Three-way class-specific attribute reducts based on three-way weighted combination-entropies

被引:0
作者
Tang, Lingyu [1 ]
Zhang, Xianyong [2 ]
Wang, Jun [3 ]
Zhou, Yanhong [1 ]
Zhang, Zhixi [4 ]
机构
[1] Civil Aviat Flight Univ China, Sch Sci, Guanghan 618307, Sichuan, Peoples R China
[2] Sichuan Normal Univ, Sch Math Sci, Chengdu 610066, Sichuan, Peoples R China
[3] Sichuan Normal Univ, Business Sch, Chengdu 610066, Sichuan, Peoples R China
[4] Civil Aviat Flight Univ China, Coll Air Traff Management, Guanghan 618307, Sichuan, Peoples R China
关键词
Rough set; Attribute reduction; Class-specific attribute reducts; Information theory; Three-way decision; Granular computing; DECISION;
D O I
10.1007/s13042-025-02532-0
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Attribute reduction plays a fundamental role in data analysis, and it mainly resorts to algebraic and informational measures. Class-specific attribute reducts recently emerge for decision class optimization, and their algebraic type is initial while their informational types need developing. In this paper, three-way informational class-specific attribute reducts (including prior, posterior, and likelihood types) are established by introducing three-way weighted combination-entropies, which are hierarchically constructed for uncertainty measurement, and both their mutual relationships with algebraic class-specific reducts and their internal relationships with three-way informational systematicness are revealed. At first, three-way informational class-specific reducts are defined based on prior, posterior, and likelihood weighted combination-entropies, and their basic properties and heuristic algorithms are given. Then, optimization preservation conditions of three-way weighted combination-entropies are deeply mined to describe three-way informational reduction targets; thus, systematic relationships among informational and algebraic class-specific reducts are investigated, and relevant reduction strength and balance are acquired to generate derivation properties and algorithms of class-specific reducts. Finally, theoretical constructions and systematic connections of three-way class-specific reducts are validated via table examples and dataset experiments. This study deepens three-way uncertainty measurement and attribute reduction at the level of decision class, so it enriches three-way decision in terms of granular computing.
引用
收藏
页码:4627 / 4654
页数:28
相关论文
共 50 条
[21]   The geometry of three-way decision [J].
Yao, Yiyu .
APPLIED INTELLIGENCE, 2021, 51 (09) :6298-6325
[22]   Three-Way Spectral Clustering [J].
Shi, Hong ;
Liu, Qiang ;
Wang, Pingxin .
FOUNDATIONS OF INTELLIGENT SYSTEMS (ISMIS 2018), 2018, 11177 :389-398
[23]   Three-way rough semiconcept [J].
Mao, Hua ;
Cheng, Yilin .
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2021, 40 (03) :4317-4330
[24]   A three-way efficacy evaluation approach with attribute reduction based on weighted temporal fuzzy rough sets [J].
Ye, Jin ;
Sun, Bingzhen ;
Zhao, Xixuan ;
Chu, Xiaoli .
INFORMATION SCIENCES, 2025, 712
[25]   Intuitionistic Fuzzy Three-Way Decision Model Based on the Three-Way Granular Computing Method [J].
Xin, Xianwei ;
Song, Jihua ;
Peng, Weiming .
SYMMETRY-BASEL, 2020, 12 (07)
[26]   On two novel types of three-way decisions in three-way decision spaces [J].
Hu, Bao Qing ;
Wong, Heung ;
Yiu, Ka-fai Cedric .
INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, 2017, 82 :285-306
[27]   Influence of Attribute Granulation on Three-Way Concept Lattices [J].
Long, Jun ;
Li, Yinan ;
Yang, Zhan .
BIG DATA MINING AND ANALYTICS, 2024, 7 (03) :655-667
[28]   Characteristics of three-way concept lattices and three-way rough concept lattices [J].
Yu, Huiying ;
Li, Qingguo ;
Cai, Mingjie .
KNOWLEDGE-BASED SYSTEMS, 2018, 146 :181-189
[29]   An Attribute Reduction Method Based On Three-Way Decisions Model for Decision Tables [J].
Yin, Linzi ;
Xu, Xuemei ;
Ding, Jiafeng ;
Jiang, Zhaohui ;
Sun, Kehui .
PROCEEDINGS OF THE 30TH CHINESE CONTROL AND DECISION CONFERENCE (2018 CCDC), 2018, :381-386
[30]   A novel attribute reduction algorithm based on granular sequential three-way decision [J].
Chen, Yuliang ;
Cheng, Yunlong ;
Luo, Binbin ;
Shao, Yabin ;
Zhao, Mingfu ;
Zhang, Qinghua .
INFORMATION SCIENCES, 2025, 694