Hybrid Binary Grey Wolf With Harris Hawks Optimizer for Feature Selection

Despite Grey Wolf Optimizer's (GWO) superior performance in many areas, stagnation local optima areas may still be a concern. Several significant GWO factors can explored to enhance the of selection classification, with two conflicting concepts considered using or modeling metaheuristic method, exploring search field, and exploiting optimal solutions. Balancing exploration exploitation good manner will improve algorithm's performance. To achieve balance, this paper proposes binary hybrid Harris Hawks Optimization (HHO) form memetic approach called HBGWOHHO. The sigmoid transfer function is used continuous space into one meet feature nature requirement. A wrapper-based k-Nearest neighbor evaluate goodness selected features. validate proposed 18 standard UCI benchmark datasets were used. method was compared Binary Optimizer (BGWO), Particle Swarm (BPSO), (BHHO), Genetic Algorithm (BGA) Hybrid BWOPSO. findings revealed that effective improving BGWO algorithm. outperforms algorithm terms accuracy, size, computational time. Similarly, BPSO BGA algorithms, HBGWOHHO surpassed them yield better smaller size features much lower