Feature selection based on sensitivity analysis of fuzzy ISODATA

被引：24

作者：

Liu, Quanjin ^{[1
,2
]}

Zhao, Zhimin ^{[1
]}

Li, Ying-Xin ^{[3
]}

Li, Yuanyuan ^{[1
]}

机构：

[1] Nanjing Univ Aeronaut & Astronaut, Coll Sci, Nanjing 210016, Jiangsu, Peoples R China

[2] AnQing Normal Coll, Sch Phys & Elect Engn, Anqing 246011, Peoples R China

[3] Beijing Jingwei Text Machinery New Technol Co Ltd, Inst Machine Vis & Machine Intelligence, Beijing 100176, Peoples R China

来源：

NEUROCOMPUTING | 2012年 / 85卷

基金：

中国国家自然科学基金; 高等学校博士学科点专项科研基金;

关键词：

Feature selection; Fuzzy ISODATA; Sensitivity analysis; Microarray; Classification; Clustering; SUPPORT VECTOR MACHINES; CANCER-DIAGNOSIS; MICROARRAY DATA; GENE SELECTION; CLASSIFICATION; ALGORITHM; PERFORMANCE; PREDICTION; WRAPPERS; TUMOR;

D O I：

10.1016/j.neucom.2012.01.005

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A feature selection method based on sensitivity analysis and the fuzzy Interactive Self-Organizing Data Algorithm (ISODATA) is proposed for selecting features from high dimensional gene expression data sets. First, feature sensitivities for discriminating classes are calculated on the basis of the fuzzy ISODATA method. Then, candidate feature subsets are generated according to feature sensitivities with the recursive feature elimination procedure. Finally, the obtained optimal feature subsets are evaluated using both supervised and unsupervised methods to validate their abilities for separating different categories. The proposed method is applied to five microarray datasets, and the experimental results indicate its effectiveness. (c) 2012 Elsevier B.V. All rights reserved.

引用

页码：29 / 37

页数：9

共 50 条

[1] SVM-FuzCoC: A novel SVM-based feature selection method using a fuzzy complementary criterion
Moustakidis, S. P.
Theocharis, J. B.
PATTERN RECOGNITION, 2010, 43 (11) : 3712 - 3729
[2] Training error and sensitivity-based ensemble feature selection
Ng, Wing W. Y.
Tuo, Yuxi
Zhang, Jianjun
Kwong, Sam
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2020, 11 (10) : 2313 - 2326
[3] An unsupervised approach to feature discretization and selection
Ferreira, Artur J.
Figueiredo, Mario A. T.
PATTERN RECOGNITION, 2012, 45 (09) : 3048 - 3060
[4] Feature selection via Boolean independent component analysis
Apolioni, Bruno
Bassis, Simone
Brega, Andrea
INFORMATION SCIENCES, 2009, 179 (22) : 3815 - 3831
[5] A fuzzy clustering based algorithm for feature selection
Sun, HJ
Wang, SR
Mei, Z
2002 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-4, PROCEEDINGS, 2002, : 1993 - 1998
[6] Sensitivity Analysis for Feature Selection
Kamalov, Firuz
2018 17TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA), 2018, : 1466 - 1470
[7] A feature selection approach based on sensitivity of RBFNNs
Zeng, Xiaoqin
Zhen, Zhilong
He, Jiasheng
Han, Lixin
NEUROCOMPUTING, 2018, 275 : 2200 - 2208
[8] A Novel Feature Selection Method Based on Correlation-Based Feature Selection in Cancer Recognition
Lu, Xinguo
Peng, Xianghua
Deng, Yong
Feng, Bingtao
Liu, Ping
Liao, Bo
JOURNAL OF COMPUTATIONAL AND THEORETICAL NANOSCIENCE, 2014, 11 (02) : 427 - 433
[9] Multimodal feature selection from microarray data based on Dempster-Shafer evidence fusion
Nekouie, Nadia
Romoozi, Morteza
Esmaeili, Mahdi
JOURNAL OF SUPERCOMPUTING, 2023, 79 (11) : 12591 - 12621
[10] A new filter-based Gene selection method based on dragonfly optimization and correlation-based feature selection
Ghoneimy, Mohamed
Nabil, Emad
Badr, Amr
El-Khamisy, Sherif F.
BIOSCIENCE RESEARCH, 2019, 16 (03): : 3139 - 3154

← 1 2 3 4 5 →