An Improved Northern Goshawk Optimization Algorithm for Feature Selection

Rongxiang Xie

doi:10.1007/s42235-024-00515-5

2024-05-14

PRE

Rongxiang Xie

Shaobo Li *

Fengbin Wu

DOI：10.1007/s42235-024-00515-5

原文链接

原文求助

摘要

En 中文

Feature Selection (FS) is an important data management technique that aims to minimize redundant information in a dataset. This work proposes DENGO, an improved version of the Northern Goshawk Optimization (NGO), to address the FS problem. The NGO is an efficient swarm-based algorithm that takes its inspiration from the predatory actions of the northern goshawk. In order to overcome the disadvantages that NGO is prone to local optimum trap, slow convergence speed and low convergence accuracy, two strategies are introduced in the original NGO to boost the effectiveness of NGO. Firstly, a learning strategy is proposed where search members learn by learning from the information gaps of other members of the population to enhance the algorithm's global search ability while improving the population diversity. Secondly, a hybrid differential strategy is proposed to improve the capability of the algorithm to escape from the trap of the local optimum by perturbing the individuals to improve convergence accuracy and speed. To prove the effectiveness of the suggested DENGO, it is measured against eleven advanced algorithms on the CEC2015 and CEC2017 benchmark functions, and the obtained results demonstrate that the DENGO has a stronger global exploration capability with higher convergence performance and stability. Subsequently, the proposed DENGO is used for FS, and the 29 benchmark datasets from the UCL database prove that the DENGO-based FS method equipped with higher classification accuracy and stability compared with eight other popular FS methods, and therefore, DENGO is considered to be one of the most prospective FS techniques. DENGO's code can be obtained at https://www.mathworks.com/matlabcentral/fileexchange/158811-project1.

Keyword:

Northern goshawk optimization

Learning strategy

Hybrid differential strategy

Numerical optimization

Feature selection