eprintid: 13845
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/38/45
datestamp: 2023-11-10 03:28:24
lastmod: 2023-11-10 03:28:24
status_changed: 2023-11-10 01:52:08
type: article
metadata_visibility: show
creators_name: Al-Tashi, Q.
creators_name: Abdulkadir, S.J.
creators_name: Rais, H.M.
creators_name: Mirjalili, S.
creators_name: Alhussian, H.
creators_name: Ragab, M.G.
creators_name: Alqushaibi, A.
title: Binary Multi-Objective Grey Wolf Optimizer for Feature Selection in Classification
ispublished: pub
keywords: Benchmarking; Classification (of information); Dimensionality reduction; Feature extraction; Genetic algorithms; Neural networks; Particle swarm optimization (PSO); Screening; Transfer functions, Classification performance; Continuous optimization problems; Feature selection problem; Multi objective particle swarm optimization; Multi-objective optimization problem; Non dominated sorting genetic algorithm (NSGA II); Sigmoid transfer function; Single objective optimization problems, Multiobjective optimization
note: cited By 69
abstract: Feature selection or dimensionality reduction can be considered as a multi-objective minimization problem with two objectives: minimizing the number of features and minimizing the error rate simultaneously. Despite being a multi-objective problem, most existing approaches treat feature selection as a single-objective optimization problem. Recently, Multi-objective Grey Wolf optimizer (MOGWO) was proposed to solve multi-objective optimization problem. However, MOGWO was originally designed for continuous optimization problems and hence, it cannot be utilized directly to solve multi-objective feature selection problems which are inherently discrete in nature. Therefore, in this research, a binary version of MOGWO based on sigmoid transfer function called BMOGW-S is developed to optimize feature selection problems. A wrapper based Artificial Neural Network (ANN) is used to assess the classification performance of a subset of selected features. To validate the performance of the proposed method, 15 standard benchmark datasets from the UCI repository are employed. The proposed BMOGWO-S was compared with MOGWO with a tanh transfer function and Non-dominated Sorting Genetic Algorithm (NSGA-II) and Multi-objective Particle Swarm Optimization (MOPSO). The results showed that the proposed BMOGWO-S can effectively determine a set of non-dominated solutions. The proposed method outperforms the existing multi-objective approaches in most cases in terms of features reduction as well as classification error rate while benefiting from a lower computational cost. © 2013 IEEE.
date: 2020
publisher: Institute of Electrical and Electronics Engineers Inc.
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85086737786&doi=10.1109%2fACCESS.2020.3000040&partnerID=40&md5=afb3ba464561276cf31fc5b1003d1f47
id_number: 10.1109/ACCESS.2020.3000040
full_text_status: none
publication: IEEE Access
volume: 8
pagerange: 106247-106263
refereed: TRUE
issn: 21693536
citation:   Al-Tashi, Q. and Abdulkadir, S.J. and Rais, H.M. and Mirjalili, S. and Alhussian, H. and Ragab, M.G. and Alqushaibi, A.  (2020) Binary Multi-Objective Grey Wolf Optimizer for Feature Selection in Classification.  IEEE Access, 8.  pp. 106247-106263.  ISSN 21693536