MODELING OF NON-GAUSSIAN ARRAY DATA USING CUMULANTS - DOA ESTIMATION OF MORE SOURCES WITH LESS SENSORS

被引：42

作者：

SHAMSUNDER, S

GIANNAKIS, GB

机构：

[1] Department of Electrical Engineering, University of Virginia, Charlottesville

来源：

SIGNAL PROCESSING | 1993年 / 30卷 / 03期

关键词：

ARRAY MODELING; DIRECTION-OF-ARRIVAL ESTIMATION; NON-GAUSSIAN MULTIVARIATE PROCESSES; CUMULANTS;

D O I：

10.1016/0165-1684(93)90014-2

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Multichannel, non-Gaussian linear processes are modeled via direct and inverse cumulant-based methods using noisy, multivariate output data. The proposed methods are theoretically insensitive to additive Gaussian noise (perhaps colored, with unknown covariance matrix), and are guaranteed to uniquely identify the system matrix within a post-multiplication by a permutation matrix. Asymptotically optimal and computationally less intensive modeling criteria are also discussed. Further, it is proved that using higher-than-second-order cumulants, it is possible to estimate more angles-of-arrival (or harmonics) with fewer sensors. The problem of detecting the number of sources (or inputs) using output cumulants only is also addressed. Simulation results show that the proposed algorithms outperform the traditional correlation-based methods.

引用

页码：279 / 297

页数：19

共 30 条

[1]

Bresler, Macowski, On the number of signals resolvable by a uniform linear array, IEEE Trans. Acoust. Speech Signal Process., 34, pp. 1081-1089, (1986)

[2]

Cardoso, Eigenstructure of the 4th-order cumulant tensor with application to the blind source separation problem, Internat. Conf. Acoust. Speech Signal Process., pp. 2655-2658, (1990)

[3]

Cardoso, Source separation using higher order moments, Internat. Conf. Acoust. Speech Signal Process., pp. 2109-2112, (1989)

[4]

Cardoso, Super-symmetric decomposition of the fourth-order cumulant tensor. Blind-identification of more sources than sensors, Internat. Conf. Acoust. Speech Signal Process., pp. 3109-3112, (1991)

[5]

Comon, Separation of stochastic processes, Workshop on Higher-Order Spectral Analysis, pp. 174-179, (1989)

[6]

Comon, Cardoso, Eigenvalue decomposition of a cumulant tensor with applications, Proc. SPIE Conf. on Advanced Signal Processing Algorithms, Architectures and Implementations, 1348, pp. 361-372, (1990)

[7]

Dandawate, Giannakis, Ergodicity results for non-stationary signals - Cumulants, ambiguity functions and wavelets, Proc. Conf. on Information Sciences and Systems, pp. 976-983, (1991)

[8]

Forster, Nikias, Bearing estimation in the bispectrum-domain, 5th ASSP Workshop on Spectrum Estimation and Modeling, pp. 5-9, (1990)

[9]

Giannakis, A Kronecker product formulation of the cumulant-based realization of stochastic systems, Proc. Amer. Control Conf., pp. 2096-2101, (1988)

[10]

Giannakis, Shamsunder, Modeling of non-Gaussian array data using cumulants: DOA estimation with less sensors than sources, Proc. Conf. on Information Sciences and Systems, pp. 600-606, (1991)

← 1 2 3 →