A tutorial on support vector machine-based methods for classification problems in chemometrics

被引:252
作者
Luts, Jan [1 ]
Ojeda, Fabian [1 ]
Van de Plas, Raf [1 ,2 ]
De Moor, Bart [1 ]
Van Huffel, Sabine [1 ]
Suykens, Johan A. K. [1 ]
机构
[1] Katholieke Univ Leuven, Dept Elect Engn ESAT, Res Div SCD, B-3001 Louvain, Belgium
[2] Katholieke Univ Leuven, Interfac Ctr Prote & Metab, ProMeTa, B-3000 Louvain, Belgium
关键词
Support vector machine; Least squares support vector machine; Kernel logistic regression; Kernel-based learning; Feature selection; Multi-class probabilities; IMAGING MASS-SPECTROMETRY; STATISTICAL COMPARISONS; CROSS-VALIDATION; BAYESIAN METHODS; CLASSIFIERS; MULTICLASS; EXPRESSION; SELECTION; REGULARIZATION; REGRESSION;
D O I
10.1016/j.aca.2010.03.030
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
This tutorial provides a concise overview of support vector machines and different closely related techniques for pattern classification. The tutorial starts with the formulation of support vector machines for classification. The method of least squares support vector machines is explained. Approaches to retrieve a probabilistic interpretation are covered and it is explained how the binary classification techniques can be extended to multi-class methods. Kernel logistic regression, which is closely related to iteratively weighted least squares support vector machines, is discussed. Different practical aspects of these methods are addressed: the issue of feature selection, parameter tuning, unbalanced data sets, model evaluation and statistical comparison. The different concepts are illustrated on three real-life applications in the field of metabolomics, genetics and proteomics. (C) 2010 Elsevier B.V. All rights reserved.
引用
收藏
页码:129 / 145
页数:17
相关论文
共 86 条
[51]   A note on Platt's probabilistic outputs for support vector machines [J].
Lin, Hsuan-Tien ;
Lin, Chih-Jen ;
Weng, Ruby C. .
MACHINE LEARNING, 2007, 68 (03) :267-276
[52]   Brain tumor classification based on long echo proton MRS signals [J].
Lukas, L ;
Devos, A ;
Suykens, JAK ;
Vanhamme, L ;
Howe, FA ;
Majós, C ;
Moreno-Torres, A ;
Van Der Graaf, M ;
Tate, AR ;
Arús, C ;
Van Huffel, S .
ARTIFICIAL INTELLIGENCE IN MEDICINE, 2004, 31 (01) :73-89
[53]   Nosologic imaging of the brain: segmentation and classification using MRI and MRSI [J].
Luts, Jan ;
Laudadio, Teresa ;
Idema, Albert J. ;
Simonetti, Arjan W. ;
Heerschap, Arend ;
Vandermeulen, Dirk ;
Suykens, Johan A. K. ;
Van Huffel, Sabine .
NMR IN BIOMEDICINE, 2009, 22 (04) :374-390
[55]   Imaging mass spectrometry [J].
McDonnell, Liam A. ;
Heeren, Ron M. A. .
MASS SPECTROMETRY REVIEWS, 2007, 26 (04) :606-643
[56]   SIRENE: supervised inference of regulatory networks [J].
Mordelet, Fantine ;
Vert, Jean-Philippe .
BIOINFORMATICS, 2008, 24 (16) :I76-I82
[57]   Inference for the generalization error [J].
Nadeau, C ;
Bengio, Y .
MACHINE LEARNING, 2003, 52 (03) :239-281
[58]  
Neter J, 1985, Applied linear statistical models: Regression, analysis of variance, and experimental design, DOI DOI 10.2307/1271154
[59]   Low rank updated LS-SVM classifiers for fast variable selection [J].
Ojeda, Fabian ;
Suykens, Johan A. K. ;
De Moor, Bart .
NEURAL NETWORKS, 2008, 21 (2-3) :437-449
[60]  
Platt JC, 2000, ADV NEUR IN, P61