DocumentCode :
2256157
Title :
Robust linear estimation using M-estimation and weighted L1 regularization: Model selection and recursive implementation
Author :
Zhang, Z.G. ; Chan, S.C. ; Zhou, Y. ; Hu, Y.
Author_Institution :
Dept. of Orthopaedics & Traumatology, Univ. of Hong Kong, Hong Kong, China
fYear :
2009
fDate :
24-27 May 2009
Firstpage :
1193
Lastpage :
1196
Abstract :
This paper studies an M-estimation-based method for linear estimation with weighted L1 regularization and its recursive implementation. Motivated by the sensitivity of conventional least-squares-based L1-regularized linear estimation (Lasso) in impulsive noise environment, an M-estimator-based Lasso (M-Lasso) method is introduced to restrain the outliers and an iterative re-weighted least-squares (IRLS) algorithm is proposed to solve this M-estimation problem. Moreover, instead of using the matrix inversion formula, QR decomposition (QRD) is employed in the M-Lasso for recursive implementation with a lower arithmetic complexity. Simulation results show that the M-estimation-based Lasso performs considerably better than the traditional LS-based Lasso in suppressing the impulsive noise, and its recursive QRD algorithm has a good performance in online processing.
Keywords :
impulse noise; iterative methods; least squares approximations; matrix decomposition; recursive estimation; regression analysis; signal denoising; L1-regularized linear estimation; M-estimator-based Lasso method; impulsive noise; iterative reweighted least-squares algorithm; least-squares-based estimation; robust linear estimation; weighted L1 regularization; Additive noise; Arithmetic; Linear regression; Orthopedic surgery; Performance evaluation; Proposals; Recursive estimation; Robustness; Signal design; Working environment noise;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems, 2009. ISCAS 2009. IEEE International Symposium on
Conference_Location :
Taipei
Print_ISBN :
978-1-4244-3827-3
Electronic_ISBN :
978-1-4244-3828-0
Type :
conf
DOI :
10.1109/ISCAS.2009.5117975
Filename :
5117975
Link To Document :
بازگشت