Semi-supervised attribute reduction for interval data based on misclassification cost

被引：8

作者：

Dai, Jianhua ^{[1
,2
,3
]}

Liu, Qiong ^{[1
,2
,3
]}

机构：

[1] Hunan Normal Univ, Hunan Prov Key Lab Intelligent Comp & Language In, Changsha 410081, Peoples R China

[2] Hunan Normal Univ, Coll Informat Sci & Engn, Changsha 410081, Peoples R China

[3] Hunan Xiangjiang Artificial Intelligence Acad, Changsha 410081, Peoples R China

来源：

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS | 2022年 / 13卷 / 06期

基金：

中国国家自然科学基金;

关键词：

Attribute reduction; Interval data; Neighborhood rough set; KL divergence; Misclassification cost; Semi-supervised; ROUGH SET APPROACH; FEATURE-SELECTION; INFORMATION; UNCERTAINTY;

D O I：

10.1007/s13042-021-01483-6

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 is a key issue in rough set theory which is widely used to handle uncertain knowledge. In reality, partially labeled interval data exist widely. So far, there are very few studies on partially labeled interval information systems. In this paper, we first define the concept of interval neighborhood by means of Kullback-Leibler (KL) divergence and standard deviation. Then a method is proposed to estimate the missing label by the nearest labeled objects to an unlabeled object and the cost of misclassification is constructed. Next a new entropy structure based on misclassification cost is proposed. After that, a semi-supervised attribute reduction method for partially labeled interval data is advanced. Finally, The rationality and validity of the method are demonstrated by experimental comparison.

引用

页码：1739 / 1750

页数：12

共 24 条

[1] Maximal-Discernibility-Pair-Based Approach to Attribute Reduction in Fuzzy Rough Sets [J].

Dai, Jianhua ;

Hu, Hu ;

Wu, Wei-Zhi ;

Qian, Yuhua ;

Huang, Debiao .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2018, 26 (04) :2174-2187

[2] Locally Linear Approximation Approach for Incomplete Data [J].

Dai, Jianhua ;

Hu, Hu ;

Hu, Qinghua ;

Huang, Wei ;

Zheng, Nenggan ;

Liu, Liang .

IEEE TRANSACTIONS ON CYBERNETICS, 2018, 48 (06) :1720-1732

[3] Uncertainty measurement for incomplete interval-valued information systems based on α-weak similarity [J].

Dai, Jianhua ;

Wei, Bingjie ;

Zhang, Xiaohong ;

Zhang, Qilai .

KNOWLEDGE-BASED SYSTEMS, 2017, 136 :159-171

[4] Attribute Selection for Partially Labeled Categorical Data By Rough Set Approach [J].

Dai, Jianhua ;

Hu, Qinghua ;

Zhang, Jinghong ;

Hu, Hu ;

Zheng, Nenggan .

IEEE TRANSACTIONS ON CYBERNETICS, 2017, 47 (09) :2460-2471

[5] DualPOS: A Semi-supervised Attribute Selection Approach for Symbolic Data Based on Rough Set Theory [J].

Dai, Jianhua ;

Han, Huifeng ;

Hu, Hu ;

Hu, Qinghua ;

Zhang, Jinghong ;

Wang, Wentao .

WEB-AGE INFORMATION MANAGEMENT, PT II, 2016, 9659 :392-402

[6] Uncertainty measurement for interval-valued information systems [J].

Dai, Jianhua ;

Wang, Wentao ;

Mi, Ju-Sheng .

INFORMATION SCIENCES, 2013, 251 :63-78

[7] Entropy measures and granularity measures for set-valued information systems [J].

Dai, Jianhua ;

Tian, Haowei .

INFORMATION SCIENCES, 2013, 240 :72-82

[8] Attribute selection based on a new conditional entropy for incomplete decision systems [J].

Dai, Jianhua ;

Wang, Wentao ;

Tian, Haowei ;

Liu, Liang .

KNOWLEDGE-BASED SYSTEMS, 2013, 39 :207-213

[9] Attribute selection based on information gain ratio in fuzzy rough set theory with application to tumor classification [J].

Dai, Jianhua ;

Xu, Qing .

APPLIED SOFT COMPUTING, 2013, 13 (01) :211-221

[10] Approximations and uncertainty measures in incomplete information systems [J].

Dai, Jianhua ;

Xu, Qing .

INFORMATION SCIENCES, 2012, 198 :62-80

← 1 2 3 →