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

[21] Sensitivity and specificity based multiobjective approach for feature selection: Application to cancer diagnosis
Garcia-Nieto, J.
Alba, E.
Jourdan, L.
Talbi, E.
INFORMATION PROCESSING LETTERS, 2009, 109 (16) : 887 - 896
[22] An Enhanced Diabetes Mellitus Prediction Using Feature Selection-Based Type-2 Fuzzy Model
Awotunde, Joseph Bamidele
Misra, Sanjay
Pham, Quoc Trung
FUTURE DATA AND SECURITY ENGINEERING. BIG DATA, SECURITY AND PRIVACY, SMART CITY AND INDUSTRY 4.0 APPLICATIONS, FDSE 2022, 2022, 1688 : 625 - 639
[23] Feature Selection for Microarray Data by AUC Analysis
Canul-Reich, Juana
Hall, Lawrence O.
Goldgof, Dmitry
Eschrich, Steven A.
2008 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC), VOLS 1-6, 2008, : 768 - +
[24] MaskedPainter: Feature selection for microarray data analysis
Apiletti, Daniele
Baralis, Elena
Bruno, Giulia
Fiori, Alessandro
INTELLIGENT DATA ANALYSIS, 2012, 16 (04) : 717 - 737
[25] Fuzzy Feature Selection Based On Interval Type-2 Fuzzy Sets
Cherif, Sahar
Baklouti, Nesrine
Alimi, Adel
Snasel, Vaclav
NINTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2016), 2017, 10341
[26] A novel hybrid feature selection method based on dynamic feature importance
Wei, Guangfen
Zhao, Jie
Feng, Yanli
He, Aixiang
Yu, Jun
APPLIED SOFT COMPUTING, 2020, 93
[27] Infinite Feature Selection: A Graph-based Feature Filtering Approach
Roffo, Giorgio
Melzi, Simone
Castellani, Umberto
Vinciarelli, Alessandro
Cristani, Marco
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (12) : 4396 - 4410
[28] Principal Component Analysis With Fuzzy Elastic Net for Feature Selection
Gao, Yunlong
Wu, Qinting
Xu, Zhenghong
Cao, Chao
Pan, Jinyan
Shao, Guifang
Nie, Feiping
Zhu, Qingyuan
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2024, 32 (12) : 6878 - 6890
[29] An efficient feature selection framework based on information theory for high dimensional data
Manikandan, G.
Abirami, S.
APPLIED SOFT COMPUTING, 2021, 111
[30] A graph partitioning-based hybrid feature selection method in microarray datasets
Oubaouzine, Abdelali
Ouaderhman, Tayeb
Chamlal, Hasna
KNOWLEDGE AND INFORMATION SYSTEMS, 2025, 67 (01) : 633 - 660

← 1 2 3 4 5 →