-
Open Access Article
1 - Classifier Ensemble Framework: a Diversity Based Approach
Hamid Parvin Hosein Alizadeh Mohsen Moshki -
Open Access Article
2 - Offline Auto-Tuning of a PID Controller Using Extended Classifier System (XCS) Algorithm
Ehsan Abbasi Nader Naghavi -
Open Access Article
3 - Predict the trend of stock prices using XCS based on genetic algorithms and reinforcement learning
Ahmad Reza PakraeiDevelopments for investigation in the area of artificial intelligence and machine learning, especially in the field of evolutionary computation not only enabled us for having more effective analysis of data, but also providing the ability to use it for under MoreDevelopments for investigation in the area of artificial intelligence and machine learning, especially in the field of evolutionary computation not only enabled us for having more effective analysis of data, but also providing the ability to use it for understanding any underlying model of financial markets. Economists, statisticians, and finance teachers were always interested in the development and experiment of stock price behavioral models. XCS is a compound system of genetic algorithm and reinforcement learning, which has on-line interaction with the environment and the ability of learning from its own experience. In this study we will provide a model which predicts the movements of next day‘s stock price on one of the corporations in Tehran stock exchange based on historical data and different technical indicators by using XCS. Then, efficiency of the proposed model was measured in comparison with the random walk model. Results showed that the proposed model has more predicting accuracy in comparison with that random walk model Manuscript profile -
Open Access Article
4 - Tree Cover detection through Maxlike Classification of Land sat ETM + Images of the Year 2001 in Golestan Province
Aborasoul Salman Mahini Azadeh Nadali Jahangir Feghhi Borhan RiaziSparse vegetation gives rise to increased overland water flow، soil erosion، water pollution and decreased soil fertility. Golestan Province has witnessed a relatively extensive forest clearing during recent years causing intensified flooding. We used ETM+ land sat imag MoreSparse vegetation gives rise to increased overland water flow، soil erosion، water pollution and decreased soil fertility. Golestan Province has witnessed a relatively extensive forest clearing during recent years causing intensified flooding. We used ETM+ land sat imagery to classify forest cover of the Golestan Province using Max like classification and assessed its accuracy. Land uses and land covers were distinguished on the color composite images of the area and used as training sites for image classification that included all six bands of the imagery. We also used an ISO-Cluster unsupervised classification to derive 100 clusters for purifying initial training sites. Accuracy assessment was implemented through test set pixels that were randomized and set aside from the training set pixels. We also used a LISS III imagery to assess the accuracy of the classification. Our assessment proved the classification to be of high accuracy. Manuscript profile -
Open Access Article
5 - Tree Cover detection through Maxlike Classification of Land sat ETM + Images of the Year 2001 in Golestan Province
Abdorrasoul Salman Mahini Azade Nadali Jahangir i Feghhi Borhan RiyaziSparse vegetation gives rise to increased overland water flow, soil erosion, water pollution and decreased soil fertility. Golestan Province has witnessed a relatively extensive forest clearing during recent years causing intensified flooding. We used ETM+ land sa MoreSparse vegetation gives rise to increased overland water flow, soil erosion, water pollution and decreased soil fertility. Golestan Province has witnessed a relatively extensive forest clearing during recent years causing intensified flooding. We used ETM+ land sat imagery to classify forest cover of the Golestan Province using Max like classification and assessed its accuracy. Land uses and land covers were distinguished on the color composite images of the area and used as training sites for image classification that included all six bands of the imagery. We also used an ISO-Cluster unsupervised classification to derive 100 clusters for purifying initial training sites. Accuracy assessment was implemented through test set pixels that were randomized and set aside from the training set pixels. We also used a LISS III imagery to assess the accuracy of the classification. Our assessment proved the classification to be of high accuracy. Manuscript profile -
Open Access Article
6 - An Ensemble Classifier Method for Breast Cancer Detection Using Genetic Algorithm and Multistage Adjustment of Weights in the MLP Neural Network
Amin Rezaeipanah S. J. Mirabedini ali mobarakiToday, with the increasing spread of science, the use of decision support systems can be of great help in the therapeutic policies of the Doctor. For this purpose, the use of artificial intelligence systems in predicting and diagnosing breast cancer, which is one of the MoreToday, with the increasing spread of science, the use of decision support systems can be of great help in the therapeutic policies of the Doctor. For this purpose, the use of artificial intelligence systems in predicting and diagnosing breast cancer, which is one of the most common cancers among women, is being considered. In this study, the process of diagnosis of breast cancer is done by using multistage weights in the MLP neural network in two layers. In the first layer, the three classifiers are trained simultaneously on the learning set data. Upon completion of the training, the output of the classifier of the first layer is accumulated together with the learning set data in the new sets. This set is given as an input to the second layer superconductor, and the supra-class mapping maps between the outputs of each of the ordinary classifiers of the first layer with the actual output classes. The three-layer structure of the first layer, as well as the second-layer supraclavicle, is a MLP neural network that optimizes the weights, effective properties and the size of the hidden layer simultaneously using an innovative genetic algorithm. In order to evaluate the accuracy of the proposed model, the Wisconsin database is used, which was created by the FNA test. Experiment results on the WBCD dataset the accuracy is 98.72% for the proposed method, which is relative to GAANN, CAFS algorithms provide better performance. Manuscript profile -
Open Access Article
7 - Optimal Prediction in the Diagnosis of Existing Heart Diseases using Machine Learning: Outlier Data Strategies
Omid Rahmani Seyyed Amir Mahdi Ghoreishi Zadeh Mostafa Setak -
Open Access Article
8 - Identification of Attention Deficit Hyperactivity Disorder Patients Using Wavelet-Based Features of EEG Signals
Sahar Karimi Shahraki Mahdi KhezriAttention Deficit Hyperactivity Disorder (ADHD) is a neurological and psychiatric disorder which causes to attention deficit, anxiety, hyperactivity and impulsive behaviors. ADHD is more common in children and directly leads to their learning disability. The aim of this MoreAttention Deficit Hyperactivity Disorder (ADHD) is a neurological and psychiatric disorder which causes to attention deficit, anxiety, hyperactivity and impulsive behaviors. ADHD is more common in children and directly leads to their learning disability. The aim of this study was to accurately identify ADHD patients by using wavelet-based features of brain signals (EEG). Recorded EEG signals from 61 children with ADHD (diagnosed according to the DSM-IV criteria) and 60 healthy controls in the age range of 7-12 years were used to design the system. In the proposed method by applying wavelet transform, EEG signals were decomposed into subbands; for the time version of the signals in each subband, the temporal and statistical features were calculated. The reduced feature set by principal component analysis (PCA) method was then used to train the classification unit to identify ADHD patients from healthy individuals. To obtain the desired results, different types of wavelet functions and decomposition levels were investigated. The bior3.1 wavelet function with the support vector machine (SVM) classifier and the rbio1.1 wavelet function with the k-nearest neighbor (kNN) classifier presented the best performance with the recognition accuracy of 98.33% and 99.17%, respectively. The SVM classification method with radial basis kernel function (RBF) and the kNN method with the number of nearest neighbors, k = 3 obtained the best results.The results obtained in this study compared to the results reported in previous studies showed at least a 2% improvement in the recognition accuracy of ADHD patients. Manuscript profile -
Open Access Article
9 - Stress Detection Based on Fusion of Multimodal Physiological signals using Dempster-Shafer Evidence Theory
Sara Majlesi Mahdi KhezriDetecting and controlling stress levels in drivers is especially important to reduce the potential risks while driving. Accordingly, in this study, a detection system was presented to identify four levels of stress (low, neutral, high and very high) in drivers based on MoreDetecting and controlling stress levels in drivers is especially important to reduce the potential risks while driving. Accordingly, in this study, a detection system was presented to identify four levels of stress (low, neutral, high and very high) in drivers based on physiological signals. The proposed method used the drivedb database, which includes the recording of physiological signals from 17 healthy volunteers while driving on specific routes on city streets and highways. A set of statistical and entropy features along with morphological features that were calculated only for the ECG signals, were used. The calculated features were applied as inputs to the classification units to detect stress levels. Support vector machine (SVM), k nearest neighbors (kNN) and decision tree (DT) were evaluated as classification methods. The main purpose of this study was to improve the accuracy of stress level detectionusing the idea of classifiers fusion. To achieve this goal, the combination of individual classification units, each of which used only the features of one of the ECG, EMG and GSR signals, was performed by the Demster-Shafer method. Using genetic algorithm as feature selection method, SVM classifier and Dempster-Shafer fusion strategy, the best stress detection accuracy of 96.9% was obtained. While the highest detection accuracy among individual classifiers was 75% and obtained by a subsystem that used ECG features.The results show significant performance of the proposed method compared to previous studies that used the same dataset. Manuscript profile -
Open Access Article
10 - Evaluation of Deep Neural Networks in Emotion Recognition Using Electroencephalography Signal Patterns
Azin Kermanshahian Mahdi KhezriIn this study, the design of a reliable detection system that is able to identify different emotions with the desired accuracy has been considered. To reach this goal, two different structures for the emotion recognition system include 1) using linear and non-linear fea MoreIn this study, the design of a reliable detection system that is able to identify different emotions with the desired accuracy has been considered. To reach this goal, two different structures for the emotion recognition system include 1) using linear and non-linear features of the electroencephalography (EEG) signal along with common classifiers and 2) using EEG signal in a deep learning structure is considered to identify emotional states. To design the system, the EEG signals of the DEAP database which were recorded by displaying emotional videos from 32 subjects were used. After the preparation and noise removal, linear and non-linear features such as: Skewness, Kurtosis, Hjorth parameters, Lyapunov exponent, Shannon entropy, correlation and fractal dimension and time reversibility were extracted from the alpha, beta and gamma subbands of the EEG signals. Then according to structure 1, the features were applied as input to common classifiers such as decision tree (DT), k nearest neighbor (kNN) and support vector machine (SVM). Also in structure 2, the EEG signal was considered as the input of the convoloutional neural network (CNN). The goal is to evaluate the results of deep learning networks and other methods for emotion recognition. According to the obtained results, the SVM achieved the best performance for identifying four emotional states with 94.1 % accuracy. Also, the proposed CNN identified the desired emotional states with the accuracy of 86%. Deep learning methods are superior to simple classifiers because they do not require the features of the signals and are resistant to different noises. Using a short period of time for the signals and performing near optimal preprocessing and conditioning, can further improve the results of deep neural networks. Manuscript profile -
Open Access Article
11 - Brain Stroke Classification Based on Deep Learning Approach in Microwave Brain Imaging System
Majid Roohi Jalil Mazloum Mohammad Ali Pourmina Behbod GhalamkariOne of the main reasons of death in the world, mostly affecting seniors, is brain stroke. Almost 85% of all brain strokes are ischemic due to internal bleeding in a part of the brain. Due the high mortality rate, quick diagnosic and treatment of ischemic and hemorrhagic MoreOne of the main reasons of death in the world, mostly affecting seniors, is brain stroke. Almost 85% of all brain strokes are ischemic due to internal bleeding in a part of the brain. Due the high mortality rate, quick diagnosic and treatment of ischemic and hemorrhagic strokes are of utmost importance. In this paper, to realize microwave brain imaging system, a circular array-based of modified bowtie antennas located around the multilayer head phantom with a spherical target with radius of 1 cm as intracranial hemorrhage target aresimulated in CST simulator. To obtain satisfied radiation characteristics in the desired band (from 0.5-5 GHz) an appropriate matching medium is designed. First, in the processing section, a confocal image-reconstructing method based using delay and sum (DAS) and delay, multiply and sum (DMAS) beam-forming algorithms is used. The reconstructed images generated shows the usefulness of the proposed confocal method in detecting the spherical target in the range of 1 cm. The main purpose of this paper is stroke classification using deep learning approaches. For this, an image classification algorithm is developed to estimate the stroke type from reconstructed images. By using the proposed deep learning method, the reconstructed images are classified into different categories of cerebrovascular diseases using a multiclass linear support vector machine (SVM) trained with convol­uti­onal neural networks (CNN) features extracted from the images. The simulated results show the suitability of the proposed image reconstruction method for precisely localizing bleeding targets, with 89% accuracy in 9 seconds. In addition, the proposed deep-learning approach shows good performance in terms of classification, since the system does not confuse between different classes. Manuscript profile -
Open Access Article
12 - Improving Diagnosis of Heart Disease by Analyzing Chaotic Indices of ECG Signals
Ali Tamizi Mohammad Ataei Mohammad Reza YazdchiElectrocardiogram (ECG) signals are the most popular non-invasive approach for diagnosis of heart irregularities and indications of possible heart diseases. Previous studies have shown that ECG signals do not have a linear distribution and contain a variety of non-linea MoreElectrocardiogram (ECG) signals are the most popular non-invasive approach for diagnosis of heart irregularities and indications of possible heart diseases. Previous studies have shown that ECG signals do not have a linear distribution and contain a variety of non-linear dimensions. In the present research we have treated the ECG signals as time-series data and applied chaos indices analysis. Utilizing data from MIT_BIH Database, the present study has improved the past research by analysing chaotic indices such as Lyapunov Exponent (λmax), and Correlation Dimension to ECG signal data from healthy individuals and heart patients. We present appropriate algorithms for reconstruction of Phase Space and estimations of the model parameters using Lyapunov Exponent and CorrelationDimension.We then present the results from reconstruction of Phase Space based on chaotic indices, and fuzzy classifier, to discriminate healthy individuals (NSR) from the heart patients.The heart patients include those with Arterial Fibrillation (AF) and those with Left Bundle Branch Block (LBBB). These results ascertain the effectiveness of application of chaotic distribution to ECG data in improving the heart disease diagnosis. Manuscript profile -
Open Access Article
13 - The Introduction of a Heuristic Mutation Operator to Strengthen the Discovery Component of XCS
Ahmad Reza Pakraei Kamal Mirzaie -
Open Access Article
14 - Presenting a Fast Classifier Based on Unsupervised Learning for Diagnosis Diseases
Najmeh Hosseinpour Afzal Ghaseimi -
Open Access Article
15 - Categorization of Persian Detached Handwritten Letters Using Intelligent Combinations of Classifiers
Hossein Sadr Mojdeh Nazari Solimandarabi Mahsa Mirhosseini Moghadam -
Open Access Article
16 - Improving Accuracy in Intrusion Detection Systems Using Classifier Ensemble and Clustering
Ensieh Nejati Hassan Shakeri Hassan Raei -
Open Access Article
17 - An Optimal Configuration of Neural Networks by Multi-Objective Genetic Algorithm and Ensemble-Classifier Approach for Evaluation Trust in the Single Web Service
baharak shakeri aski Abolfazl Haghighat mehran mohsenzadeh -
Open Access Article
18 - Detection of Pulmonary Nodules in CT Images Using Template Matching and Neural Classifier
Hosien Hasanabadi Mohsen Zabihi Qazaleh Mirsharif -
Open Access Article
19 - Combining Classifier Guided by Semi-Supervision
Mohammad Mohammadi Hamid Parvin Eshagh Faraji Sajad Parvin -
Open Access Article
20 - Common Spatial Pattern for Human Identification Based on Finger Vein Images in Radon space
Akram Gholami Hamid Hassanpour -
Open Access Article
21 - Presenting a New Text-Independent Speaker Verification System Based on Multi Model GMM
Mohammad Mosleh Faraz Forootan Najmeh Hosseinpour -
Open Access Article
22 - Analysis of the performance of different classifiers in solving the credit risk scoring problem with noisy and clean data
Reza Yousefi Zenouz Fatemeh Atapour Mashhad -
Open Access Article
23 - Detection of Seizure EEG Signals Based on Reconstructed Phase Space of Rhythms in EWT Domain and Genetic Algorithm
Hesam Akbari Somayeh Saraf Esmaili Sima Farzollah Zadeh -
Open Access Article
24 - Determination of the Type of The Imagined Movement of Organs in People with Mobility Disabilities Using Corrected Common Spatial Patterns
Alireza Pirasteh Manouchehr Shamseini Ghiyasvand Majid Pouladian -
Open Access Article
25 - Voltage Sag Compensation with DVR in Power Distribution System Based on Improved Cuckoo Search Tree-Fuzzy Rule Based Classifier Algorithm
Majid Aryanezhad Mahmood Joorabian Morteza Razaz -
Open Access Article
26 - Incorporation of Demand Response Programs and Wind Turbines in Optimal Scheduling of Smart Distribution Networks: A Case Study
Mehrdad Ghahramani Morteza Nazari Heris Kazem zare Behnam Mohammadi Ivatloo