Hybrid Dipper Throated and Grey Wolf Optimization for Feature Selection Applied to Life Benchmark Datasets

Selecting the most relevant subset of features from a dataset is vital step in data mining and machine learning. Each feature has 2n possible subsets, making it challenging to select optimum collection using typical methods. As result, new metaheuristics-based selection method based on dipper-throated grey-wolf optimization (DTO-GW) algorithms been developed this research. Instability can result when subject metaheuristics, which lead wide range results. Thus, we adopted hybrid our optimizing, allowed us better balance exploration harvesting chores more equitably. We propose utilizing binary DTO-GW search approach previously devised for selecting optimal attributes. In proposed method, number selected minimized, while classification accuracy increased. To test method’s performance against eleven other state-of-the-art approaches, eight datasets UCI repository were used, such as grey wolf (bGWO), wolf, particle swarm (bGWO-PSO), bPSO, stochastic fractal (bSFS), whale algorithm (bWOA), modified (bMGWO), multiverse (bMVO), bowerbird (bSBO), hysteresis (bHy), (bHWO). The suggested superior successful handling problem selection, according results experiments.