An improved relief feature selection algorithm based on Monte-Carlo tree search
The goal of feature selection methods is to find the optimal feature subset by eliminating irrelevant or redundant information from the original feature space according to some evaluation criteria. In the literature, the Relief algorithm is a typical feature selection method, which is simple and eas...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2019-01-01
|
| Series: | Systems Science & Control Engineering |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/21642583.2019.1661312 |
| _version_ | 1819152407491248128 |
|---|---|
| author | Jianyang Zheng Hexing Zhu Fangfang Chang Yunlong Liu |
| author_facet | Jianyang Zheng Hexing Zhu Fangfang Chang Yunlong Liu |
| author_sort | Jianyang Zheng |
| collection | DOAJ |
| description | The goal of feature selection methods is to find the optimal feature subset by eliminating irrelevant or redundant information from the original feature space according to some evaluation criteria. In the literature, the Relief algorithm is a typical feature selection method, which is simple and easy to execute. However, the classification accuracy of the Relief algorithm is usually affected by the noise. In recent years, the Monte Carlo Tree Search (MCTS) technique has achieved great success in strategy selections of large-scale systems by building a tree and quickly focusing on the most valuable part of the search space. In this paper, with the benefit of MCTS, an MCTS-based feature selection approach is proposed to deal with the feature selection problem of high dimensional data, where the Relief algorithm is used as the evaluation function of the MCTS approach. The effectiveness of the proposed approach is demonstrated by experiments on some benchmark problems. |
| first_indexed | 2024-12-22T14:48:48Z |
| format | Article |
| id | doaj.art-78b8bf5c3dcc4b77948f67569eed9513 |
| institution | Directory Open Access Journal |
| issn | 2164-2583 |
| language | English |
| last_indexed | 2024-12-22T14:48:48Z |
| publishDate | 2019-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Systems Science & Control Engineering |
| spelling | doaj.art-78b8bf5c3dcc4b77948f67569eed95132022-12-21T18:22:22ZengTaylor & Francis GroupSystems Science & Control Engineering2164-25832019-01-017130431010.1080/21642583.2019.16613121661312An improved relief feature selection algorithm based on Monte-Carlo tree searchJianyang Zheng0Hexing Zhu1Fangfang Chang2Yunlong Liu3Xiamen UniversityXiamen UniversityXiamen UniversityXiamen UniversityThe goal of feature selection methods is to find the optimal feature subset by eliminating irrelevant or redundant information from the original feature space according to some evaluation criteria. In the literature, the Relief algorithm is a typical feature selection method, which is simple and easy to execute. However, the classification accuracy of the Relief algorithm is usually affected by the noise. In recent years, the Monte Carlo Tree Search (MCTS) technique has achieved great success in strategy selections of large-scale systems by building a tree and quickly focusing on the most valuable part of the search space. In this paper, with the benefit of MCTS, an MCTS-based feature selection approach is proposed to deal with the feature selection problem of high dimensional data, where the Relief algorithm is used as the evaluation function of the MCTS approach. The effectiveness of the proposed approach is demonstrated by experiments on some benchmark problems.http://dx.doi.org/10.1080/21642583.2019.1661312Feature selectionRelief algorithmMonte-Carlo tree search |
| spellingShingle | Jianyang Zheng Hexing Zhu Fangfang Chang Yunlong Liu An improved relief feature selection algorithm based on Monte-Carlo tree search Systems Science & Control Engineering Feature selection Relief algorithm Monte-Carlo tree search |
| title | An improved relief feature selection algorithm based on Monte-Carlo tree search |
| title_full | An improved relief feature selection algorithm based on Monte-Carlo tree search |
| title_fullStr | An improved relief feature selection algorithm based on Monte-Carlo tree search |
| title_full_unstemmed | An improved relief feature selection algorithm based on Monte-Carlo tree search |
| title_short | An improved relief feature selection algorithm based on Monte-Carlo tree search |
| title_sort | improved relief feature selection algorithm based on monte carlo tree search |
| topic | Feature selection Relief algorithm Monte-Carlo tree search |
| url | http://dx.doi.org/10.1080/21642583.2019.1661312 |
| work_keys_str_mv | AT jianyangzheng animprovedrelieffeatureselectionalgorithmbasedonmontecarlotreesearch AT hexingzhu animprovedrelieffeatureselectionalgorithmbasedonmontecarlotreesearch AT fangfangchang animprovedrelieffeatureselectionalgorithmbasedonmontecarlotreesearch AT yunlongliu animprovedrelieffeatureselectionalgorithmbasedonmontecarlotreesearch AT jianyangzheng improvedrelieffeatureselectionalgorithmbasedonmontecarlotreesearch AT hexingzhu improvedrelieffeatureselectionalgorithmbasedonmontecarlotreesearch AT fangfangchang improvedrelieffeatureselectionalgorithmbasedonmontecarlotreesearch AT yunlongliu improvedrelieffeatureselectionalgorithmbasedonmontecarlotreesearch |