The Experts below are selected from a list of 21126 Experts worldwide ranked by ideXlab platform
P. Marikkannu - One of the best experts on this subject based on the ideXlab platform.
-
Research Article Hybrid RGSA and Support Vector Machine Framework for Three-Dimensional Magnetic Resonance Brain Tumor Classification
2016Co-Authors: Rajesh R. Sharma, P. MarikkannuAbstract:Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. A novel hybrid approach for the identification of brain regions using magnetic resonance images accountable for brain tumor is presented in this paper. Classification of medical images is substantial in both clinical and research areas. Magnetic resonance imaging (MRI)modality outperforms towards diagnosing brain abnormalities like brain tumor,multiple sclerosis, hemorrhage, and manymore.The primary objective of this work is to propose a three-dimensional (3D) novel brain tumor classificationmodel using MRI images with bothmicro- andmacroscale textures designed to differentiate theMRI of brain under two classes of lesion, benign and malignant. The design approach was initially preprocessed using 3D Gaussian filter. Based on VOI (volume of interest) of the image, featureswere extracted using 3Dvolumetric SquareCentroid LinesGray LevelDistributionMethod (SCLGM) alongwith 3D run length and cooccurrence matrix. The optimal features are selected using the proposed refined gravitational search algorithm (RGSA). Support vector machines, over Backpropagation Network, an
-
Hybrid RGSA and Support Vector Machine Framework for Three-Dimensional Magnetic Resonance Brain Tumor Classification
Hindawi Limited, 2015Co-Authors: Rajesh R. Sharma, P. MarikkannuAbstract:A novel hybrid approach for the identification of brain regions using magnetic resonance images accountable for brain tumor is presented in this paper. Classification of medical images is substantial in both clinical and research areas. Magnetic resonance imaging (MRI) modality outperforms towards diagnosing brain abnormalities like brain tumor, multiple sclerosis, hemorrhage, and many more. The primary objective of this work is to propose a three-dimensional (3D) novel brain tumor classification model using MRI images with both micro- and macroscale textures designed to differentiate the MRI of brain under two classes of lesion, benign and malignant. The design approach was initially preprocessed using 3D Gaussian filter. Based on VOI (volume of interest) of the image, features were extracted using 3D volumetric Square Centroid Lines Gray Level Distribution Method (SCLGM) along with 3D run length and cooccurrence matrix. The optimal features are selected using the proposed refined gravitational search algorithm (RGSA). Support vector machines, over Backpropagation Network, and k-nearest neighbor are used to evaluate the goodness of classifier approach. The preliminary evaluation of the system is performed using 320 real-time brain MRI images. The system is trained and tested by using a leave-one-case-out method. The performance of the classifier is tested using the receiver operating characteristic curve of 0.986 (±002). The experimental results demonstrate the systematic and efficient feature extraction and feature selection algorithm to the performance of state-of-the-art feature classification methods
Rajesh R. Sharma - One of the best experts on this subject based on the ideXlab platform.
-
Research Article Hybrid RGSA and Support Vector Machine Framework for Three-Dimensional Magnetic Resonance Brain Tumor Classification
2016Co-Authors: Rajesh R. Sharma, P. MarikkannuAbstract:Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. A novel hybrid approach for the identification of brain regions using magnetic resonance images accountable for brain tumor is presented in this paper. Classification of medical images is substantial in both clinical and research areas. Magnetic resonance imaging (MRI)modality outperforms towards diagnosing brain abnormalities like brain tumor,multiple sclerosis, hemorrhage, and manymore.The primary objective of this work is to propose a three-dimensional (3D) novel brain tumor classificationmodel using MRI images with bothmicro- andmacroscale textures designed to differentiate theMRI of brain under two classes of lesion, benign and malignant. The design approach was initially preprocessed using 3D Gaussian filter. Based on VOI (volume of interest) of the image, featureswere extracted using 3Dvolumetric SquareCentroid LinesGray LevelDistributionMethod (SCLGM) alongwith 3D run length and cooccurrence matrix. The optimal features are selected using the proposed refined gravitational search algorithm (RGSA). Support vector machines, over Backpropagation Network, an
-
Hybrid RGSA and Support Vector Machine Framework for Three-Dimensional Magnetic Resonance Brain Tumor Classification
Hindawi Limited, 2015Co-Authors: Rajesh R. Sharma, P. MarikkannuAbstract:A novel hybrid approach for the identification of brain regions using magnetic resonance images accountable for brain tumor is presented in this paper. Classification of medical images is substantial in both clinical and research areas. Magnetic resonance imaging (MRI) modality outperforms towards diagnosing brain abnormalities like brain tumor, multiple sclerosis, hemorrhage, and many more. The primary objective of this work is to propose a three-dimensional (3D) novel brain tumor classification model using MRI images with both micro- and macroscale textures designed to differentiate the MRI of brain under two classes of lesion, benign and malignant. The design approach was initially preprocessed using 3D Gaussian filter. Based on VOI (volume of interest) of the image, features were extracted using 3D volumetric Square Centroid Lines Gray Level Distribution Method (SCLGM) along with 3D run length and cooccurrence matrix. The optimal features are selected using the proposed refined gravitational search algorithm (RGSA). Support vector machines, over Backpropagation Network, and k-nearest neighbor are used to evaluate the goodness of classifier approach. The preliminary evaluation of the system is performed using 320 real-time brain MRI images. The system is trained and tested by using a leave-one-case-out method. The performance of the classifier is tested using the receiver operating characteristic curve of 0.986 (±002). The experimental results demonstrate the systematic and efficient feature extraction and feature selection algorithm to the performance of state-of-the-art feature classification methods
Sebastian Verhelst - One of the best experts on this subject based on the ideXlab platform.
-
prediction of the cetane number of biodiesel using artificial neural Networks and multiple linear regression
Energy Conversion and Management, 2013Co-Authors: Ramon Pilotorodriguez, Yisel Sanchezborroto, Magin Lapuerta, Leonardo Goyosperez, Sebastian VerhelstAbstract:Abstract Models for estimation of cetane number of biodiesel from their fatty acid methyl ester composition using multiple linear regression and artificial neural Networks were obtained in this work. For the obtaining of models to predict the cetane number, an experimental data from literature reports that covers 48 and 15 biodiesels in the modeling-training step and validation step respectively were taken. Twenty-four neural Networks using two topologies and different algorithms for the second training step were evaluated. The model obtained using multiple regression was compared with two other models from literature and it was able to predict cetane number with 89% of accuracy, observing one outlier. A model to predict cetane number using artificial neural Network was obtained with better accuracy than 92% except one outlier. The best neural Network to predict the cetane number was a Backpropagation Network (11:5:1) using the Levenberg–Marquardt algorithm for the second step of the Networks training and showing R = 0.9544 for the validation data.
Soheil Aber - One of the best experts on this subject based on the ideXlab platform.
-
removal of cr vi from polluted solutions by electrocoagulation modeling of experimental results using artificial neural Network
Journal of Hazardous Materials, 2009Co-Authors: Soheil Aber, Ali Reza Amanighadim, V MirzajaniAbstract:Abstract In the present work, the removal of Cr(VI) from synthetic and real wastewater using electrocoagulation (EC) process was studied. The influence of anode material, initial Cr(VI) concentration, initial pH of solution, type of electrolyte, current density and time of electrolysis was investigated. During 30 min of electrocoagulation, maximum removal efficiencies achieved by Al and Fe anodes were 0.15 and 0.98, respectively. High removal efficiency was achieved over pH range of 5–8. NaCl, Na 2 SO 4 and NaNO 3 were used as supporting electrolyte during the electrolysis. NaCl was more effective than Na 2 SO 4 and NaNO 3 in removal of hexavalent chromium. Also in this work, a real electroplating wastewater containing 17.1 mg/l Cr(VI) was treated successfully using EC process. Artificial neural Network (ANN) was utilized for modeling of experimental results. The model was developed using a 3-layer feed forward Backpropagation Network with 4, 10 and 1 neurons in first, second and third layers, respectively. A comparison between the model results and experimental data gave high correlation coefficient ( R 2 = 0.976) shows that the model is able to predict the concentration of residual Cr(VI) in the solution.
-
study of acid orange 7 removal from aqueous solutions by powdered activated carbon and modeling of experimental results by artificial neural Network
Desalination, 2007Co-Authors: Soheil Aber, N Daneshvar, Saeed Mohammad Soroureddin, Ammar Chabok, Karim AsadpourzeynaliAbstract:Abstract In this work, removal of acid orange 7 (AO7) by powdered activated carbon, from aqueous solutions with initial concentrations of 150 ppm to 350 ppm and initial pH values of 2.8, 5.8, 8.0 and 10.5 at 25°C was studied. Experiments were done in batch mode and the experimental solutions were agitated periodically. All concentrations were measured spectrophotometrically at 483 nm and three times replicated. In most cases, after 75 min contact time, the most of AO7 removal is performed. The maximum equilibrium removal of acid orange 7 (AO7) was 96.24% for its initial concentration of 150 ppm at pHi = 2.8, and minimum equilibrium removal was 48.05% for initial concentration of 350 ppm at pHi = 5.8. At the similar experimental conditions, application of different initial pH values altered the AO7 removal percent no more than 9.06%. It is found that the adsorption system follows the second-order adsorption rate expression and the constants of the rate expression at different conditions were calculated which are comparable and often higher than other adsorbents in adsorption of other dyes. The constants of Langmuir equation, Q and b, and constants of Freundlich equation, Kf and 1/n, were calculated and results show that the adsorption process is favorable. Comparison of R2 values shows that fitting of Freundlich equation to experimental data is better than Langmuir equation. The experimental results were also modeled by artificial neural Network with mean relative error of 5.81%. This model was developed in Matlab 6.5 environment using a 3-layer feed forward Backpropagation Network with 3, 2 and 1 neurons in first, second and third layers, respectively.
Jose De Jesus Rubio - One of the best experts on this subject based on the ideXlab platform.
-
modified optimal control with a Backpropagation Network for robotic arms
Iet Control Theory and Applications, 2012Co-Authors: Jose De Jesus RubioAbstract:In this study, the trajectory tracking problem of robotic arms is considered. To solve this problem, two novel modified optimal controllers based on neural Networks are proposed. The uniform stability of both the tracking error and approximation error for the aforementioned controllers is guaranteed by means of a Lyapunov-like analysis. The effectiveness of the proposed controllers is verified by simulations.
