A modified grey wolf optimizer with multi-solution crossover integration algorithm for feature selection

作     者：Ihsan, Muhammad Din, Fakhrud Zamli, Kamal Z. Ghadi, Yazeed Yasin Alahmadi, Tahani Jaser Innab, Nisreen 

作者机构：Faculty of IT Department of Computer Science and IT University of Malakand Khyber Pakhtunkhwa Chakdara18800 Pakistan Faculty of Computing College of Computing and Applied Sciences Universiti Malaysia Pahang Pahang Pekan26600 Malaysia Department of computer science and software engineering Al Ain University Abu Dhabi12555 United Arab Emirates Department of Information SystemsCollege of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh84428 Saudi Arabia Department of Computer Science and Information SystemsCollege of Applied Sciences Al-Maarefa University Diriyah Riyadh13713 Saudi Arabia 

出 版 物：《Journal of Ambient Intelligence and Humanized Computing》 (J. Ambient Intell. Humanized Comput.)

年 卷 期：2025年第16卷第1期

页      面：329-345页

核心收录：

学科分类：07[理学] 08[工学] 070105[理学-运筹学与控制论] 071101[理学-系统理论] 0303[法学-社会学] 0710[理学-生物学] 0711[理学-系统科学] 081203[工学-计算机应用技术] 0835[工学-软件工程] 0836[工学-生物工程] 081101[工学-控制理论与控制工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work didn't receive any specific funding 

主　　题：Constrained optimization 

摘      要：Feature selection helps eradicate redundant features which is essential to mitigate the curse of dimensionality when a machine-learning model deals with high-dimensional datasets. Grey Wolf Optimizer (GWO) is a swarm-based algorithm that simulates the wolves’ hunting behavior. Although very efficient, GWO faces some limitations which may cause premature convergence and/or local optima trapping. Moreover, GWO relies mainly on the three best wolves, limiting its potential for diverse exploration and exploitation. This work proposes an improved version of GWO namely, a modified grey wolf optimizer with multi-solution crossover integration (MGWO-MCI) algorithm. MGWO-MCI algorithm incorporates a multi-solution strategy that evolves new potential solutions in the optimization process. A crossover operation is performed between the new wolves and the existing hierarchy, reforming the position-updating process. MGWO-MCI utilizes this position-updating process using two different approaches. The first approach named MGWO-MCI-I expands the additional wolves’ role to both exploration and exploitation whereas the second approach named MGWO-MCI-II incorporates their role to exploration only. These approaches are evaluated and tested using 18 datasets and an Intrusion detection dataset NSL-KDD for feature selection. Statistically, the results are analyzed through the Wilcoxon test, which shows the superiority of MGWO-MCI-II. MGWO-MCI-II outperforms others with an accuracy of 98.6% on NSL-KDD and achieves 55.5% overall best outcomes on other datasets. Moreover, the MGWO-MCI was evaluated on two constrained optimization problems, the pressure vessel and welded beam design validating its effectiveness and adaptability in solving different optimization problems. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.