Comparative Analysis of Meta-heuristic Algorithms for Unconstrained Optimization Problems | ||||
| Assiut University Journal of Multidisciplinary Scientific Research | ||||
| Volume 54, Issue 2, May 2025, Page 358-385 PDF (793.88 K) | ||||
| Document Type: Novel Research Articles | ||||
| DOI: 10.21608/aunj.2025.347716.1112 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
Amira A.Allam  1; Alaa M.Asklany2; Mohamed A.Tawhid3; Hassan Mohamed El-Hawary4
| ||||
| 1Mathematics, faculty of Science, Assiut university, Assiut, Egypt | ||||
| 2Department of Mathematics, Faculty of Science, Assiut University, Egypt | ||||
| 3Department of Mathematics and Statistics, Faculty of Science, Thompson Rivers University, Kamloops, Canada | ||||
| 4Mathematics Department, Faculty of Science, Assiut University, Assiut, Egypt | ||||
| Abstract | ||||
| The use of metaheuristic algorithms in optimization has recently gained significant attention from researchers, often referred to as new or novel algorithms. These algorithms aim to efficiently solve complex optimization problems by mimicking natural processes or behaviors. This study explores the implementation of several recent meta-heuristic algorithms, such as the Hippopotamus Optimization Algorithm (HO), Puma Optimizer (PO), Spider Wasp Optimizer (SWO), Mountain Gazelle Optimizer (MGO), A Sinh Cosh Optimizer (SCHO), Kepler Optimization Algorithm (KOA), and Seahorse Optimizer (SHO). A comprehensive comparison is made between these meta-heuristic approaches using a set of 23 standard test functions, including both unimodal and multimodal functions that vary in complexity. The evaluation criteria include accuracy, convergence speed, and robustness. The results indicate that the Spider Wasp Optimizer (SWO) consistently outperforms other algorithms in terms of optimization performance. Additionally, two non-parametric statistical tests, the Friedman and the Wilcoxon Signed-Rank tests, have been employed to rigorously rank the performance of the algorithms. The findings provide valuable insights into the strengths and weaknesses of each algorithm and demonstrate the potential of SWO for addressing real-world optimization challenges. | ||||
| Keywords | ||||
| Metaheuristic; Population-Based Metaheuristics; Swarm Intelligence; Unconstrained Optimization Problems | ||||
|
Statistics Article View: 32 PDF Download: 31 |
||||
