Attribute reduction based on the Boolean matrix
- 200 Downloads
Attribute reduction is an important preprocessing step in machine learning and pattern recognition. This paper introduces condition-attribute Boolean matrix and decision-attribute Boolean matrix and proposes a new attribute reduction model based on Boolean operations according to the concept of neighborhood rough set. Some operation rules of Boolean vectors are defined and an uncertainty measure, named attribute support function, is proposed to evaluate the importance degree of candidate attributes with respect to decision attributes. An attribute reduction algorithm based on the proposed measure is designed. Ten data sets selected from public data sources are used to compare the proposed algorithm with some existing algorithms. The experimental results show that the proposed reduction algorithm is feasible and effective.
KeywordsRough set Attribute reduction Boolean vector Boolean matrix
This work was supported by the National Natural Science Foundation of China under Grants 61572082, 61673396, and 61473111, the Foundation of Educational Committee of Liaoning Province (LZ2016003), and the Natural Science Foundation of Liaoning Province (20170540012, 20170540004).
- An S, Hu Q, Pedrycz W, Zhu P, Eric C, Tsang C (2016) Data-distribution-aware fuzzy rough set model and its application to robust classification. IEEE Trans Cybern 46(12):3073–3085Google Scholar
- Lin T (1997) Neighborhood systems: application to qualitative fuzzy and rough sets. In: Wang PP (ed) Advances in machine intelligence and soft computing. Department of Electrical Engineering, Duke University, Durham, pp 132–155Google Scholar