AFNFS: Adaptive fuzzy neighborhood-based feature selection with adaptive synthetic over-sampling for imbalanced data

被引：29

作者：

Sun, Lin ^{[1
,3
]}

Li, Mengmeng ^{[1
]}

Ding, Weiping ^{[2
]}

Zhang, En ^{[1
]}

Mu, Xiaoxia ^{[1
]}

Xu, Jiucheng ^{[1
]}

机构：

[1] Henan Normal Univ, Coll Comp & Informat Engn, Xinxiang 453007, Peoples R China

[2] Nantong Univ, Sch Informat Sci & Technol, Nantong 226019, Peoples R China

[3] Engn Lab Intelligence Business & Internet Things H, Xinxiang 453007, Peoples R China

来源：

INFORMATION SCIENCES | 2022年 / 612卷

基金：

中国国家自然科学基金;

关键词：

Imbalanced data classification; Feature selection; Adaptive fuzzy neighborhood; Fuzzy neighborhood rough sets; Over-sampling; MUTUAL INFORMATION; ROUGH SETS; CLASSIFICATION;

D O I：

10.1016/j.ins.2022.08.118

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The classification efficiency of majority classes for imbalanced data is so concerned in real -world applications. Almost fuzzy neighborhood radius still needs to be manually set and many entropy measures may ignore the boundary region of data, these limitations will result in the poor classification effect. To address these limitations, this paper designs a novel adaptive fuzzy neighborhood-based feature selection method for imbalanced data with adaptive synthetic over-sampling. First, the closeness is defined according to the vari-ance distance between the samples of the minority class, the pair set of neighboring sam-ples is designed, and then an improved adaptive synthetic over-sampling model is presented for constructing balanced decision systems consisting of the synthetic samples and original samples. Second, an adaptive fuzzy neighborhood radius is developed when using the data margins of all homogeneous and heterogeneous samples. Then the adaptive fuzzy neighborhood granule and upper and lower approximations are defined to construct a new FNRS model. Thus, approximate accuracy and roughness are presented to measure the uncertainty from the fuzzy and rough perspectives for imbalanced data. Third, by com-bining the roughness with adaptive fuzzy neighborhood entropy, adaptive fuzzy neighbor-hood joint entropy is constructed to evaluate the uncertainty in fuzzy neighborhood decision systems from two viewpoints of algebra and information. Then the reduced set and the significance of the feature are further developed. Finally, this improved adaptive synthetic over-sampling algorithm is designed to aim to build this balanced decision sys-tem, and an adaptive fuzzy neighborhood-based feature selection algorithm with the tol-erance parameter is developed to achieve an optimal feature subset. Experiments on 26 imbalanced datasets demonstrate that the constructed algorithms compared to the other related algorithms are effective.(c) 2022 Elsevier Inc. All rights reserved.

引用

页码：724 / 744

页数：21

共 50 条

[31] Feature selection using Fisher score and multilabel neighborhood rough sets for multilabel classification [J].

Sun, Lin ;

Wang, Tianxiang ;

Ding, Weiping ;

Xu, Jiucheng ;

Lin, Yaojin .

INFORMATION SCIENCES, 2021, 578 :887-912

[32] Multilabel feature selection using ML-ReliefF and neighborhood mutual information for multilabel neighborhood decision systems [J].

Sun, Lin ;

Yin, Tengyu ;

Ding, Weiping ;

Qian, Yuhua ;

Xu, Jiucheng .

INFORMATION SCIENCES, 2020, 537 :401-424

[33] Feature Selection Using Fuzzy Neighborhood Entropy-Based Uncertainty Measures for Fuzzy Neighborhood Multigranulation Rough Sets [J].

Sun, Lin ;

Wang, Lanying ;

Ding, Weiping ;

Qian, Yuhua ;

Xu, Jiucheng .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2021, 29 (01) :19-33

[34] Neighborhood multi-granulation rough sets-based attribute reduction using Lebesgue and entropy measures in incomplete neighborhood decision systems [J].

Sun, Lin ;

Wang, Lanying ;

Ding, Weiping ;

Qian, Yuhua ;

Xu, Jiucheng .

KNOWLEDGE-BASED SYSTEMS, 2020, 192

[35] Hybrid Multilabel Feature Selection Using BPSO and Neighborhood Rough Sets for Multilabel Neighborhood Decision Systems [J].

Sun, Lin ;

Yin, Tengyu ;

Ding, Weiping ;

Xu, Jiucheng .

IEEE ACCESS, 2019, 7 :175793-175815

[36] Feature selection using Lebesgue and entropy measures for incomplete neighborhood decision systems [J].

Sun, Lin ;

Wang, Lanying ;

Qian, Yuhua ;

Xu, Jiucheng ;

Zhang, Shiguang .

KNOWLEDGE-BASED SYSTEMS, 2019, 186

[37] Feature selection using neighborhood entropy-based uncertainty measures for gene expression data classification [J].

Sun, Lin ;

Zhang, Xiaoyu ;

Qian, Yuhua ;

Xu, Jiucheng ;

Zhang, Shiguang .

INFORMATION SCIENCES, 2019, 502 :18-41

[38] Cost-sensitive boosting for classification of imbalanced data [J].

Sun, Yamnin ;

Kamel, Mohamed S. ;

Wong, Andrew K. C. ;

Wang, Yang .

PATTERN RECOGNITION, 2007, 40 (12) :3358-3378

[39]

Ting KM, 2002, IEEE T KNOWL DATA EN, V14, P659, DOI 10.1109/TKDE.2002.1000348

[40] Under-sampling class imbalanced datasets by combining clustering analysis and instance selection [J].

Tsai, Chih-Fong ;

Lin, Wei-Chao ;

Hu, Ya-Han ;

Yao, Guan-Ting .

INFORMATION SCIENCES, 2019, 477 :47-54

← 1 2 3 4 5 →