An improved multi-strategy Golden Jackal algorithm for real world engineering problems

Abstract

The Golden Jackal Optimization (GJO) algorithm is a novel, nature-inspired optimization technique that has gained recognition as a highly promising metaheuristic due to its notable efficiency and adaptability. However, the GJO algorithm possesses several shortcomings, including inadequate exploitation ability, vulnerability to local optima, and imbalanced exploration-exploitation. Therefore, this paper presents an enhanced version of the named mGJO, tailored explicitly for addressing real-world engineering and feature selection problems. The mGJO incorporates four improvements to the standard GJO. To begin with, Chaos-OBL (COBL) based population initialization is proposed to increase diversity in population. Secondly, a nonlinear control parameter is proposed to regulate the exploration-exploitation transition. Thirdly, the original updating rule of GJO is combined with the ESQ mechanism to prevent the leader solutions from influencing the local optimal solutions. Finally, a new adaptive mutation strategy is presented to alter individuals and improve positions based on their fitness. To evaluate the efficiency of the suggested mGJO is assessed using CEC2005, CEC2017, CEC2020 and CEC2022 benchmark functions. The proposed mGJO is also applied to five common real-world engineering problems and is also applied to the feature selection problems to assess its performance. Furthermore, the proposed mGJO is compared with various advanced algorithms to evaluate its performance. Statistical analyses, including the Friedman rank test and Wilcoxon test, are applied to the experimental data to validate the superiority of the extracted results. The experimental results and the statistical analysis indicate the superiority of mGJO in terms of convergence rate, solution quality, and optimization accuracy.