Comments on "fuzzy probabilistic approximation spaces and their information measures"

被引:19
作者
Hu, Qinghua [1 ]
Xie, Zongxia [1 ]
Yu, Daren [1 ]
机构
[1] Harbin Inst Technol, Harbin 150001, Heilonghiang Pr, Peoples R China
关键词
entropy; feature selection; fuzzy set; information measure; rough set;
D O I
10.1109/TFUZZ.2007.896321
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Some errors in our original paper in defining relative reduct with information measures are pointed out in this paper. It is shown that in our original work, Theorems 10 and 19 hold just under the condition that decision tables are consistent. We also show that an attribute reduction algorithm based on the entropies can be used to select features in practical applications although the two theorems do not hold in inconsistent cases.
引用
收藏
页码:549 / 551
页数:3
相关论文
共 6 条
[1]  
[Anonymous], 2002, CHINESE J COMPUTERS
[2]   ROUGH FUZZY-SETS AND FUZZY ROUGH SETS [J].
DUBOIS, D ;
PRADE, H .
INTERNATIONAL JOURNAL OF GENERAL SYSTEMS, 1990, 17 (2-3) :191-209
[3]   Fuzzy probabilistic approximation spaces and their information measures [J].
Hu, QH ;
Yu, DR ;
Xie, ZX ;
Liu, JF .
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2006, 14 (02) :191-201
[4]   Information-preserving hybrid data reduction based on fuzzy-rough techniques [J].
Hu, QH ;
Yu, DR ;
Xie, ZX .
PATTERN RECOGNITION LETTERS, 2006, 27 (05) :414-423
[5]   On the generalization of fuzzy rough sets [J].
Yeung, DS ;
Chen, DG ;
Tsang, ECC ;
Lee, JWT ;
Wang, XZ .
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2005, 13 (03) :343-361
[6]   Using rough sets with heuristics for feature selection [J].
Zhong, N ;
Dong, J ;
Ohsuga, S .
JOURNAL OF INTELLIGENT INFORMATION SYSTEMS, 2001, 16 (03) :199-214