Improved Binary Grasshopper Optimization Algorithm for Feature Selection Problem

Abstract

The migration and predation of grasshoppers inspire the grasshopper optimization algorithm (GOA). It can be applied to practical problems. The binary grasshopper optimization algorithm (BGOA) is used for binary problems. To improve the algorithm’s exploration capability and the solution’s quality, this paper modifies the step size in BGOA. The step size is expanded and three new transfer functions are proposed based on the improvement. To demonstrate the availability of the algorithm, a comparative experiment with BGOA, particle swarm optimization (PSO), and binary gray wolf optimizer (BGWO) is conducted. The improved algorithm is tested on 23 benchmark test functions. Wilcoxon rank-sum and Friedman tests are used to verify the algorithm’s validity. The results indicate that the optimized algorithm is significantly more excellent than others in most functions. In the aspect of the application, this paper selects 23 datasets of UCI for feature selection implementation. The improved algorithm yields higher accuracy and fewer features.

Low-Voltage Arc Fault Identification Using a Hybrid Method Based on Improved Salp Swarm Algorithm–Variational Mode Decomposition– Random Forest

“…The initial population is generated by tent mapping, which has randomness and ergodicity, and can better be evenly covered in the initial space and directly affects the convergence speed and the solution quality. The calculation method is as follows ( 5) [33]:…”