首页    期刊浏览 2024年11月30日 星期六
登录注册

文章基本信息

  • 标题:Neighborhood search methods with Moth Optimization algorithm as a wrapper method for feature selection problems
  • 本地全文:下载
  • 作者:Malek Alzaqebah ; Nashat Alrefai ; Eman A. E. Ahmed
  • 期刊名称:International Journal of Electrical and Computer Engineering
  • 电子版ISSN:2088-8708
  • 出版年度:2020
  • 卷号:10
  • 期号:4
  • 页码:3672-3684
  • DOI:10.11591/ijece.v10i4.pp3672-3684
  • 出版社:Institute of Advanced Engineering and Science (IAES)
  • 摘要:Feature selection methods are used to select a subset of features from data, therefore only the useful information can be mined from the samples to get better accuracy and improves the computational efficiency of the learning model. Moth-flam Optimization (MFO) algorithm is a population-based approach, that simulates the behavior of real moth in nature, one drawback of the MFO algorithm is that the solutions move toward the best solution, and it easily can be stuck in local optima as we investigated in this paper, therefore, we proposed a MFO Algorithm combined with a neighborhood search method for feature selection problems, in order to avoid the MFO algorithm getting trapped in a local optima, and helps in avoiding the premature convergence, the neighborhood search method is applied after a predefined number of unimproved iterations (the number of tries fail to improve the current solution). As a result, the proposed algorithm shows good performance when compared with the original MFO algorithm and with state-of-the-art approaches.
  • 关键词:Classification;Feature selection;Metaheuristic optimization;Moth optimization;Neighborhood search
国家哲学社会科学文献中心版权所有