Opposition-based starfish optimization algorithm for function optimization

This paper proposes a novel hybrid optimization algorithm, termed the opposition-based starfish optimization algorithm (OB-SFOA), designed for solving complex function optimization problems. By integrating the opposition-based learning (OBL) mechanism into the standard starfish optimization algorithm (SFOA), the proposed method aims to enhance population diversity, improve convergence speed, and reduce the risk of stagnation in local optima. The performance of OB-SFOA is evaluated using six widely used benchmark functions (Rosenbrock, Step, Schwefel, Penalized, Kowalik, and Shekel 5) covering diverse optimization characteristics including unimodality, multimodality, and fixed dimensionality. Comparative evaluations were conducted against standard SFOA, grey wolf optimizer (GWO), and RIME (an emerging physics-based algorithm). Results indicate that OB-SFOA consistently outperforms the competing algorithms in terms of average fitness, stability, and best-found solutions across all benchmark cases. These outcomes demonstrate the robustness and effectiveness of OB-SFOA as a promising candidate for general-purpose function optimization tasks.