A novel control factor and Brownian motion-based improved Harris Hawks Optimization for feature selection

The massive growth in data size has prompted proliferation in need for Feature Selection (FS). Hence, FS has become an imperative method for dealing with high-dimensional data. This research critique proposes an enhanced feature selection of Harris Hawks Optimization (HHO) based on the novel control factor and Brownian motion. The Brownian motion augments the exploitation of foragers. It also replicates the deceptive movement of prey, allowing predators to correct their location and direction according to the prey's position. At the same time, the novel control factor imitates the exact behavior of the prey's escaping energy. The comparative analysis with the existing technique using six real high-dimensional microarray datasets highlights the impact of the proposed Improved Harris Hawks Optimization (iHHO). The experimental results of FS and classification accuracy vividly depict how the proposed model outperforms the existing techniques.

Automated summary

The massive growth in data size has led to a proliferation of the need for feature selection methods. This research proposes an enhanced Harris Hawks Optimization algorithm for feature selection, which utilizes Brownian motion and a novel control factor to improve the search process. Experimental results demonstrate the superiority of this algorithm over existing techniques.