Improved Harris Hawks Optimization Using Elite Opposition-Based Learning and Novel Search Mechanism for Feature Selection

Abstract

The rapid increase in data volume and features dimensionality have a negative influence on machine learning and many other fields, such as decreasing classification accuracy and increasing computational cost. Feature selection technique has a critical role as a preprocessing step in reducing these issues. It works by eliminating the features that may negatively influence the classifiers' performance, such as irrelevant, redundant and less informative features. This paper aims to introduce an improved Harris hawks optimization (IHHO) by utilizing elite oppositebased learning and proposing a new search mechanism. Harris hawks optimization (HHO) is a novel metaheuristic general-purpose algorithm recently introduced to solve continuous search problems. Compared to conventional HHO, the proposed IHHO can avoid trapping in local optima and has an enhanced search mechanism, relying on mutation, mutation neighborhood search, and rollback strategies to raise the search capabilities. Moreover, it improves population diversity, computational accuracy, and accelerates convergence rate. To evaluate the performance of IHHO, we conducted a series of experiments on twenty benchmark datasets collected from the UCI repository and the scikit-feature project. The datasets represent different levels of feature dimensionality, such as low, moderate, and high. Further, four criteria were adopted to determine the superiority of IHHO: classification accuracy, fitness value, number of selected features, and statistical tests. Furthermore, a comparison between IHHO and other well-known algorithms such as Generic algorithm (GA), Grasshopper Optimization Algorithm (GOA), Particle Swarm Optimization (PSO), Ant Lion Optimizer (ALO), Whale Optimization Algorithm (WOA), Butterfly Optimization Algorithm (BOA) and Slime Mould Algorithm (SMA) was performed. The experimental results have confirmed the dominance of IHHO over the other optimization algorithms in different aspects, such as accuracy, fitness value, and feature selection.

An Improved Harris Hawks Optimization Algorithm With Simulated Annealing for Feature Selection in the Medical Field

“…The importance of this work comes from the fact that the Harris Hawks Optimization algorithm has been applied in many fields such as image processing [36], Optimal Power Flow Problem [37], drug design, and discovery [38]. Also, HHO applied in feature selection by using the Elite Opposition-Based Learning method [39] and provide good results. In the following section, basics and background about the HHO algorithm.…”

A Hybrid Approach for Solving Systems of Nonlinear Equations Using Harris Hawks Optimization and Newton’s Method

“…As mentioned earlier, hybridized algorithms are created by combining two optimization algorithms to overcome the demerits of one algorithm and taking advantage of the merits of the other. However, most of the hybridized algorithms still suffer from premature convergence depending on the original optimization algorithms mechanism [47]. The key point is to find a good match between the selected algorithms while creating the hybrid to obtain a more efficient variant.…”

Dynamic Butterfly Optimization Algorithm for Feature Selection

“…Generally speaking, there are two main types of feature selection methods: filter-based methods and wrapper-based methods. Chi-Square (Chi) and Information Gain (IG) are some examples of filter-based methods [2]. On the other hand, the wrapper-based methods mainly work based on using an optimisation algorithm to select the optimal subset of features.…”

“…Therefore, in wrapper mode, there is a direct interaction between the features and the used classifier. In the wrapper-based method, a fitness function will be used by the optimisation algorithm to find the quality of the selected features taking into account the achieved classification accuracy and the number of selected features [2].…”

“…In the literature, there are several studies that applied optimisation algorithms for feature selection problem. For example, [3,4] improved whale optimisation algorithm (WOA) and used it for feature selection, [5] improved particle swarm optimisation (PSO) and used it for feature selection, [6] used Grasshopper optimisation algorithm (GOA) for feature selection, [7] used Firefly algorithm (FFA) for feature selection, [8] used Differential Evolution (DE) for feature selection, [1] improved Salp Swarm Algorithm (SSA)and used it for feature selection, [9] used Genetic Algorithm (GA) for feature selection, [10] used Grey Wolf Optimization (GWO) for feature selection, [11] improved Gravitational Search algorithm (GSA) and used it for feature selection, [12] used fish swarm optimisation (FSO) for feature selection, [13] improved crow search algorithm (CSA) and used it for feature selection, [14] improved Dragonfly Algorithm (DA) and used it for feature selection, [15] improved social spider algorithm (SSA) and used it for feature selection, [1,16] improved Salp Swarm Algorithm (SSA) and used it for feature selection, [2] improved Harris hawks optimisation (HHO) and used it for feature selection.…”