不完备序信息系统的模型扩展及其属性约简

南京大学学报(自然科学版) ›› 2015, Vol. 51 ›› Issue (2): 430–437.

不完备序信息系统的模型扩展及其属性约简

莫京兰1,2，吕跃进2，李金海3

出版日期:2015-03-06 发布日期:2015-03-06
作者简介:(广西科技大学鹿山学院基础教学部,柳州,545616广西大学数学与信息科学学院,南宁,530004昆明理工大学理学院,昆明 650500)
基金资助:
国家自然科学基金( 6 1 3 0 5 0 5 7 , 7 1 3 6 1 0 0 2 ) , 广西高等学校立项科研项目(2 0 1 3 L X 0 9 5 , Y B 2 0 1 4 5 0 1)

Extension of rough set model and attribute reduction in incomplete ordered information system based on dominance relation

Mo Jinglan 1,2*Lv Yuejin 2L Jinhai 3

Online:2015-03-06 Published:2015-03-06
About author:(1. Department of Basic Teaching, Lushan College of Guangxi University of Science and Technology, Liuzhou, 545616, China; 2. School of Mathematics and Information Sciences, Guangxi University, Nanning, 530004, China; 3. Faculty of Science, Kunming University of Science and Technology, Kunming, 650500, China)

摘要/Abstract

摘要： 多粒度粗糙集是目前粗糙集理论研究的一个新的方向，粒度约简是多粒度粗糙集研究的重要内容之一。首先将信息量引入悲观多粒度粗糙集的下近似分布约简，定义了悲观多粒度粗糙集下近似分布约简中粒度集的信息量。其次基于信息量定义了粒度的重要度，以粒度的重要度作为启发信息，设计了基于信息量的悲观多粒度粗糙集启发式粒度约简算法，通过实例验证了算法的有效性，为多粒度空间下粗糙集的粒度约简提供了理论依据。

Abstract: Rough set theory is an effective mathematical?tool to deal with inaccuracy, uncertainty, and incompleteness of knowledge. Note that the classical rough set theory is based on complete information systems. However, incomplete information systems are frequently encountered in the real world. As a result, extension of rough set model and attribute reduction are basic issues for incomplete ordered information systems. For the incomplete ordered information systems with missing unknown attribute values, both the generalized extended dominance relation and limited extended dominance relation are not able to compare the dominance relationship of two objects. Motivated by this problem,-dominance relation was proposed based on the probability distributions of attribute values. And then, we put forward the notion of -dominance-relation-based relative reducts and their implementation method from the perspective of matrix. Furthermore, a real example was used to show the validity and advantages of -dominance relation. Finally, we carry on the simulation experiments on UCI data sets, simulation experiments were made to illustrate that more reasonable approximation accuracy can be obtained using -dominance relation of the incomplete ordered information system. athematicalmethodAnd carries on the simulation experiments on UCI data sets, the experiment illustrate the advantages of in for the superiority of attribute reduction

莫京兰1,2，吕跃进2，李金海3. 不完备序信息系统的模型扩展及其属性约简[J]. 南京大学学报(自然科学版), 2015, 51(2): 430–437.

Mo Jinglan 1,2*Lv Yuejin 2L Jinhai 3. Extension of rough set model and attribute reduction in incomplete ordered information system based on dominance relation[J]. Journal of Nanjing University(Natural Sciences), 2015, 51(2): 430–437.

参考文献

[1].1] Pawlak Z. Rough sets. International Journal of Computer and Science, 1982, 11(5): 341~356.
[2].[2] 张文修,吴伟志. 粗糙集理论与方法北京:科学出版社, 2001.
[3].[3] 张文修,米据生吴伟志.不协调目标信息系统的知识约简计算机学报, 2003, 1(26): 1218.
[4].[4] 李金海,吕跃进.决策系统的快速属性约简算法电子科技大学学报(自然科学版), 2007, 6(36): 12371240.
[5].[5] 王丽娟,杨习贝,杨静宇等. 一种新的不完备多粒度粗糙集. 南京大学学报(自然科学), 2, 48(4): 436~444.
[6].[6] 谢骋,商琳. 基于三支决策粗糙集的视频异常行为检测.南京大学学报(自然科学), 2, 49(4): 475~482.
[7].[7] Mavrotas G, Trifillis P. Multi-criteria decision analysis with minimum information: Combining DEA with MAVT. Computers＆Operations Research, 2006, 33(8): 20832098.
[8].[8] Greco S, Matarazzo B, Slowingski R. Rough approximation of apreference relation by dominance relation. European Journal of Operation Research, 1999, 117: 63~83.
[9].[9] Greco S, Matarazzo B, Slowiflski R. Rough approximation by dominance relations. International Journal of Intelligent Systerns, 2002, 17: 153~171.
[10].[10] Shao M W, Zhang W X. Dominance relation and rules in an incomplete ordered information system. International Journal of Intelligent Systems, 2005, 20: 13~27.
[11].[11] 胡明礼,刘思峰.基于有限扩展优势关系的粗糙决策分析方法系统工程, 2006, 24(4): 106110.
[12].[12] 胡明礼,刘思峰.基于广义扩展优势关系的粗糙决策分析方法控制与决策, 2007, 22(12): 13471351.
[13].[13] 骆公志,杨晓江,周德群.基于限制扩展优势关系的粗糙决策分析模型系统管理学报,2009,184)：391396.
[14].[14] 谢军,宋余庆,陈健美等. 不完备序值决策系统中的拓展粗集模型及集对分析计算机科学, 2008, 35 (12):154157.
[15].[15] 莫京兰,朱广生.基于限制优势关系的集对粗糙决策分析模型科学技术与工程,2011, 11 (16): 242246.
[16].[16] 杨习贝,窦慧莉,宋晓宁等. 广义不完备序值系统中的优势关系粗糙集江苏科技大学学报(自然科学版), 2011, 3(25): 262267.
[17].[17] 莫京兰,吕跃进,郭恒.广义不完备信息系统中一种拓展粗糙集模型计算机工程与应用, 2012, 48(19): 126130.
[18].[18] 徐伟华.序信息系统与粗糙集北京: 科学出版社, 2013,.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed