Experimental Exploration of Evolutionary Algorithms and their Applications in Complex Problems: Genetic Algorithm and Particle Swarm Optimization Algorithm

Abstract

The primary aim of this study was to experiment and compare the empirical evidence of evolutionary algorithms and their applications using the Genetic Algorithm (GA) and Particle Swamp Optimization (PSO) algorithm. The objectives of the study included reviewing recent scholarly scientific research papers and practices, and algorithms with existing genetic algorithm techniques, identifying the need for lessons learned and leveraging best health practices garnered from the existing problems of optimization, reviewing and identifying the technological tools used in the healthcare domain, algorithms, and the effectiveness of GA and PSO techniques and to develop and analyse GA algorithms using datasets to predict and determine which of the two algorithms performs better. Evolutionary algorithms which are normally viewed as components of both evolutionary computing and bio-inspired computing use mechanisms inspired by nature and are indeed capable of solving problems through processes that emulate the behaviours of living organisms. Genetic algorithms (GAs), evolution strategies (ESs), differential evolution (DE), and particle swarm optimization (PSO) are typical examples. Therefore, evolutionary algorithms are typically used to provide good, estimated solutions to problems that cannot be solved easily using other techniques, and as such numerous optimization problems fall into this category. This work aims to provide a systematic evaluation of the literature on contemporary PSO methods for knowledge discovery in the area of illness detection. Although the major objective is to present recommendations for future enhancement and development in this field, the systematic analysis reveals the possible study topics of PSO techniques as well as the research gaps. The essential ideas, theoretical underpinnings, and traditional application domains are covered in this study. It is fervently anticipated that the findings will help researchers to thoroughly examine PSO algorithms for disease diagnosis. According to the current state of PSO strategies in healthcare, several difficulties that can be taken on to advance the sector are mentioned.