Metric Based Attribute Reduction Method in Dynamic Decision Tables
http://repository.vnu.edu.vn/handle/VNU_123/10836
Feature selection is a vital problem need to be effectively solved in knowledge discovery in databases and pattern recognition because of two basic reasons: to minimize cost and to accurately classify data.
Feature selection using rough set theory also is called attribute reduction have attracted much attention from researchers and numerous potential results are gained.
However, most of them are applied on static data and attribute reduction in dynamic databases is still in the early stage.
This paper focus on developing incremental methods and algorithms to derive reducts employing a distance measure when decision systems vary in condition attribute set.
We as well conduct experiments on UCI data sets and the experimental results show that the proposed algorithms are better in terms of time consuming and reducts’ cardinality in comparison with non-incremental heuristic algorithm and the incremental approach using information entropy proposed by authors in
Feature selection is a vital problem need to be effectively solved in knowledge discovery in databases and pattern recognition because of two basic reasons: to minimize cost and to accurately classify data.
Feature selection using rough set theory also is called attribute reduction have attracted much attention from researchers and numerous potential results are gained.
However, most of them are applied on static data and attribute reduction in dynamic databases is still in the early stage.
This paper focus on developing incremental methods and algorithms to derive reducts employing a distance measure when decision systems vary in condition attribute set.
We as well conduct experiments on UCI data sets and the experimental results show that the proposed algorithms are better in terms of time consuming and reducts’ cardinality in comparison with non-incremental heuristic algorithm and the incremental approach using information entropy proposed by authors in
| Title: | Metric Based Attribute Reduction Method in Dynamic Decision Tables |
| Authors: | Demetrovics Janos, Nguyen Thi Lan Huong, Vu Duc Thi, Nguyen Long Giang |
| Keywords: | Rough set, decision systems, attribute reduction, reduct, metric |
| Issue Date: | 2015 |
| Publisher: | ĐHQGHN |
| Abstract: | Feature selection is a vital problem need to be effectively solved in knowledge discovery in databases and pattern recognition because of two basic reasons: to minimize cost and to accurately classify data. Feature selection using rough set theory also is called attribute reduction have attracted much attention from researchers and numerous potential results are gained. However, most of them are applied on static data and attribute reduction in dynamic databases is still in the early stage. This paper focus on developing incremental methods and algorithms to derive reducts employing a distance measure when decision systems vary in condition attribute set. We as well conduct experiments on UCI data sets and the experimental results show that the proposed algorithms are better in terms of time consuming and reducts’ cardinality in comparison with non-incremental heuristic algorithm and the incremental approach using information entropy proposed by authors in [17]. |
| URI: | http://repository.vnu.edu.vn/handle/VNU_123/10836 |
| Appears in Collections: | ITI - Papers |
Nhận xét
Đăng nhận xét