南京大学学报(自然科学版) ›› 2013, Vol. 49 ›› Issue (2): 133–141.

• •    下一篇

 一种有效的基于风险最小化的属性约简算法*

 于洪**,姚园,赵军
  

  • 出版日期:2015-10-29 发布日期:2015-10-29
  • 作者简介: (重庆邮电大学计算智能重庆市重点实验室,重庆,400065)
  • 基金资助:
     国家自然科学基金(61073146,61272060),重庆市自然科学基金(cstc2011jjA40045)

 An attribute reduction algorithm based on risk minimization

 Yu Hong,Yuo Yuan,Zhuo Jun
  

  • Online:2015-10-29 Published:2015-10-29
  • About author: (Chongqing Key Laboratory of Computational lntelligence,Chongqing University of Posts and
    Telecommunications, Chongqing, 400065 , China)

摘要:  基于粗糙集理论定义的属性约简大都要求约简前后正区域保持不变或者非负区域不变.在概
率型决策粗糙集模型卜,决策区域和决策规则与属性增减之间并不具备单调性.因此,决策者基于约简
后的属性集合所作的决策风险最小就变得非常有意义.针对这种与各个区域无关的基于决策风险最小
化的属性约简进行了研究.考虑到不同属性对决策表的决策分类能力不同,提出了基于决策粗糙集模型
的属性重要性概念,设计了一种有效的基于属性重要性的决策风险最小化启发式属性约简算法.实例分
析与对比实验结果说明新方法是有效的.

Abstract:  The most important part of the classical rough set theory is upper approximate set and lower approxi-
mate set which is defined by accurate set inclusion. However the data at present is not accurate. As we all known,the
Pawlak algebra rough set model is too rigid to lack fault tolerance capability.ln order to solve this problem,a bunch
of probabilistic rough set models were proposed. Among these models the decision rough set model simulated better
than others in human intelligence solving problems from semantic perspective.
Attribute reduction is one important research field in rough set theory.The decision region,decision rule and the
increase or decrease of attributes are not following monotonicity in the models of probability decision rough set,the
positive region,negativc region and border region of decision table maybe change differently before and after attribute
reduction,therefore it’s a important problem to evaluate attribute reduction is appropriate according to regions
change.Therefore the definition of attribute reduction based on risk minimization under decision rough set model was
proposed in order to solve this problem.
The definition of attribute reduction based on rough set theory mostly requires that positive or nonnegative re
gion are the same as before. Decision region,decision rule and the increase or decrease of attributes are not following
monotonicity in the model of probability decision rough set.Therefore,it is very meaningful to minimize the decision
risk according to attributes sets after reduction for decision makers.This paper studies the attribute reduction based
on the minimum risk decision which has nothing to do with every region. Considering different attributes has differ-
ent abilities to decide and make classification to decision table, an attribute significance concept based on decision
rough set model was proposed,then we propose an effective decision-making risk minimization heuristic attribute re
Examples analysis and experiment results comparison show new method is effective.

[1]Wang G Y,Yao Y Y,Yu H. A survey on rough set theory and applications. Chinese Journal of
Computers,2009 , 32( 7) ; 1229 - 1246.(粗糙集理论与应用研究综述.计算机学报,2009,32(7); 1229一1246).
[2]Wang L,Qiu T R,He N,et al. A method for fea- ture selection based on rough sets and ant colony
optimization algorithm. Journal of Nanjing Uni- versity( Natural Sciences),2010,46(5):487一
493.(王璐,邱桃荣,何妞等.基于粗糙集和蚁群优化算法的特征选择方法.南京大学学报(自然科学),2010,46(5):487-493).
[3]Yao Y Y. A decision theoretic framework for ap- proximating concepts, international Journal of
Man-machine Studies,l992,37(6):793一809.
[4]Yao Y Y.The superiority of three-way decisions in probabilistic rough set models. Information Sciences.2011,181(6):1080一1096.
[5]Yao Y Y,Mi J S, Li Z J. Attribute reduction based on generalized fuzzy evidence theory in
fuzzy decision systems. Fuzzy Sets and Systems,2011,170(1):64一75.
[6]Xu W H,Zhang X Y,Zhang W X. Lower ap- proximation reduction in inconsistent information
systems based on dominance relations. Computer Engineering and Applications, 2009,45(16):
191-193.(徐伟华,张晓燕,张文修.优势关系下不协调目标信息系统的上近似约简.计算机工程,2009,36(18):191一193).
[7]Hu Q H, Zhao H, Xie Z X , et al. Consistency based attribute reduction. Proceedings of the 11th Pacific-A-
sia conference on Advances in knowledge discovery and data mining. Heidelberg;Springer,2007,96一107.
[8]Wu W Z. Attribute reduction based on evidence the ory in incomplete decision systems, information Sci-
ences 2008,178:1355一1371.
[9]Yu H,Yang D C. Approach to solving attribute reductions with ant colony optimization. Pattern
Recognition and Artificial intelligence, 2011,24 (02):176-184.(于洪,杨大春.基于蚁群优化
的多个属性约简的求解方法.模式识别与人工智能,2011,24(02):176一184).
[10]Miao D Q, Zhou J,Zhang N, et al. Research of at- tribute reduction based on algebraic equations. Acta Electronica Sinica,2010,38(5):1021一1027.(苗夺谦,周杰,张楠等.基于代数方程组的属性约简研究.电子学报,2010,38(5) :1021一1027).
[11]Chen Y M, Wu K S, Sun J H. Minimal attribute re- duction based on power set tree in decision table.
Journal of Nanjing University(Natural Sciences), 2012,48(2);164-171.陈玉明,吴可寿,孙金华.
基于幂树的决策表最小属性约简.南京大学学报(自然科学),2012,48(2);164-171).
[12]Chen H Y, Jun A Z, Zhen Q. The core of attributes and minimal attributes reduction in variable precision
rough set. Chinese Journal of Computers, 2012,35 (5):1011一1017.陈昊,杨俊安,庄镇泉.变精
度粗糙集的属性核和最小属性约简算法.计算机学报,2012,35(6):1011一1017).
[13]Jia X Y, Li W W, Shang L, et al. An optimization viewpoint of decision一Theoretic rough set model.
Proceedings of the 6th International Conference on Rough Sets and Knowledge Technology. Berlin, Hei-
delberg; Springer-Verlag, 201 1 , 457一465.
[14]Jia X Y,Shang L,Chen J J. Attribute reduction based on minimum decision cost. Journal of Fron- tiers of Computer Science and Techonology, 2011,5(2):155一160.(贾修一,商琳,陈家骏. 决策风险最小化属性约简.计算机科学与探索,2011,5(2):155一160.
[15]Li H X,Zhou X Z,Li T R,et al. Decision rough sets and it’s research progress. Beijing; Science
Press,2011,31-49.(李华雄,周献中,李天瑞等. 决策粗糙集理论及其研究进展.北京:科学出版社,2011,31一49).
[16]Wang G Y,Zheng G, Zhang Y. RIDAS-A rough set based intelligent data analysis system. Pro-
cecdings of the First International Conference on Machine Learning and Cybernetics,Beijing, 2002: 646一649.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!