The SVM Classifier Based on the Modified Particle Swarm Optimization

TL;DR

This paper introduces a modified particle swarm optimization algorithm to optimize SVM classifier parameters, improving classification quality and reducing development time through particle regeneration based on accuracy.

Contribution

The paper presents a novel PSO-based method with particle regeneration for simultaneous optimization of SVM kernel type and parameters, enhancing efficiency and accuracy.

Findings

Enhanced classification accuracy with the proposed method

Reduced development time for SVM classifiers

Experimental results confirm the algorithm's efficiency

Abstract

The problem of development of the SVM classifier based on the modified particle swarm optimization has been considered. This algorithm carries out the simultaneous search of the kernel function type, values of the kernel function parameters and value of the regularization parameter for the SVM classifier. Such SVM classifier provides the high quality of data classification. The idea of particles' {\guillemotleft}regeneration{\guillemotright} is put on the basis of the modified particle swarm optimization algorithm. At the realization of this idea, some particles change their kernel function type to the one which corresponds to the particle with the best value of the classification accuracy. The offered particle swarm optimization algorithm allows reducing the time expenditures for development of the SVM classifier. The results of experimental studies confirm the efficiency of this algorithm.