Journal
INFORMATION SCIENCES
Volume 589, Issue -, Pages 283-299Publisher
ELSEVIER SCIENCE INC
DOI: 10.1016/j.ins.2021.12.119
Keywords
Attribute reduction; Rough set; Incremental learning; Attribute group; Stable
Categories
Funding
- National Natural Science Foundation of China [61773324, 61876157]
- Humanity and Social Science Youth Foundation of Ministry of Education of China [20YJC630191]
- Fundamental Research Funds for the Central Universities [JBK2001004]
- Fintech Innovation Center of Southwestern University of Finance and Economics
- Financial Intelligence & Financial Engineering Key Laboratory of Sichuan Province
Ask authors/readers for more resources
In this paper, a method for improving the performance of attribute reduction in a dynamic data environment is proposed. By combining incremental technology and accelerated reduction strategy, the method utilizes stable attribute groups and matrix-based incremental mechanisms for reduction search and dynamic attribute reduction. Experimental results demonstrate the effectiveness of the proposed method in terms of stability, computational cost, and classification accuracy.
In dynamic and open data environment, how to improve the performance of reduction is of great importance from incremental evaluation of attributes and quick search of attributes. In this paper, by considering both two perspectives, we first combine the incremental technology and the accelerated strategy in attribute reduction. On the one hand, we utilize the stable attribute group generated by DBSCAN to accelerate the process of searching reduction. On the other hand, we propose the matrix-based incremental mechanisms to dynamic attribute reduction when the objects are evolved over time. Moreover, these two methods are fused together in a unified algorithm of reduction. Finally, a series of comparative experiments is conducted to verify the effectiveness of proposed approach from stability, computational cost, and classification accuracy. (C) 2021 Elsevier Inc. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available