期刊
出版社
ELSEVIER SCIENCE BV
DOI: 10.1016/j.procs.2015.09.006
关键词
Gray-Wolf; Multi-Objective; Attribute Reduction
Feature sets are always dependent, redundant and noisy in almost all application domains. These problems in The data always declined the performance of any given classifier as it make it difficult for the training phase to converge effectively and it affect also the running time for classification at operation and training time. In this work a system for feature selection based on multi-objective gray wolf optimization is proposed. The existing methods for feature selection either depend on the data description; filter-based methods, or depend on the classifier used; wrapper approaches. These two main approaches lakes of good performance and data description in the same system. In this work gray wolf optimization; a swarm-based optimization method, was employed to search the space of features to find optimal feature subset that both achieve data description with minor redundancy and keeps classification performance. At the early stages of optimization gray wolf uses filter-based principles to find a set of solutions with minor redundancy described by mutual information. At later stages of optimization wrapper approach is employed guided by classifier performance to further enhance the obtained solutions towards better classification performance. The proposed method is assessed against different common searching methods such as particle swarm optimization and genetic algorithm and also was assessed against different single objective systems. The proposed system achieves an advance over other searching methods and over the other single objective methods by testing over different UCI data sets and achieve much robustness and stability. (C) 2015 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). Peer-review under responsibility of Universal Society for Applied Research
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据