Artificial Neural Network Training Using Marine Predators Algorithm for Medical Data Classification

Abstract

The artificial neural network (ANN) is an important machine learning tool used in medical data classification for disease diagnosis. The learning algorithm in ANN training plays a crucial role in classification performance. In this paper, a recently developed swarm intelligence algorithm named as marine predators algorithm (MPA) is applied as a learning algorithm to train the ANN for classification tasks. The classification tasks are carried out on 10 well-known medical datasets. A comparative study is conducted with the classical Levenberg–Marquardt (LM) and particle swarm optimizer (PSO) algorithms. The classification results are analysed using multi-criteria decision-making (MCDM) method. The results with analysis establish that MPA outperforms other algorithms.