Journal article
System identification in the presence of outliers and random noises: A compressed sensing approach
Automatica (Oxford), Vol.50(11), pp.2905-2911
11/2014
DOI: 10.1016/j.automatica.2014.10.017
Abstract
In this paper, we consider robust system identification of FIR systems when both sparse outliers and random noises are present. We reduce this problem of system identification to a sparse error correcting problem using a Toeplitz structured real-numbered coding matrix and prove the performance guarantee. Thresholds on the percentage of correctable errors for Toeplitz structured matrices are established. When both outliers and observation noise are present, we have shown that the estimation error goes to 0 asymptotically as long as the probability density function for observation noise is not “vanishing” around origin. No probabilistic assumptions are imposed on the outliers.
Details
- Title: Subtitle
- System identification in the presence of outliers and random noises: A compressed sensing approach
- Creators
- Weiyu Xu - Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA 52242, United StatesEr-Wei Bai - Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA 52242, United StatesMyung Cho - Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA 52242, United States
- Resource Type
- Journal article
- Publication Details
- Automatica (Oxford), Vol.50(11), pp.2905-2911
- Publisher
- Elsevier Ltd
- DOI
- 10.1016/j.automatica.2014.10.017
- ISSN
- 0005-1098
- eISSN
- 1873-2836
- Grant note
- Simons Foundation (http://dx.doi.org/10.13039/100000893) DE-FG52-09NA29364 / DoE (http://dx.doi.org/10.13039/100000015) CNS-1329657 / NSF (http://dx.doi.org/10.13039/100000001)
- Language
- English
- Date published
- 11/2014
- Academic Unit
- Electrical and Computer Engineering
- Record Identifier
- 9984083894402771
Metrics
16 Record Views