OPTIMIZING OF SVM FOR CT CLASSIFICATION
N. T. Renukadevi, P. Thangaraj · 2013
An automated classification of Computerized tomography (CT) images method uses Coiflet wavelets to extract features as input for the classifiers. Support Vector Machine (SVM) module is used to classify the images into different classes. Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) are used to optimize the parameters C and gamma of the RBF kernel in SVM. Parameter selection is thought of as an optimization problem where search techniques are used to maximize SVM performance. The observed results are considerably better than the results achieved by employing Support Vector Machine.