文章快速检索 高级检索

1. 江苏科技大学 计算机科学与工程学院，江苏 镇江 212003;
2. 南京理工大学 计算机科学与技术学院，江苏 南京 210094

Test-cost-sensitive based variable precision classification rough set in incomplete information system
JU Hengrong1, MA Xingbin1, YANG Xibei1,2, QI Yunsong1, YANG Jingyu2
1. School of Computer Science and Engineering,Jiangsu University of Science and Technology,Zhenjiang 212003,China ;
2. School of Computer Science and Technology,Nanjing University of Science and Technology,Nanjing 210094,China
Abstract: In an incomplete information system,the precision-variable classification relation is an improvement of the limited tolerance relation. However,the test costs of the data concentration attributes are not taken into account. To solve this problem,a test-cost-sensitive-based precision-variable precision classification rough set is proposed. Furthermore,the traditional heuristic algorithm does not take the importance of the test costs of the attributes into account,and backtracking algorithm is very time-consuming. Therefore,not only was a new importance of the attribute proposed,but a new heuristic algorithm was also presented for obtaining reduction with minor test costs. The experimental results show the effectiveness of the new algorithm by comparing it with the other algorithms.
Key words: attribute reduction     incomplete information system     test cost sensitive     variable precision classification rough set

1 基本概念

 (1)

2 测试代价与可变精度分类粗糙集

3 属性约简

Min等从获取约简的测试代价最小出发设计出新的约简算法,即回溯算法(记为算法2)。其算法复杂度为。详细算法见文献[11]。

3.1 考虑属性测试代价的启发式算法

1)计算;令θ=0,;

2) ;

3) ,计算属性ai的重要度TCSLSigin(ai,AT,D);

4)若,则,计算;

5)若,则重复以下循环,否则转6);

,计算TCSLSigout(ai,red,D);

②若,则;

6),若,则red=red-ai,tmp=c*(red);

7);

8)若θ大于给定阈值,则(此处δ为步长,δ>0)且重复2)~7),否则转9);

9)输出red及c*(red)。

3.2 实验分析

 Data ID Data sets Samples Attributes DecisionClasses 1 Bridges 108 12 7 2 Credit Approval 263 15 3 3 Heart-Disease 303 14 5 4 Hepatitis 155 19 2

 图 1 3种约简算法所求得的测试代价对比 Fig. 1 Comparisons among test costs obtained by three algorithms

4 结束语

 [1] PAWLAK Z. Rough sets-theoretical aspects of reasoning about data[M]. Dordrecht: Kluwer Academic, 1991 . [2] HU Q H, CHE X J, ZHANG L, et al. Rank entropy based decision trees for monotonic classification[J]. IEEE Transactions on Knowledge and Data Engineering , 2012, 24 (11) : 2052-2064 DOI:10.1109/TKDE.2011.149 [3] HU Q H, PAN W W, ZHANG L, et al. Feature selection for monotonic classification[J]. IEEE Transactions on Fuzzy Systems , 2012, 20 (1) : 69-81 DOI:10.1109/TFUZZ.2011.2167235 [4] LUO G Z, YANG X B. Limited dominance-based rough set model and knowledge reductions in incomplete decision system[J]. Journal of Information Science and Engineering , 2010, 26 (6) : 2199-2211 [5] 王国胤. Rough集理论在不完备信息系统中的扩充[J]. 计算机研究与发展 , 2002, 39 (10) : 1238-1243 WANG Guoyin. Extension of rough set under incomplete information systems[J]. Journal of Computer Research and Development , 2002, 39 (10) : 1238-1243 [6] 杨习贝, 杨静宇, 於东军, 等. 不完备信息系统中的可变精度分类粗糙集模型[J]. 系统工程理论与实践 , 2008, 28 (5) : 116-121 YANG Xibei, YANG Jingyu, YU Dongjun, et al. Rough set model based on variable parameter classification in incomplete information systems[J]. System Engineering-Theory and Practice , 2008, 28 (5) : 116-121 [7] MIN F, HE H P, QIAN Y H, et al. Test-cost-sensitive attribute reduction[J]. Information Sciences , 2011, 181 (22) : 4928-4942 DOI:10.1016/j.ins.2011.07.010 [8] MIN F, LIU Q H. A hierarchical model for test-cost-sensitive decision systems[J]. Information Sciences , 2009, 179 (14) : 2442-2452 DOI:10.1016/j.ins.2009.03.007 [9] MIN F,ZHU W. Test-cost-sensitive attribute reduction based on neighborhood rough set[C]//2011 IEEE International Conference on Granular Computing. Kaohsiung,China,2011: 802-806. [10] MIN F, ZHU W. Attribute reduction of data with error ranges and test costs[J]. Information Sciences , 2012, 211 : 48-67 DOI:10.1016/j.ins.2012.04.031 [11] MIN F, HE H P, QIAN Y H, et al. Test-cost-sensitive attribute reduction[J]. Information Sciences , 2011, 181 : 4928-4942 DOI:10.1016/j.ins.2011.07.010
DOI: 10.3969/j.issn.1673-4785.201307010

0

#### 文章信息

JU Hengrong, MA Xingbin, YANG Xibei, QI Yunsong, YANG Jingyu

Test-cost-sensitive based variable precision classification rough set in incomplete information system

CAAI Transactions on Intelligent Systems, 2014, 9(2): 219-223
http://dx.doi.org/10.3969/j.issn.1673-4785.201307010