-
Open Access Article
1 - Determination of Optimum SVMs Based on Genetic Algorithm in Classification of Hyper spectral Imagery
farhad samadzadegan hadise hassaniHyper spectral remote sensing imagery, due to its rich source of spectral information provides an efficient tool for ground classifications in complex geographical areas with similar classes. Referring to robustness of Support Vector Machines (SVMs) in high dimensional MoreHyper spectral remote sensing imagery, due to its rich source of spectral information provides an efficient tool for ground classifications in complex geographical areas with similar classes. Referring to robustness of Support Vector Machines (SVMs) in high dimensional space, they are efficient tool for classification of hyper spectral imagery. However, there are two optimization issues which strongly effect on the SVMs performance: Optimum SVMs parameters determination and optimum feature subset selection. Traditional optimization algorithms are appropriate in limited search space but they usually trap in local optimum in high dimensional space, therefore it is inevitable to apply meta-heuristic optimization algorithms such as Genetic Algorithm to obtain global optimum solution. This paper evaluates the potential of different proposed optimization scenarios in determining of SVMs parameters and feature subset selection based on Genetic Algorithm (GA). Obtained results on AVIRIS Hyper spectral imagery demonstrate superior performance of SVMs achieved by simultaneously optimization of SVMs parameters and input feature subset. In Gaussian and Polynomial kernels, the classification accuracy improves by about 5% and15% respectively and more than 90 redundant bands are eliminated. For comparison, the evaluation is also performed by applying it to Simulated Annealing (SA) that shows a better performance of Genetic Algorithm especially in complex search space where parameter determination and feature selection are solve simultaneously. Manuscript profile -
Open Access Article
2 - Comparison of support vector machine and artificial neural network classification methods to produce landuse maps (Case study: Bojagh National Park)
Mahsa Abdoli Laktasaraei Maryam Haghighi khomamiNational parks and wildlife shelter are the most important natural heritages; therefore, knowing of quantitative and qualitative changes in their land use plays an essential role in the quality of these areas' management. various algorithms have been developed to classi MoreNational parks and wildlife shelter are the most important natural heritages; therefore, knowing of quantitative and qualitative changes in their land use plays an essential role in the quality of these areas' management. various algorithms have been developed to classify satellite imagery in remote sensing, selecting an appropriate classification algorithm is very important in achieving the accurate results. In this research, a more accurate algorithm was determined by comparing the classification accuracy of two artificial neural network and support vector machine algorithms, and it was used to examine the process of the land use changes. The present study was performed in Boujagh National Park, in the Guilan Province, during the years 2000 to 2017, using satellite imagery ETM and OLI of Landsat 7 and 8. The results of the research revealed that the support vector machine algorithm with overall accuracy and Kappa coefficient of 86.42 and 0.83 respectively for the year 2000 and, 90.65 and 0.88 for the year 2017, classified the satellite images more precisely, in comparison with the artificial neural network algorithm with overall accuracy and Kappa coefficient of 83.71 and 0.80 respectively for the year 2000 and overall accuracy and Kappa coefficient of 89.25 and 0.87 for the year 2017. Therefore, the land use maps of the support vector machine algorithm were used to determine the land use changes. The study of land use change by this method concluded that the areas of the waterbody, sea, grassland and agriculture have decreased and marshland, woody and bare lands classes showed an increase during the study period. Manuscript profile -
Open Access Article
3 - Separating alteration units in the Takht-e-Gonbad district using via comparing two classification methods of Support vector machine and maximum likelihood,
Davoud Nazari neda mahvash mohammadi Adabi Mohammad Ghavidel-Syooki haniyeh kalaniSeparation of alteration units has an important role in exploration of ore deposits. In the past, classical methods were used for this purpose. Recently, the support vector machine (SVM), one of the most important data driven models, has been applied for geological purp MoreSeparation of alteration units has an important role in exploration of ore deposits. In the past, classical methods were used for this purpose. Recently, the support vector machine (SVM), one of the most important data driven models, has been applied for geological purpose. This algorithm is a useful learning system based on constrained optimization theory. In this study, the SVM algorithm with various kernels and maximum likelihood method were used to separate the alteration units of the Takht-e-Gonbad district situated in Chahar Gonbad sheet by using satellite images of the ASTER sensor. The results were analyzed and evaluated according to the field studies. Based on the achieved results and field studies, the SVM method with the RBF kernel function compared to other kernels and the maximum likelihood method had the highest accuracy (89.17%) and kappa coefficient (0.83). Thus, the SVM method for classification of alteration is more accurate compared to other discussed methods. Manuscript profile -
Open Access Article
4 - Performance Analysis of SVM-Type Per Tone Equalizer Using Blind and Radius Directed Algorithms for OFDM Systems
Babak Haji Bagher NaeeniIn this paper, we present Support Vector Machine (SVM)-based blind per tone equalization for OFDM systems. Blind per tone equalization using Constant Modulus Algorithm (CMA) and Multi-Modulus Algorithm (MMA) are used as the comparison benchmark. The SVM-based cost funct MoreIn this paper, we present Support Vector Machine (SVM)-based blind per tone equalization for OFDM systems. Blind per tone equalization using Constant Modulus Algorithm (CMA) and Multi-Modulus Algorithm (MMA) are used as the comparison benchmark. The SVM-based cost function utilizes a CMA-like error function and the solution is obtained by means of an Iterative Re-Weighted Least Squares Algorithm (IRWLS). Moreover, like CMA, the error function allows to extend the method to multilevel modulations. In this case, a dual mode algorithm is proposed. Dual mode equalization techniques are commonly used in communication systems working with multilevel signals. Practical blind algorithms for multilevel modulation are able to open the eye of the constellation, but they usually exhibit a high residual error. In a dual mode scheme, once the eye is opened by the blind algorithm, the system switches to another algorithm, which is able to obtain a lower residual error under a suitable initial ISI level. Simulation experiments show that the performance of blind per tone equalization using support vector machine has better than blind per tone equalization using CMA and MMA, from viewpoint of average Bit-Error Rate (BER). Manuscript profile -
Open Access Article
5 - Facial Expression Recognition Using Texture Description of Displacement Image
Hamid Sadeghi Abolghasem Asadollah Raie Mohammad Reza MohammadiIn recent years, facial expression recognition, as an interesting problem in computer vision has been performed by means of static and dynamic methods. Dynamic information plays an important role in recognizing facial expression. However, using the entire dynamic inform MoreIn recent years, facial expression recognition, as an interesting problem in computer vision has been performed by means of static and dynamic methods. Dynamic information plays an important role in recognizing facial expression. However, using the entire dynamic information in the expression image sequences is of higher computational cost compared to the static methods. To reduce the computational cost, instead of entire image sequence, only neutral and emotional faces can be employed. In the previous research, this idea was used by means of DLBPHS method in which facial important small displacements were vanished by subtracting LBP features of neutral and emotional face images. In this paper, a novel approach is proposed to utilize two face images. In the proposed method, the face component displacements are highlighted by subtracting neutral image from emotional image; then, LBP features are extracted from the difference image. The proposed method is evaluated on standard databases and the results show a significant accuracy improvement compared to DLBPHS. Manuscript profile -
Open Access Article
6 - Online Signature Verification: a Robust Approach for Persian Signatures
Mohamamd Esmaeel Yahyatabar Yasser Baleghi Mohammad Reza Karami-MollaeiIn this paper, the specific trait of Persian signatures is applied to signature verification. Efficient features, which can discriminate among Persian signatures, are investigated in this approach. Persian signatures, in comparison with other languages signatures, have MoreIn this paper, the specific trait of Persian signatures is applied to signature verification. Efficient features, which can discriminate among Persian signatures, are investigated in this approach. Persian signatures, in comparison with other languages signatures, have more curvature and end in a specific style. Usually, Persian signatures have special characteristics, in terms of speed, acceleration and pen pressure, during drawing curves. An experiment has been designed to determine the function indicating the most robust features of Persian signatures. Results obtained from this experiment are then used in feature extraction stage. To improve the performance of verification, a combination of shape based and dynamic extracted features is applied to Persian signature verification. To classify these signatures, Support Vector Machine (SVM) is applied. The proposed method is examined on two common Persian datasets, the new proposed Persian dataset in this paper (Noshirvani Dynamic Signature Dataset) and an international dataset (SVC2004). For three Persian datasets EER value are equal to 3, 3.93, 4.79, while for SVC2004 the EER value is 4.43. Manuscript profile -
Open Access Article
7 - Automatic Facial Emotion Recognition Method Based on Eye Region Changes
Mina Navraan charkari charkari Muharram MansoorizadehEmotion is expressed via facial muscle movements, speech, body and hand gestures, and various biological signals like heart beating. However, the most natural way that humans display emotion is facial expression. Facial expression recognition is a great challenge in the MoreEmotion is expressed via facial muscle movements, speech, body and hand gestures, and various biological signals like heart beating. However, the most natural way that humans display emotion is facial expression. Facial expression recognition is a great challenge in the area of computer vision for the last two decades. This paper focuses on facial expression to identify seven universal human emotions i.e. anger, disgust, fear, happiness, sadness, surprise, and neu7tral. Unlike the majority of other approaches which use the whole face or interested regions of face, we restrict our facial emotion recognition (FER) method to analyze human emotional states based on eye region changes. The reason of using this region is that eye region is one of the most informative regions to represent facial expression. Furthermore, it leads to lower feature dimension as well as lower computational complexity. The facial expressions are described by appearance features obtained from texture encoded with Gabor filter and geometric features. The Support Vector Machine with RBF and poly-kernel functions is used for proper classification of different types of emotions. The Facial Expressions and Emotion Database (FG-Net), which contains spontaneous emotions and Cohn-Kanade(CK) Database with posed emotions have been used in experiments. The proposed method was trained on two databases separately and achieved the accuracy rate of 96.63% for spontaneous emotions recognition and 96.6% for posed expression recognition, respectively Manuscript profile -
Open Access Article
8 - Foreground-Back ground Segmentation using K-Means Clustering Algorithm and Support Vector Machine
Masoumeh Rezaei mansoureh rezaei Masoud RezaeiForeground-background image segmentation has been an important research problem. It is one of the main tasks in the field of computer vision whose purpose is detecting variations in image sequences. It provides candidate objects for further attentional selection, e.g., MoreForeground-background image segmentation has been an important research problem. It is one of the main tasks in the field of computer vision whose purpose is detecting variations in image sequences. It provides candidate objects for further attentional selection, e.g., in video surveillance. In this paper, we introduce an automatic and efficient Foreground-background segmentation. The proposed method starts with the detection of visually salient image regions with a saliency map that uses Fourier transform and a Gaussian filter. Then, each point in the maps classifies as salient or non-salient using a binary threshold. Next, a hole filling operator is applied for filling holes in the achieved image, and the area-opening method is used for removing small objects from the image. For better separation of the foreground and background, dilation and erosion operators are also used. Erosion and dilation operators are applied for shrinking and expanding the achieved region. Afterward, the foreground and background samples are achieved. Because the number of these data is large, K-means clustering is used as a sampling technique to restrict computational efforts in the region of interest. K cluster centers for each region are set for training of Support Vector Machine (SVM). SVM, as a powerful binary classifier, is used to segment the interest area from the background. The proposed method is applied on a benchmark dataset consisting of 1000 images and experimental results demonstrate the supremacy of the proposed method to some other foreground-background segmentation methods in terms of ER, VI, GCE, and PRI. Manuscript profile -
Open Access Article
9 - A Fast Algorithm for Hyperspectral Image Analysis Using SVM and Spatial Dependency
H. Ghassemian Ahmad KeshavarzRecent significant development in sensor technology makes possible Earth observational remote sensing system with unprecedented spectral resolution and data dimensionality. The value of these new sensor systems lies in their ability to acquire a nearly complete optical MoreRecent significant development in sensor technology makes possible Earth observational remote sensing system with unprecedented spectral resolution and data dimensionality. The value of these new sensor systems lies in their ability to acquire a nearly complete optical spectrum for each pixel in the scene. Such imaging spectrometry now makes possible the acquisition of data in hundreds of spectral bands simultaneously, and it is called hyperspectral images. With the limited number of training samples of hyperspectral images, the classification of these images using conventional feature extraction algorithms (PCA, ICA, PP, DBFE, DAFE and Wavelet) is considered useless. In this paper a two stages classification algorithm is proposed, by fussing the spatial and spectral information. In the first stage the classes of each pixel and its eight neighbors are identified, using a classical classification algorithm. In the second stage two primary classes of a pixel and its neighbors are compared in each node of decision tree by a SVM. The proposed, binary tree SVM, takes advantage of both the efficient computation of the tree architecture and the high classification accuracy of SVM. The hyperspectral data set used in our experiments is a scene from Indiana’s Indian Pine by the AVIRIS sensor. The examples results show the problem of limited training samples can be mitigated using the proposed algorithm; moreover the computational time is significantly reduced. This suggests that binary tree SVM could be a promising tool for classifying hyperspectral images. Manuscript profile -
Open Access Article
10 - Blind Modulation Recognition of Communication Signals Based on Support Vector Machines
S. Shaerbaf M. Khademi Mohammad MolaviAutomatic modulation type classifier is a system which recognizes the modulation type of received signal automatically from some possible, pre-assumed types. Automatic modulation classification has applications such as spectrum surveillance, signal confirmation, interfe MoreAutomatic modulation type classifier is a system which recognizes the modulation type of received signal automatically from some possible, pre-assumed types. Automatic modulation classification has applications such as spectrum surveillance, signal confirmation, interference identification, software radio, etc. This paper, proposes a new method for recognition of 9 famous digital and analog modulations, which no need for prior knowledge of the signal to be recognized. This system is used to separate AM, FM, DSB and SSB in Analog modulations and 2ASK, 2PSK, 2FSK, 4PAM and 16QAM in digital modulations. Support Vector Machines (SVM) is used to classify these modulations and Genetic Algorithm is used to optimize Classifier Structure. Simulation results show that proposed algorithms have a good performance in comparison with other algorithms. Computational simplicity, High training speed and High classification rate, are the advantages of proposed algorithms. Manuscript profile -
Open Access Article
11 - Performance Improvement of the Traditional SVM-Based Face Detection Method
M. Roohi G. Mirjalily M. T. SadeghiIn this paper, we propose some ideas to improve the performance of the traditional face detection based on support vector machine (SVM). The traditional SVM-based system for face detection detects faces by exhaustively scanning an image for face-like patterns at any pos MoreIn this paper, we propose some ideas to improve the performance of the traditional face detection based on support vector machine (SVM). The traditional SVM-based system for face detection detects faces by exhaustively scanning an image for face-like patterns at any possible scales. It divides the original image into overlapping sub-images by using a fixed-size cutting window and classifies them using the Support Vector Machine to determine the appropriate class (face or non-face). This approach has not an acceptable detection rate. In this paper to improve the performance, we use cutting windows with different sizes. We fuse the decisions obtained by using different windows. An important issue in the Support Vector Machine classifier is to shift the decision threshold adequately towards the better represented class. In this paper, a novel method is proposed for determining the threshold value adaptively. A post processing algorithm is also presented for reducing the false alarm rate. Experimental results using standard database show that the performance of the proposed SVM-based method is much better than the basic SVM classifier. Manuscript profile -
Open Access Article
12 - Improvement of GMM Model Using PSK for Spoken Language Recognition Systems
F. Ghasemian M. M. HomayounpourGaussian Mixture Model (GMM) is a simple and effective method for statistical modeling of the feature space which is widely used in spoken language recognition systems and EM algorithm is used for training the parameters of this model. In this paper, considering the wea MoreGaussian Mixture Model (GMM) is a simple and effective method for statistical modeling of the feature space which is widely used in spoken language recognition systems and EM algorithm is used for training the parameters of this model. In this paper, considering the weakness of GMM models, a new model named PAW-GMM is proposed. In this model, the power of each component of GMM in discriminating one language from the others is considered for determining the weights of components. Since PAW-GMM considers the discriminating property of GMM components, it could increase the accuracy of language recognition systems. Also one of the problems of GMM-PSK-SVM which is one of the best GMM models is the high complexity especially for high number of languages. Therefore UBM-PSK-SVM is proposed that has the same accuracy as GMM-PSK-SVM but lower complexity. Experiments on four languages of OGI corpus show the efficiency of the proposed techniques. Manuscript profile -
Open Access Article
13 - Select the Optimal Subset of LABP Features Based on CLA-EC Method in Face Recognition System
A. Hazrati Bishak K. Faez H. Barghi Jond S. GhateiIn this paper, we present a new efficient method based on local binary pattern descriptor, for face recognition. Because, the calculations in Local binary pattern are done between two pixels values, so, small changes in the binary pattern affect its performance. In this MoreIn this paper, we present a new efficient method based on local binary pattern descriptor, for face recognition. Because, the calculations in Local binary pattern are done between two pixels values, so, small changes in the binary pattern affect its performance. In this paper, a new local average binary pattern descriptor is presented based on cellular learning automata and evolutionary computation (CLA-EC). In the proposed method, first, the LABP operator are used to extract uniform local binary patterns from face images; it should be noted that, in LABP operator to obtain more robust feature representation, many sample points has been used. Then, the best subset of patterns found by CLA-EC methods, and the histogram of these patterns is obtained. Finally, support vector machine is used for classification. The results of experiment on FERET data base show the advantage of the proposed algorithm compared to other algorithms. Manuscript profile -
Open Access Article
14 - Using Context Dependent Information for Discriminative Spoken Term Detection
S. Tabibian Ahmad Akbari B. NasersharifSpoken Term Detection (STD) approaches can be divided into two main groups: Hidden Markov Model (HMM)-based and Discriminative STD (DSTD) approaches. One of the important advantages of HMM-based methods is that they can use context dependent (diphone or triphones) infor MoreSpoken Term Detection (STD) approaches can be divided into two main groups: Hidden Markov Model (HMM)-based and Discriminative STD (DSTD) approaches. One of the important advantages of HMM-based methods is that they can use context dependent (diphone or triphones) information to improve the whole STD system performance. On the other hand, lack of triphones information is one of the significant drawbacks of DSTD methods. In this paper, we propose a solution to overcome this drawback of DSTD systems. To this end, we modify the feature extraction part of an Evolutionary DSTD (EDSTD) system to consider triphones information. At first, we propose a monophone-based feature extraction part for the EDSTD system. Then, we propose an approach for exploiting triphones information in the EDSTD system. The results on TIMIT database indicate that the true detection rate of the triphone-based EDSTD (Tph-EDSTD) system, in false alarm per keyword per hour greater than two, is about 3% higher than that of the monophone-based EDSTD (Mph-SDSTD) system. This improvement costs about 36% degradation of the system response speed which is neglected. Manuscript profile -
Open Access Article
15 - Automatic Detection of Grand-Mal Epileptic Seizure and Recognizing Normal Activities in Video by a Combination of Machine Vision and Machine Learning Techniques
A. Hakimi Rad N. Moghadam CharkariThe most relevant method to detect epileptic seizures is the electroencephalogram (EEG) based signal processing method which, due to the need for installing some electrodes on different places of the person's head, causes many movement problems. The aim of this research MoreThe most relevant method to detect epileptic seizures is the electroencephalogram (EEG) based signal processing method which, due to the need for installing some electrodes on different places of the person's head, causes many movement problems. The aim of this research is to automatically and intelligently detect grand-mal epileptic seizures and also to recognize normal activities of a person suffering from the disease by video surveillance. In this paper we have used the combination of machine vision and machine learning techniques to automatically detect grand-mal epileptic seizure when the person is lying on the ground or on the bed. After subtracting the background from video frame sequences and extracting the image silhouette, appropriate geometrical features have been extracted and fed to the multi-class support vector machine as the input for automatically classifying the videos and assigning proper activity label. All the implementations have been done on MATLAB R2011a. In this intelligent system the accuracy of detecting and recognizing activities is 90.21%. Using this system in addition to reducing the number of human observers is very helpful for the on time and constant detection of the condition. The need for just a conventional video camera and a computer system makes it affordable for people with different incomes. Because it needs not to be in contact with the person's body, there is no movement problem too. High accuracy verifies the optimal performance of the system. Manuscript profile -
Open Access Article
16 - Semi-Supervised Self-Training Classification Based on Neighborhood Construction
mona emadi jafar tanha Mohammadebrahim Shiri Mehdi Hosseinzadeh AghdamUsing the unlabeled data in the semi-supervised learning can significantly improve the accuracy of supervised classification. But in some cases, it may dramatically reduce the accuracy of the classification. The reason of such degradation is incorrect labeling of unlabe MoreUsing the unlabeled data in the semi-supervised learning can significantly improve the accuracy of supervised classification. But in some cases, it may dramatically reduce the accuracy of the classification. The reason of such degradation is incorrect labeling of unlabeled data. In this article, we propose the method for high confidence labeling of unlabeled data. The base classifier in the proposed algorithm is the support vector machine. In this method, the labeling is performed only on the set of the unlabeled data that is closer to the decision boundary from the threshold. This data is called informative data. the adding informative data to the training set has a great effect to achieve the optimal decision boundary if the predicted label is correctly. The Epsilon- neighborhood Algorithm (DBSCAN) is used to discover the labeling structure in the data space. The comparative experiments on the UCI dataset show that the proposed method outperforms than some of the previous work to achieve greater accuracy of the self-training semi-supervised classification. Manuscript profile -
Open Access Article
17 - Fear Recognition Using Early Biologically Inspired Features Model
Elham AskariFacial expressions determine the inner emotional states of people. Different emotional states such as anger, fear, happiness, etc. can be recognized on people's faces. One of the most important emotional states is the state of fear because it is used to diagnose many di MoreFacial expressions determine the inner emotional states of people. Different emotional states such as anger, fear, happiness, etc. can be recognized on people's faces. One of the most important emotional states is the state of fear because it is used to diagnose many diseases such as panic syndrome, post-traumatic stress disorder, etc. The face is one of the biometrics that has been proposed to detect fear because it contains small features that increase the recognition rate. In this paper, a biological model inspired an early biological model is proposed to extract effective features for optimal fear detection. This model is inspired by the model of the brain and nervous system involved with the human brain, so it shows a similar function compare to brain. In this model, four computational layers were used. In the first layer, the input images will be pyramidal in six scales from large to small. Then the whole pyramid entered the next layer and Gabor filter was applied for each image and the results entered the next layer. In the third layer, a later reduction in feature extraction is performed. In the last layer, normalization will be done on the images. Finally, the outputs of the model are given to the svm classifier to perform the recognition operation. Experiments will be performed on JAFFE database images. In the experimental results, it can be seen that the proposed model shows better performance compared to other competing models such as BEL and Naive Bayes model with recognition accuracy, precision and recall of 99.33%, 99.71% and 99.5%, respectively Manuscript profile -
Open Access Article
18 - Detection and Analysis of Acoustic Signals of Power Transformers On-Load Tap Changers for Assessment of Their Faults
adel younesi Abbas Ghayebloo Hasanreza Mirzaei<p><span style="font-size: 10.0pt; font-family: 'Times New Roman',serif; mso-fareast-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;">On load tap changers are very important equipment of the power transfor More<p><span style="font-size: 10.0pt; font-family: 'Times New Roman',serif; mso-fareast-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;">On load tap changers are very important equipment of the power transformers. Due to the strongly mechanical movements and high-energy arcs, this equipment has a much higher failure rate with respect to other internal transformer equipment. Online and accurate evaluation of well operation of these equipment by indicators with no interfere on the normal operation of the transformer, is very important issue. In this paper, various faults detecting methods in the tap changer have been discussed an investigated by some extracted features of acoustic signals. These signals have been captured experimentally in various tap changing periods by an accelerometer sensor mounted on a power transformer body. In this paper, in addition to common features, two new feathers entitled time and frequency indicators have been introduced. Finally, for selecting the proper features to faults detection and proposing an effective classification method, some available experimental data were randomly defected by results in the references, and classified successfully as healthy and defective data by support vector machine (SVM) method.</span></p> Manuscript profile
Rimag
Rimag is an integrated platform to accomplish all scientific journal requirements such as submission, evaluation, reviewing, editing, DOI assignment and publishing in the web.
Links
Related Centers
Technical Support
Official pages
The rights to this website are owned by the Raimag Press Management System.
Copyright © 2017-2024