计算机科学 ›› 2024, Vol. 51 ›› Issue (11A): 231100176-6.doi: 10.11896/jsjkx.231100176

• 大数据&数据科学 • 上一篇    下一篇

基于三支决策的差别矩阵属性约简算法

宋姝璇1, 张宇红1, 万仁霞1, 苗夺谦2   

  1. 1 北方民族大学数学与信息科学学院 银川 750021
    2 同济大学计算机科学与技术系 上海 201804
  • 出版日期:2024-11-16 发布日期:2024-11-13
  • 通讯作者: 万仁霞(wanrx1022@126.com)
  • 作者简介:(wanrx1022@126.com)
  • 基金资助:
    国家自然科学基金(62066001);宁夏自然科学基金(2021AAC03203);宁夏科技领军人才项目(2022GKLRLX08);北方民族大学研究生创新项目(YCX23088)

Attribute Reduction of Discernibility Matrix Based on Three-way Decision

SONG Shuxuan1, ZHANG Yuhong1, WAN Renxia1, MIAO Duoqian2   

  1. 1 College of Mathematics and Information Science,North Minzu University,Yinchuan 750021,China
    2 Department of Computer Science and Technology,Tongji University,Shanghai 201804,China
  • Online:2024-11-16 Published:2024-11-13
  • About author:SONG Shuxuan,born in 2000.Her main research interests include three-way decision and rough set,data mining and pattern recognition.
    WAN Renxia,born in 1975,Ph.D,professor,Ph.D supervisor.His main research interests include information systems,data mining,knowledge lear-ning,and granular computing.
  • Supported by:
    National Natural Science Foundation of China(62066001),Natural Science Foundation of Ningxia,China(2021AAC03203),Ningxia Science and Technology Leading Talent Project(2022GKLRLX08) and Graduate Innovation Project of North Minzu University (YCX23088).

摘要: 属性约简是粗糙集理论研究的核心内容之一,也是粗糙集理论的重要组成部分。该方法旨在减少冗余信息,提取出最具代表性和关键性质的属性集合。在属性约简的过程中,差别矩阵通常用于度量属性之间的关系,通过分析差别矩阵,研究者可以识别那些在描述系统行为方面贡献相似信息的属性,从而进行属性约简。基于三支决策的差别矩阵属性约简算法从差别矩阵的属性出发,首先刻画核以外的属性重要度,并以三支决策理论为基础构建一种新的属性约简方法。算法将传统概率粗糙集的上、下近似划分为三支决策中的正域、负域、边界域,基于不同的区域给出了决策规则,并通过决策损失函数来控制三支决策阈值。与同类算法相比,所提算法可以得到更为简洁的约简集和决策规则,且具有更小的时间复杂度。

关键词: 三支决策, 阈值, 差别矩阵, 重要度, 属性约简

Abstract: Attribute reduction is one of the core contents of the study of rough set theory and a crucial component of the theory itself.This approach aims to minimize redundant information and extract a set of attributes that is both representative and pivotal.In the process of attribute reduction,a difference matrix is commonly employed to measure the relationships between attributes.By analyzing the difference matrix,researchers can identify attributes that contribute similar information in describing the system's behavior,facilitating the process of attribute reduction.The three-decision-based difference matrix attribute reduction algorithm,starting from the attributes of the difference matrix,characterizes the importance of attributes beyond the core.It establishes a novel approach to attribute reduction based on the three-decision theory,dividing the upper and lower approximations of traditional probability rough sets into the positive region,negative region,and boundary region within the framework of three decisions.The proposed algorithm provides decision rules based on different regions and controls the three decision thresholds through a decision loss function.Compared to similar algorithms,it yields more concise reduction sets and decision rules,and has a lower time complexity.

Key words: Three-way decision, Threshold value, Discernibility matrix, Importance degree, Attribute reduction

中图分类号: 

  • TP391
[1]PAWLAK Z.Rough Set[J].International Journal of Parallel Programming,1982,11,341-356.
[2]LI F,YU Y T,XIAO J.Correlation Analysis of Haze and Meteo-rological Elements Based on the Rough Set Model[J].Journal of Nanchang University(Natural Science Edition),2019,43(2):187-192.
[3]ACHARJYA D P,RATHI R.An integrated fuzzy rough set and real coded genetic algorithm approach for crop identification in smart agriculture[J].Multimedia Tools and Applications,2022,81(24):35117-35142.
[4]GUESGEN H W.Using Rough Sets to Improve Activity Recognition Based on Sensor Data[J].Sensors,2020,20(6):1-10.
[5]HOSSAIN M T,WATAADA J,HERMANA M,et al.Super-vised Machine Learning in Electrofacies Classification:A Rough Set Theory Approach[J].Journal of Physics:Conference Series,2020,1529(5):052048.
[6]WANG L H,WU G F.Attribute Reduction and InformationGranularity[J].Journal of Systemics,Cybernetics and Informa-tics,2003,1(1):32-37.
[7]GAO K,TAN Y J,PAN W.Rough Set Knowledge Reduction Algorithm based on Improved Chaos Genetic Algorithm[C]//东北大学、IEEE新加坡工业电子分会.第28届中国控制与决策会议论文集(上).2016:5.
[8]HE Y,HE D.Discernibility Matrix-Based Attribute Reduction Algorithm of Decision Table[J].Advanced Materials Research,2012,1639.
[9]ZHOU Y,YANG X J,XU Y.Research on Dependency Algorithm for Attribute Reduction[J].Computer Engineering and Applications,2004(4):78-79,223.
[10]LI J L.Improved Attribute Reduction Algorithm Based on Conditional Information Entropy[J].Journal of North University of China(Natural Science Edition),2014,35(6):709-713.
[11]QIAN W B,XIONG C Z,WANG Y L.A ranking-based feature selection for multi-label classification with fuzzy relative discer-nibility[J].Applied Soft Computing,2021,102(1).
[12]HAN S Z,ZHANG N,ZHANG Z X.Specific Class β-Distribution Reduction for Interval-Valued Decision Systems[J].Journal of Shandong University(Natural Science Edition),2020,55(11):66-77.
[13]ZHANG X H,MI J S,LI M Z.Attribute Reduction and Rule Fusion in the Context of Granular Coordinated Decision Forms[J].Journal of Intelligent Systems,2019,14(6):1138-1143.
[14]KHAN M J,KUMAM P,LIU P D,et al.An adjustable weighted soft discernibility matrix based on generalized picture fuzzy soft set and its applications in decision making[J].Journal of Intelligent & Fuzzy Systems,2019,38(2).
[15]LI L T,ZHANG N,TONG X R,et al.Beta Distribution Reduction for Interval-Valued Decision Systems Based on Difference Matrix[J/OL].Computer Applications:1-11[2021-02-09].
[16]TANG Y K,ZHANG N,TONG X R,et al.Generalized Decision Reduction for Multi-Specific Class in Incomplete Decision Systems[J].Journal of Intelligent Systems,2019,14(6):1199-1208.
[17]YU T Y,ZHANG N,YUE X D,et al.Approximate Reduction Based on Multi-Specific Class in Sequential Decision Tables[J].Computer Science,2019,46(10):242-251.
[18]LI Y N,QI J J,SUN B Z,et al.Three-Decision Theory Domain Method [M].Beijing:Science Press,2019.
[19]LI F,YU Y T,XIAO J.Correlation Analysis of Haze and Meteo-rological Elements Based on the Rough Set Model[J].Journal of Nanchang University(Natural Science Edition),2019,43(2):187-192.
[20]HONG Y,YUN C,PAWAN L,et al.A three-way cluster en-semble approach for large-scale data[J].International Journal of Approximate Reasoning,2019,115.
[21]TANG G L,CHICLANA F,LIU P D.A decision-theoreticrough set model with q -rung orthopair fuzzy information and its application in stock investment evaluation[J].Applied Soft Computing Journal,2020,91.
[22]LI Z W,HUANG D.A three-way decision method in a fuzzy condition decision information system and its application in creditcard evaluation[J].Granular Computing,2020,5(4).
[23]LUO C,JU Y B,GIANNAKIS M,et al.A novel methodology to select sustainable municipal solid waste management scena-rios from three-way decisions perspective[J].Journal of Cleaner Production,2021,280(5):124312.
[24]ZHANG W X,WU W Z,LIANG J,et al.Rough Set Theory and Methods [M].Beijing:Science Press,2001.
[25]YAO Y Y.Three-way decisions with probabilistic rough sets[J].Information Sciences,2010,180:341-353.
[26]YAO Y Y.The superiority of three-way decision inprobabilistic rough set models[J].Information Sciences,2011,181:1080-1096.
[27]LIU D,LI T R,MIAO D,et al.Three-way decisions and granular computing[M].Bejing:Science Publishing,2013,332.
[28]FAN X,CHEN H M.Stepwise Optimized Feature Selection Algorithm Based on Difference Matrix and mRMR[J].Computer Science,2020,47(1):87-95.
[29]HU D Y,ZHOU J,GAO C.Fuzzy Difference Matrix Attribute Reduction Algorithm Based on Markov Blanket[J].Fuzzy Systems and Mathematics,2022,36(6):54-63.
[30]TAN A H,WU W Z,LI J J,et al.Reduction foundation with multigranulation rough sets using discernibility[J].Artificial Intelligence Review:An International Science and Engineering Journal,2020,53(4).
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!