Confidence bands for least squares support vector machine classifiers: A regression approach

Authors:
K. De Brabanter;P. Karsmakers;J. De Brabanter;J. A. K. Suykens;B. De Moor
Affiliations:
Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit Leuven, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium and IBBT-K.U.Leuven Future Health Department, Kasteelpark Arenberg 10 ...;Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit Leuven, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium and K.H. Kempen (Associatie K.U. Leuven), Department IBW, Kleinhoefst ...;Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit Leuven, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium and Hogeschool KaHo Sint-Lieven (Associatie K.U. Leuven), Department ...;Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit Leuven, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium and IBBT-K.U.Leuven Future Health Department, Kasteelpark Arenberg 10 ...;Department of Electrical Engineering ESAT-SCD, Katholieke Universiteit Leuven, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium and IBBT-K.U.Leuven Future Health Department, Kasteelpark Arenberg 10 ...
Venue:
Pattern Recognition
Year:
2012

Citing 6
Cited 3

Least Squares Support Vector Machine Classifiers

Neural Processing Letters
Introduction to Nonparametric Estimation

Introduction to Nonparametric Estimation
On-line independent support vector machines

Pattern Recognition
Two-class support vector data description

Pattern Recognition
All of Nonparametric Statistics

All of Nonparametric Statistics
Approximate Confidence and Prediction Intervals for Least Squares Support Vector Regression

IEEE Transactions on Neural Networks

Prediction of dissolved oxygen content in river crab culture based on least squares support vector regression optimized by improved particle swarm optimization

Computers and Electronics in Agriculture
Joint learning and weighting of visual vocabulary for bag-of-feature based tissue classification

Pattern Recognition
A hybrid WA-CPSO-LSSVR model for dissolved oxygen content prediction in crab culture

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper presents bias-corrected 100(1-@a)% simultaneous confidence bands for least squares support vector machine classifiers based on a regression framework. The bias, which is inherently present in every nonparametric method, is estimated using double smoothing. In order to obtain simultaneous confidence bands we make use of the volume-of-tube formula. We also provide extensions of this formula in higher dimensions and show that the width of the bands are expanding with increasing dimensionality. Simulations and data analysis support its usefulness in practical real life classification problems.