How Effective is the Salp Swarm Algorithm in Data Classification

Abstract

In this paper, the Salp Swam Algorithm (SSA) is deployed in training the Multilayer Perceptron (MLP) for the task of data classification. The UCI machine learning repository standard datasets are used for evaluation of the proposed SSA based MLP. The performance of the proposed method is verified by considering various standard classification measures over the considered benchmark datasets. The result obtained by the proposed method is compared with other evolutionary algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Differential Evolution (DE), Grey Wolf Optimization (GWO), etc. From the simulation study, it has been verified that the proposed method shows supremacy in results as compared with other evolutionary algorithm based MLP.