An adaptive ranking moth flame optimizer for feature selection
Xiaobing Yu,
Haoyu Wang and
Yangchen Lu
Mathematics and Computers in Simulation (MATCOM), 2024, vol. 219, issue C, 164-184
Abstract:
Feature selection is to identify informative and concise sub-features from raw datasets, which can be modelled as an optimization issue. An adaptive ranking moth-flame optimization (ARMFO) is developed to solve the problem. The proposed ARMFO algorithm has five improvements: the ranking probability divides moths into better and worse groups; each group performs appropriate position-update equations to enhance the local and global search; a self-adaptive chaotic mutation is used to increase the quality of the best flame; a greedy selection is to maintain better solutions, and the structure of flames is changed. The search ability of the ARMFO algorithm is verified on a test suit, and the algorithm has obtained the best results on twenty-one functions, which accounts for 72.41%. Then, the proposed ARMFO algorithm and seven swarm intelligent algorithms are used for feature selection on fourteen datasets from UCI. The proposed ARMFO algorithm has obtained satisfactory results on 9 datasets compared to its seven rivals.
Keywords: Feature selection; Swarm intelligent algorithm; Moth flame optimizer; Exploration and exploitation (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:
Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S037847542300527X
Full text for ScienceDirect subscribers only
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:eee:matcom:v:219:y:2024:i:c:p:164-184
DOI: 10.1016/j.matcom.2023.12.022
Access Statistics for this article
Mathematics and Computers in Simulation (MATCOM) is currently edited by Robert Beauwens
More articles in Mathematics and Computers in Simulation (MATCOM) from Elsevier
Bibliographic data for series maintained by Catherine Liu ().