Journal of Bionic Engineering ›› 2023, Vol. 20 ›› Issue (3): 1153-1174.doi: 10.1007/s42235-022-00298-7
Crisscross Harris Hawks Optimizer for Global Tasks and Feature Selection
Xin Wang1; Xiaogang Dong1; Yanan Zhang2,3; Huiling Chen4
- 1 School of Mathematics and Statistics, Changchun University of Technology, Changchun, Jilin 130012, China 2 School of Management, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China 3 Information Construction Ofce, Changchun University of Technology, Changchun, Jilin 130012, China 4 College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, China
Crisscross Harris Hawks Optimizer for Global Tasks and Feature Selection
Xin Wang1; Xiaogang Dong1; Yanan Zhang2,3; Huiling Chen4
- 1 School of Mathematics and Statistics, Changchun University of Technology, Changchun, Jilin 130012, China 2 School of Management, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China 3 Information Construction Ofce, Changchun University of Technology, Changchun, Jilin 130012, China 4 College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, China
摘要： Harris Hawks Optimizer (HHO) is a recent well-established optimizer based on the hunting characteristics of Harris hawks, which shows excellent efficiency in solving a variety of optimization issues. However, it undergoes weak global search capability because of the levy distribution in its optimization process. In this paper, a variant of HHO is proposed using Crisscross Optimization Algorithm (CSO) to compensate for the shortcomings of original HHO. The novel developed optimizer called Crisscross Harris Hawks Optimizer (CCHHO), which can effectively achieve high-quality solutions with accelerated convergence on a variety of optimization tasks. In the proposed algorithm, the vertical crossover strategy of CSO is used for adjusting the exploitative ability adaptively to alleviate the local optimum; the horizontal crossover strategy of CSO is considered as an operator for boosting explorative trend; and the competitive operator is adopted to accelerate the convergence rate. The effectiveness of the proposed optimizer is evaluated using 4 kinds of benchmark functions, 3 constrained engineering optimization issues and feature selection problems on 13 datasets from the UCI repository. Comparing with nine conventional intelligence algorithms and 9 state-of-the-art algorithms, the statistical results reveal that the proposed CCHHO is significantly more effective than HHO, CSO, CCNMHHO and other competitors, and its advantage is not influenced by the increase of problems’ dimensions. Additionally, experimental results also illustrate that the proposed CCHHO outperforms some existing optimizers in working out engineering design optimization; for feature selection problems, it is superior to other feature selection methods including CCNMHHO in terms of fitness, error rate and length of selected features.