Journal
INFORMATION SCIENCES
Volume 417, Issue -, Pages 39-54Publisher
ELSEVIER SCIENCE INC
DOI: 10.1016/j.ins.2017.06.040
Keywords
Incomplete data; Incremental learning; Rough sets; Probabilistic approximations
Categories
Funding
- National Science Foundation of China [61602327, 61573292, 61572406, 61603313]
- National Natural Science Foundation of China [61432012, U1435213]
- China Postdoctoral Science Foundation [2016M602688]
- Postdoctoral Science Foundation of Sichuan Province
- Fundamental Research Funds for the Central Universities
- NSERC Canada
Ask authors/readers for more resources
Data in real-world applications are typically changing with time and are often incomplete. To address the challenge of processing such dynamic and incomplete data, we propose a model of dynamic probabilistic rough sets with incomplete data. We introduce incremental methods for estimating the conditional probability and present principles for updating probabilistic approximations when adding and removing objects, respectively. Based on the proposed updating strategies, algorithms are designed for dynamically updating probabilistic approximations with incomplete data. We report experimental evaluations of the efficiency and effectiveness of the proposed incremental algorithms for constructing probabilistic rough set approximations in terms of the size of data and updating ratio by comparing with a non-incremental algorithm. The results show that the new algorithms can effectively utilize the previously acquired knowledge, leading to significantly improved performance over a non-incremental algorithm. (C) 2017 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