An efficient binary whale optimisation algorithm with optimum path forest for feature selection

Abstract

Feature selection is an essential process which aims to find the most representative features for image processing and computer vision applications where utilising selected features reduces required time for classification and increases the classification rate. In this study, a new binary whale optimisation algorithm for feature selection is proposed. This optimisation algorithm is based on whales' behaviour. The Optimum-Path Forest (OPF) technique is used as an objective function. This function is much faster than the other classification techniques. The proposed binary whale optimisation algorithm is evaluated using five datasets of colour images. The proposed algorithm outperformed existing optimisation algorithms such as Particle Swarm Optimisation Algorithm (PSOA), Firefly Algorithm (FFA), Gravitational Search Algorithm (GSA), Binary Harmony Search (BHS), Binary Clonal Flower Pollination Algorithm (BCFA), Binary Cuckoo Search Algorithm (BCSA), and Binary Bat Algorithm (BBA) in terms of classification accuracy, number of selected features and execution times.