A feature selection algorithm based on redundancy analysis and interaction weight

• Published in: Applied intelligence (Dordrecht, Netherlands) Vol. 51; no. 4; pp. 2672 - 2686
• Main Authors: Gu, Xiangyuan, Guo, Jichang, Li, Chongyi, Xiao, Lijun
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.04.2021; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Computer Science; Feature selection; Machines; Manufacturing; Mechanical Engineering; Processes; Redundancy; Weight analysis; Feature selection; Three-way interaction information; Symmetric uncertainty; Redundancy analysis
• ISSN: 0924-669X; 1573-7497
• DOI: 10.1007/s10489-020-01936-5

The performance of some three-dimensional mutual information-based algorithms can be affected, since only relevance and interaction are considered. Aiming at solving the problem, a feature selection algorithm based on redundancy analysis and interaction weight is proposed in this paper. The proposed algorithm adopts three-way interaction information to measure the interaction among the class label and features, and processes features for interaction weight analysis. Then, it employs symmetric uncertainty to measure the relevance between features and the class label as well as the redundancy between features, and selects the features with greater relevance and interaction as well as smaller redundancy. To validate the performance, the proposed algorithm is compared with several feature selection algorithms. Since relevance, redundancy, and interaction analysis are all presented, the proposed algorithm can obtain better feature selection performance.