Robust least squares support vector machine based on recursive outlier elimination

Authors:
Wen Wen;Zhifeng Hao;Xiaowei Yang
Affiliations:
Guangdong University of Technology, School of Computer, 510006, Guangzhou, China;Guangdong University of Technology, School of Computer, 510006, Guangzhou, China;South China University of Technology, School of Mathematical Science, 510641, Guangzhou, China
Venue:
Soft Computing - A Fusion of Foundations, Methodologies and Applications
Year:
2010

Citing 0
Cited 2

Recursive robust least squares support vector regression based on maximum correntropy criterion

Neurocomputing
Pointwise probability reinforcements for robust statistical inference

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

To achieve robust estimation for noisy data set, a recursive outlier elimination-based least squares support vector machine (ROELS-SVM) algorithm is proposed in this paper. In this algorithm, statistical information from the error variables of least squares support vector machine is recursively learned and a criterion derived from robust linear regression is employed for outlier elimination. Besides, decremental learning technique is implemented in the recursive training–eliminating stage, which ensures that the outliers are eliminated with low computational cost. The proposed algorithm is compared with re-weighted least squares support vector machine on multiple data sets and the results demonstrate the remarkably robust performance of the ROELS-SVM.