Usage of Particle Swarm Optimization to Improve the Performance of Supervised Classifiers

Abstract

Abstract Representing the data appropriately will have a significant effect on the outcome produced by the classifier. Transforming the feature will help to represent the data points in a more suitable way for the classifier. Particle swarm optimization belongs to the Swarm Optimization techniques category and it is generally used for solving numerical optimization problems, weight updation in neural networks, and feature selection. This research work proposes a Particle swarm optimization-based transformation technique for increasing the classification metrics of popular classification algorithms namely K-Nearest Neighbor, Stochastic Gradient Descent Classifier, Decision trees, and linear discriminant analysis classifier. Experiments are conducted using the SONAR dataset and the highest accuracy of 82.69% is attained for Stochastic Gradient Descent classifier when Particle swarm optimization is used as a transformation technique