Estimation of the number of sources by using an MMSE-based MDL criterion without eigendecomposition

Lei Huang*, Teng Long, Erke Mao

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

A new computationally simple MDL approach is addressed in this paper. Unlike the eigenvalue-based MDL methods, the proposed method suggests to use the minimum mean square errors (MMSEs) of the multi-stage Wiener filter (MSWF) to calculate the description length required to encode the observed data. As a result, the proposed method is more robust to the nonuniform noise than the eigenvalue-based MDL methods. On the other hand, since the proposed method does not involve the estimation of the observed covariance matrix and its eigedecomposition, its computational complexity can be significantly reduced. Numerical results are presented to illustrate the consistency and robustness of the proposed method.

Original languageEnglish
Title of host publication2009 International Conference on Signal Processing Systems, ICSPS 2009
Pages8-12
Number of pages5
DOIs
Publication statusPublished - 2009
Event2009 International Conference on Signal Processing Systems, ICSPS 2009 - Singapore, Singapore
Duration: 15 May 200917 May 2009

Publication series

Name2009 International Conference on Signal Processing Systems, ICSPS 2009

Conference

Conference2009 International Conference on Signal Processing Systems, ICSPS 2009
Country/TerritorySingapore
CitySingapore
Period15/05/0917/05/09

Fingerprint

Dive into the research topics of 'Estimation of the number of sources by using an MMSE-based MDL criterion without eigendecomposition'. Together they form a unique fingerprint.

Cite this