BAYESIAN INFORMATION CRITERION FOR MULTIDIMENSIONAL SINUSOIDAL ORDER SELECTION

被引：0

作者：

Xiong, Jie ^{[1
]}

Liu, Kefei ^{[2
]}

da Costa, Joao Paulo C. L. ^{[3
,4
,5
]}

Wang, Wen-Qin ^{[1
]}

机构：

[1] Univ Elect Sci & Technol China, Sch Commun Engn, Chengdu, Sichuan, Peoples R China

[2] Indiana Univ Sch Med, Indianapolis, IN 46202 USA

[3] Univ Brasilia, Dept Elect Engn, Brasilia, DF, Brazil

[4] Fraunhofer IIS, Inst Integrated Circuits, Erlangen, Germany

[5] Ilmenau Univ Technol, Inst Informat Technol, Ilmenau, Germany

来源：

2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2017年

关键词：

Bayesian information criterion; model order selection; maximum likelihood estimation; frequency estimation; multidimensional signal processing; HARMONIC RETRIEVAL PROBLEMS; IDENTIFIABILITY;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Detecting the sinusoidal order is a prerequisite step for parametric multidimensional sinusoidal frequency estimation methods, whose applications range from radar and wireless communications to nuclear magnetic resonance spectroscopy. Although the Bayesian information criterion (BIC) has been commonly applied for model order selection, its application to sinusoidal order estimation is recent. By means of estimation of Fisher information matrix, we extend the 1-D BIC to multidimensional case for multidimensional sinusoidal order selection. The multidimensional BIC is shown in simulations to outperform the state-of-the-art algorithms in terms of probability of correct detection.

引用

页码：3106 / 3110

页数：5

共 20 条

[1] Multi-dimensional model order selection
Carvalho Lustosa da Costa, Joao Paulo
Roemer, Florian
Haardt, Martin
de Sousa, Rafael Timoteo, Jr.
[J]. EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2011,
[2] Asymptotic MAP criteria for model selection
Djuric, PM
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1998, 46 (10) : 2726 - 2735
[3] Simultaneous Schur decomposition of several nonsymmetric matrices to achieve automatic pairing in multidimensional harmonic retrieval problems
Haardt, M
Nossek, JA
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1998, 46 (01) : 161 - 169
[4] Higher-order SVD-based subspace estimation to improve the parameter estimation accuracy in multidimensional harmonic retrieval problems
Haardt, Martin
Roemer, Florian
Del Galdo, Giovanni
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2008, 56 (07) : 3198 - 3213
[5] Almost-sure identifiability of multidimensional harmonic retrieval
Jiang, T
Sidiropoulos, ND
ten Berge, JMF
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2001, 49 (09) : 1849 - 1859
[6] A high-resolution technique for multidimensional NMR spectroscopy
Li, YG
Razavilar, J
Liu, KJR
[J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 1998, 45 (01) : 78 - 86
[7] An eigenvector-based approach for multidimensional frequency estimation with improved identifiability
Liu, Jun
Liu, Xiangqian
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2006, 54 (12) : 4543 - 4556
[8] Detection of number of components in CANDECOMP/PARAFAC models via minimum description length
Liu, Kefei
da Costa, Joao Paulo C. L.
So, Hing Cheung
Huang, Lei
Ye, Jieping
[J]. DIGITAL SIGNAL PROCESSING, 2016, 51 : 110 - 123
[9] Multidimensional folding for sinusoidal order selection
Liu, Kefei
Huang, Lei
So, Hing Cheung
Ye, Jieping
[J]. DIGITAL SIGNAL PROCESSING, 2016, 48 : 349 - 360
[10] Subspace techniques for multidimensional model order selection in colored noise
Liu, Kefei
da Costa, Joao Paulo C. L.
So, Hing Cheung
Huang, Lei
[J]. SIGNAL PROCESSING, 2013, 93 (07) : 1976 - 1987

← 1 2 →