New hybrid Particle Swarm and Dragonfly Algorithm for features selection

Abstract

We are nowadays obligated to deal with rich datasets with exceptionally high dimensions due to big data and IoT. Therefore, a technique known as feature selection (FS) is employed to carry out any machine learning activity or get insights from such dimensions data. One of the most fundamental issues in the analysis of high-dimensional data is feature selection. In this work, we suggest a new approach to the problem of feature selection, which involves selecting a subset of pertinent features for the research topic from a wide number of attributes. To tackle the FS problem, a new bio-inspired algorithm called PSODA is developed in this study, and a novel approach is suggested to maintain a balance between the capacities for exploration and exploitation. The Dragonfly Technique (DA) and the particle swarm optimization (PSO) approach were combined to create the suggested algorithm. Over the most popular datasets in literature, the proposed approach was adequately compared to other algorithms. The outcomes show how PSODA outperforms all other algorithms.