A Novel Improved Binary Harris Hawks Optimization For High dimensionality Feature Selection

Harris Hawks Optimization (HHO) is a relatively new meta-heuristic algorithm that has shown promise in solving various optimization problems. However, HHO suffers from some limitations that can affect its performance. The two main drawbacks of HHO are population diversity and local optima. To overcome these limitations and adapt it to solve feature selection issues, a new meta-heuristic, Chaotic Opposition Harris Hawks Optimization with Simulated Annealing (COHHS), is proposed in this paper. Two main im-provements are proposed for the HHO. The first one, the chaotic opposition, is applied at the initialization phase of HHO to improve the population diversity of the search agents. The second one, simulated an-nealing, is applied to find the optimal solution during each iteration to improve HHO exploitation. The proposed method is a dynamic structure that was originally designed to solve problems with continuous optimization. In this paper, we propose a binary COHHS (BCOHHS) using X-shaped functions to boost the efficiency of feature selection. The KNN classifier is used to evaluate the classification accuracy. The performance of the proposed method is evaluated on nine high-dimensional medical datasets and com-pared with other optimization methods. The experimental results confirm the superiority of the BCOHHS method over the other methods on the majority of the datasets.& COPY; 2023 Elsevier B.V. All rights reserved.