Scout Particle Swarm Optimization

Abstract

Particle Swarm Optimization is a robust optimization algorithm proved itself in various technical areas like training of classifiers, image classification and function optimization, etc. It simulates the foraging behaviour of bird swarms. While doing that, it uses velocity and position metrics for directing its particles to food. Concerning this, it has various advantages like high convergence, speedy process capability and a few parameters to be adjusted. But it has a significant disadvantage restricting the performance. This handicap is regeneration of the particle which couldn’t improve itself along iterations. Moreover, Artificial Bee Colony Optimization (ABC) is a valuable optimization algorithm imitating the foraging behaviour like PSO. However, ABC uses honey bees grouped as employed bees, onlooker bees and scout bees. The employed bee and onlooker bee phases do the same work with velocity and position concepts in PSO. But, scout bee phase regenerates the useless particles in order to achieve higher performance by upgrading diversity. Therefore, it’s seen that addition of scout bee phase into PSO looks like a smart idea. So, in this study, Scout PSO (ScPSO) algorithm is designed which is more effective and useful than PSO. For performance analysis of ScPSO, it was used in training of NN classifier. Furthermore, ScPSO-NN is compared with NN and PSO-NN methods on medical pattern classification. For this purpose, Wisconsin Breast Cancer-Original (WBC), Pima Indian Diabetes (PID), Heart Statlog (HS) and Bupa Liver Disorders (BLD) datasets are used and test process is realized by 10-fold cross validation method. As a result, ScPSO-NN achieves classification accuracies as 97.51% (WBC), 78.13% (PID), 86.30% (HS) and 75.07% (BLD).