Class-specific feature selection using fuzzy information-theoretic metrics

被引:8
作者
Ma, Xi-Ao [1 ,2 ]
Xu, Hao [1 ]
Liu, Yi [3 ]
Zhang, Justin Zuopeng [4 ]
机构
[1] Zhejiang Gongshang Univ, Sch Comp Sci & Technol, Hangzhou 310018, Zhejiang, Peoples R China
[2] Zhejiang Gongshang Univ, Collaborat Innovat Ctr Computat Social Sci, Hangzhou 310018, Zhejiang, Peoples R China
[3] Zhejiang Sci Tech Univ, Sch Econ & Management, Hangzhou 310018, Zhejiang, Peoples R China
[4] Univ North Florida, Coggin Coll Business, Jacksonville, FL 32224 USA
关键词
Feature selection; Fuzzy information-theoretic metric; Feature relevance; Feature redundancy; Class-specific feature selection; MUTUAL INFORMATION; MAX-RELEVANCE; REDUNDANCY; REDUCTION; ALGORITHM;
D O I
10.1016/j.engappai.2024.109035
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Fuzzy information-theoretic metrics have been demonstrated to be effective in evaluating feature relevance and redundancy in both categorical and numerical feature selection tasks. Most existing feature selection methods based on fuzzy information-theoretic metrics treat all classes as a single entity, resulting in the selection of a consistent feature subset for all classes. This approach overlooks the fact that diverse classes may exhibit distinct discriminative characteristics, which requires the selection of diverse feature subsets for each class. Consequently, these methods lack the capability to handle this variability in feature selection required for optimal performance. To address this limitation, this paper proposes a class-specific feature selection method based on fuzzy information-theoretic metrics. To be more specific, we introduce several class-specific fuzzy information-theoretic metrics. Building upon these metrics, we formulate a class-specific feature selection algorithm, which is referred to as class-specific fuzzy information-theoretic feature selection. This algorithm enables the selection of highly relevant feature subsets tailored to each individual class. Furthermore, we present a class-specific ensemble classification framework that integrates the classification results obtained from the feature subsets generated by our method. Finally, we conduct extensive tests on 21 publicly available datasets using four popular classifiers to compare the performance of our method with eight up-to-date classification-specific methods. Test results demonstrate that our method outperforms the eight compared classification-specific methods in terms of performance.
引用
收藏
页数:16
相关论文
共 62 条
[21]   Binary Anarchic Society Optimization for Feature Selection [J].
Kilic, Umit ;
Sarac Essiz, Esra ;
Kaya Keles, Mumine .
ROMANIAN JOURNAL OF INFORMATION SCIENCE AND TECHNOLOGY, 2023, 26 (3-4) :351-364
[22]   Wrappers for feature subset selection [J].
Kohavi, R ;
John, GH .
ARTIFICIAL INTELLIGENCE, 1997, 97 (1-2) :273-324
[23]   Feature Selection: A Data Perspective [J].
Li, Jundong ;
Cheng, Kewei ;
Wang, Suhang ;
Morstatter, Fred ;
Trevino, Robert P. ;
Tang, Jiliang ;
Liu, Huan .
ACM COMPUTING SURVEYS, 2018, 50 (06)
[24]   Class-specific feature selection via maximal dynamic correlation change and minimal redundancy [J].
Ma, Xi-Ao ;
Xu, Hao ;
Ju, Chunhua .
EXPERT SYSTEMS WITH APPLICATIONS, 2023, 229
[25]   Fuzzy information-theoretic feature selection via relevance, redundancy, and complementarity criteria [J].
Ma, Xi-Ao ;
Ju, Chunhua .
INFORMATION SCIENCES, 2022, 611 :564-590
[26]   Cost-sensitive three-way class-specific attribute reduction [J].
Ma, Xi-Ao ;
Zhao, Xue Rong .
INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, 2019, 105 :153-174
[27]   Three-way decision perspectives on class-specific attribute reducts [J].
Ma, Xi-Ao ;
Yao, Yiyu .
INFORMATION SCIENCES, 2018, 450 :227-245
[28]   Speech Emotion Recognition Using Deep Neural Networks, Transfer Learning, and Ensemble Classification Techniques [J].
Mihalache, Serban ;
Burileanu, Dragos .
ROMANIAN JOURNAL OF INFORMATION SCIENCE AND TECHNOLOGY, 2023, 26 (3-4) :375-387
[29]   A tutorial-based survey on feature selection: Recent advancements on feature selection [J].
Moslemi, Amir .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 126
[30]   An embedded feature selection method based on generalized classifier neural network for cancer classification [J].
Naik, Akshata K. ;
Kuppili, Venkatanareshbabu .
COMPUTERS IN BIOLOGY AND MEDICINE, 2024, 168