Improved Hybrid of Artificial Gorilla Troops Optimizer and Simulated Annealing Algorithm to Address Global Optimization Problems

Metaheuristics represent a category of optimization methods that surpass traditional exact methods by effectively and efficiently solving complex optimization problems. Feature subset selection (FS) is essential and important for addressing classification problems involving choosing optimal feature subsets based on specific criteria; this process is employed to decrease dimensionality and eliminate noise from datasets, which leads to simplicity of rules, aids data visualization, accelerates learning and enhances predictive accuracy. Among these algorithms, the artificial Gorilla Troop Optimization (GTO) is a recent metaheuristic algorithm miming gorillas' social behaviors. This study introduces a novel hybridized optimization approach to be tailored for feature subset selection. The suggested GTO-SA method combines the strengths of the artificial Gorilla Troop Optimization and simulated annealing (SA) to effectively explore and exploit the search space, aiming to achieve the best promising solutions. Simulated annealing was employed as an internal function to enhance exploitation capabilities that occasionally accept inferior solutions, which gives rise to refining the search process. The empirical evaluations were conducted based on sixteen medical datasets from the UCI repository. The results demonstrate that GTO-SA outperforms native GTO, as well as other methods, including Particle Swarm Optimization (PSO), Sine Cosine Algorithm (SCA), and Ant Lion Optimizer (ALO). The experiment results clearly showed the hybrid algorithm's efficiency in exploiting and exploring feature spaces to identify the finest features. Moreover, it significantly improved classification accuracy with minimal run time across all data sets utilized.