Adaptive Neuro Particle Swarm Optimization applied for diagnosing disorders

TL;DR

This paper introduces an Adaptive Neuro Particle Swarm Optimization method combined with a fuzzy inference system for diagnosing disorders, achieving faster, more accurate diagnoses through adaptive control parameters and optimized model tuning.

Contribution

It presents a novel adaptive PSO approach integrated with fuzzy inference for disease diagnosis, enhancing search efficiency and diagnostic accuracy over traditional methods.

Findings

Faster convergence rate compared to traditional methods

Higher diagnosis accuracy on liver disorders dataset

Effective optimization of inference system parameters

Abstract

A new Adaptive Neuro Particle Swarm Optimization (ANPSO) combined with a fuzzy inference system for diagnosing disorders is presented in this paper. The main contributions of the novel proposed method can be a global search across the whole search space with faster convergence rate. Moreover, it shows a better exploration and exploitation by applying the adaptive control parameters, automatic control of inertia weight and coefficient of personal and social behaviours. Utilizing such attributes lead to a fast and smart diagnosis mechanism which is able to diagnosis the diseases by the high accuracy. The ANPSO is associated with tuning the characteristics of the inference system to achieve the minimum diagnosis error as far as the optimized model is obtained. As a case study, we use liver disorders dataset called Bupa. According to the preliminary ramifications, the suggested adaptive PSO performance can overcome the traditional inference system and combined with other optimization methods substantially.