计算机科学 ›› 2016, Vol. 43 ›› Issue (Z6): 40-43.doi: 10.11896/j.issn.1002-137X.2016.6A.008

• 智能计算 • 上一篇    下一篇

基于联合属性重要度的决策风险最小化属性约简

徐菲菲,毕忠勤,雷景生   

  1. 上海电力学院计算机科学与技术学院 上海200090,上海电力学院计算机科学与技术学院 上海200090,上海电力学院计算机科学与技术学院 上海200090
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金(61272437,4),上海市教育发展基金会和上海市教育委员会“晨光计划”(13CG58),上海市自然科学基金(13ZR1417500)资助

Attribute Reduction Based on Cost Minimization and Significance of Joint Attributes

XU Fei-fei, BI Zhong-qin and LEI Jing-sheng   

  • Online:2018-12-01 Published:2018-12-01

摘要: 经典粗糙集属性约简基本都是保持正域、负域和边界域不变,而决策粗糙集对属性的增减过程不具备单调性,因此不可能同时保持3个区域均不变。在决策粗糙集模型中,作出决策更应该考虑风险最小化原则,因此提出一种改进的风险最小化属性约简方法,在属性的选取过程中同时考虑所选取的属性子集对决策的划分能力,即联合属性重要度以及风险最小化。实验证明所提方法是有效的。

关键词: 属性约简,风险最小化,联合属性重要度,决策粗糙集

Abstract: The classical rough set attribute reduction is mainly based on maintaining positive region,boundary region and negative region unchanged.In the decision rough set model,the reduction procedure for adding or deleting an attri-bute is no longer monotonous,so that three regions can not keep all unchanged.In decision theoretic rough set model,decision making should take consideration of minimizing the cost.Therefore,this paper put forward a method for attribute reduction based on minimizing the cost,while considering the classification ability of selected attribute subset to the decision-making,which is named as the significance of joint attributes.Experiments show that our method is effective.

Key words: Attribute reduction,Minimum cost,Significance of joint attributes,Decision rough sets

[1] Pawlak Z.Rough sets,International Journal of Computer and Information Sciences,1982,11(5):341-356
[2] 王国胤,姚一豫,于洪.粗糙集理论与应用研究综述[J].计算机学报,2009,2(7):1229-1246
[3] Mac P N,Shen Q J R.Rough and fuzzy-rough methods for mammographic data analysis[J].Intelligent Data Analysis-An International Journal,2010,4(2):225-244
[4] Zhu W.Topological approaches to covering rough sets[J].Information Sciences,2007,177(6):1499-1508
[5] Qian Y,Liang J,Yao Y,et al.MGRS:A multi-granulation rough set[J].Information Sciences,2010,0(6):949-970
[6] Suyun Z,Tsang E,Degang C.The Model of Fuzzy Variable Precision Rough Sets[J].IEEE Transactions on Fuzzy Systems,2009,17(2):451-467
[7] 黄兵,胡作进,周献中.优势模糊粗糙模型及其在审计风险评估中的应用[J].控制与决策,2009,4(6):899-902
[8] Xu F F,Miao D Q,Wei L.Fuzzy-rough attribute reduction via mutual information with an application to cancer classification[J].Computers & Mathematics with Applications,2009,7(6):1010-1017
[9] 胡清华,赵辉,于达仁.基于邻域粗糙集的符号与数值属性快速约简算法[J].模式识别与人工智能,2008,1(6):732-738
[10] Liang J Y,Qian Y H,Pedrycz W,et al.An efficient accelerator for attribute reduction from incomplete data in rough set framework[J].Pattern Recognition,2011,4(8):1658-1670
[11] 钱进,苗夺谦,张志华,等.MapReduce框架下并行知识约简算法模型研究[J].计算机科学与探索,2013,7(1):35-45
[12] Pawlak Z,Wong S K M,ZiarkoW.Roughsets:probabilistic versus deterministic approach[J].Inter.Journal of Man-MachineStudies,1988,9(1):81-95
[13] Hu Qing-hua,Yu Da-ren,Liu Jin-fu,et al.Neighborhood rough set based heterogeneous feature subset selection[J].Information Sciences,2008,178(18):3577-3594
[14] Yao Y Y,Wong S K M.A decision theoretic framework for approximating concepts[J].Inter.Journal of Man-machine Stu-dies,1992,7(6):793-809
[15] Yao Y Y.The superiority of three-way decisions in probabilistic rough set models[J].Information Sciences,2011,181(6):1080-1096
[16] Yao Y Y,Zhao Y.Attribute reductions in decision-theoreticrough set models[J].Information Sciences,2008,178(17):3356-3373
[17] Li H X,Zhou X Z,Zhao J B,et al.Attribute reduction in decision-theoretic rough set model:a further investigation[C]∥Proceedings of RSKT2011.LNCS,vol.6954,2011:466-475
[18] Jia Xiu-yi,Liao Wen-he,Tang Zhen-min,et al.Minimum cost attribute reduction in decision-theoretic rough set models[J].Information Sciences,2013,219(10):151-167
[19] 于洪,姚园,赵军.一种有效的基于风险最小化的属性约简算法[J].南京大学学报(自然科学),2013,49(2):210-216
[20] Zhang Xian-yong,Miao Duo-qian.Region-based quantitative and hierarchical attribute reduction in the two-category decision theoretic rough set model[J].Knowledge-Based Systems,2014,1(11):146-161

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!