Opposition Learning based Single Candidate Optimizer for Clustering Problems

Abstract

In this study, we propose a novel optimization algorithm called Opposition Learning based Single Candidate Optimization (OppSCO) by incorporating an opposition learning mechanism into the Single Candidate Optimization (SCO) algorithm. The performance of the two algorithms is evaluated on a clustering problem. The proposed OppSCO algorithm demonstrates superior convergence compared to the original SCO algorithm. Furthermore, the OppSCO algorithm is compared with classical heuristic optimization algorithms such as Genetic Algorithm (GA), Differential Evolution (DE), and Particle Swarm Optimization (PSO). The results indicate that the OppSCO algorithm outperforms the original SCO algorithm in terms of convergence and solution quality.