Brain Tumor Classification by EGSO Based RBFNN Classifier
Rajesh Sharma R.1, Akey Sungheetha2, Jemal Nuradis3
1Rajesh Sharma R*, Dept. of CSE, Adama Science and Technology University, Adama, Ethiopia.
2Akey Sungheetha, Dept. of CSE, Adama Science and Technology University, Adama, Ethiopia.
3Jemal Nuradis, Dept. of CSE, Adama Science and Technology University, Adama, Ethiopia.
Manuscript received on January 01, 2020. | Revised Manuscript received on January 20, 2020. | Manuscript published on January 30, 2020. | PP: 3005-3012 | Volume-8 Issue-5, January 2020. | Retrieval Number: E6073018520/2020©BEIESP | DOI: 10.35940/ijrte.E6073.018520
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Tumor classifier is modelled employing a proposed Enhanced Group Search Optimizer based Radial Basis Function Neural Network model is applied in this research contribution to acquire the ideal instances from the developed VOI instance an as well EGSO is utilized to optimize the weight values of the Radial Basis Function Network classifier by limiting the mean square mistake. The anticipated EGSO based RBFNN classifier brings better characterization precision and accomplished insignificant error with quicker process. The simulation results computed prove the effectiveness of the RBFNN classifier to be better in comparison with the other proposed classifiers in this thesis and that available in the literature. The proposed pattern evaluation technique presents an automatic cancer categorization procedure thru the ultimate facets which fantastic characterizes MRI brain image is benign and malignant cancers. The planned method may perhaps stretch to categorize exceptional classes of tumor (eg. Meningioma, glioma etc.,) and depth of malignancy.
Keywords: EGSO, GSO, k-NN, PSVM, RBFNN, SVM.
Scope of the Article: Classification.