidi RCَِDAT msaidi@aut.ac.ir Y Amin Mohammadian RCَِDAT mohammadian@rcisp.ac.ir N Marzieh Daneshikohan RCَِDAT biomedicaleng_2012@yahoo.com N Zohreh Seyedsalehi RCَِDAT z.seyedsalehi@aut.ac.ir N 10.18869/acadpub.jsdp.13.3.113 Credibility assessment screening by a small system and receiving optimum result in minimum time is a basic need in critical gates. Therefore the aim of this research is automatic detection of stress in guilty persons through skin conductance response and photoplethysmograph signals which are convenient and ease-of-use sensors .In this paper, a set of database with interview protocol (including control and relevant questions) in mock crime (Stealing jewels) is provided. 40 subjects participated in the experiments. 28 time-frequency features are extracted from two mentioned signals. The function of dimension reduction algorithms including principal component analysis, Kernel based PCA, linear discriminant analysis, cluster based LDA is evaluated to select optimum features. Support Vector Machine, Bayesian and AdaBoost are used as classifiers. The evaluation of algorithms on database is based on LOO method. Maximum accuracy (81.08%) is obtained through principal components analysis as feature selection method and Bayesian as classifier. Stress detection, Screening, Skin conductance signal, Photoplethysmography. http://jsdp.rcisp.ac.ir/article-1-242-en.html http://jsdp.rcisp.ac.ir/article-1-242-en.pdf

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 13 3 2016 12 1 Different Application Fields of Brain Signal Processing in Iran 129 154 FA Asadollah Shahbahrami University of Guilan shahbahrami@guilan.ac.ir Y Kiumarc Najafi Medical Faculty gums.ac.ir N Tahereh Najafi Azad University of Rasht Tata.najafi@hotmail.com N 10.18869/acadpub.jsdp.13.3.129 According to the researches, it turns out that human's activities are the results of the internal-neural activities of their brain. The reflection of such activities which are propagated throughout the scalp can then be acquired and processed. In this regard, brain signals can be acquired and recorded by EEG (Electroencephalography). Researchers have applied different technqiues for acquiring, pre-processing, feature extrcation and reduction and classifying EEG signal. According to published papers by Iranian researchers until 2015, it  has been found that most studies have been performed in medical applications and brain computer interface fields. Sampling and receiving EEG signals have been performed more in the central region than other regions. Statistical technqiues have more been used for feature extraction than other technqiues. Finally, the support vector machines are mostly used in the classification of brain signals. At the end, a study on anxiety and depression detection on fifty cases was performed in medical field. Simulation results show that our approach achieve an accuracy of up to 97 percents. Feature Extraction, Feature Reduction, Classification, Brain Signals http://jsdp.rcisp.ac.ir/article-1-305-en.html http://jsdp.rcisp.ac.ir/article-1-305-en.pdf

Research Center on Developing Advanced Technologies Signal and Data Processing 2538-4201 2538-421X 13 3 2016 12 1 Sparse unmixing of hyper-spectral images using a pruned spectral library 155 169 FA Hossein Fayyazi Malek-Ashtar University of Technology fayyaz-_hossein@yahoo.com Y Hamid Dehghani Malek-Ashtar University of Technology hamid_deh@yahoo.com N Mojtaba Hosseini Amirkabir University of Technology mojtabahoseini@aut.ac.ir N 10.18869/acadpub.jsdp.13.3.155 Spectral unmixing of hyperspectral images is one of the most important research fields  in remote sensing. Recently, the direct use of spectral libraries in spectral unmixing is on increase. In this way  which is called sparse unmixing, we do not need an endmember extraction algorithm and the number determination of endmembers priori. Since spectral libraries usually contain highly correlated spectra, the sparse unmixing approach leads to non-admissible solutions. On the other hand, most of the proposed solutions are not noise-resistant and do not reach to a sufficiently high sparse solution. In this paper, with the purpose of overcoming the problems above, at first the spectral library will be pruned based on the spectral information of the image,clustering and classification techniques. Then a genetic algorithm  will be used for sparse unmixing. The experimental results on the simulated and real images show that the proposed method gives good results in noisy images.  Hyper-spectral images, Spectral Library Pruning, Sparse Unmixing. http://jsdp.rcisp.ac.ir/article-1-128-en.html http://jsdp.rcisp.ac.ir/article-1-128-en.pdf