Detection of Spatially Correlated Time Series From a Network of Sensor Arrays

This paper addresses the problem of testing for the independence among multiple ( ≥ 2) random vectors. The generalized likelihood ratio test tests the null hypothesis that the composite covariance matrix of the channels is block-diagonal, using a generalized Hadamard ratio. Using the theory of Gram determinants, we show that this Hadamard ratio is stochastically equivalent to a product of scalars, which are independently drawn from a beta distribution under the null hypothesis. This result is then used to derive an asymptotic null distribution, which can be used to identify an appropriate threshold when the sample support is large. These results are then extended to the problem of detecting the presence of spatially correlated time series when each observer employs an array of sensors. Assuming wide-sense stationary processes in both time and space, the likelihood ratio is shown to involve a Hadamard ratio of an estimated cross-spectral matrix at every frequency/wavenumber pair. The proposed detector is compared to several alternative detectors, using simulated space-time fields.

[1]  Louis L. Scharf,et al.  Detection of Spatially Correlated Gaussian Time Series , 2010, IEEE Transactions on Signal Processing.

[2]  Richard A. Davis,et al.  Time Series: Theory and Methods (2Nd Edn) , 1993 .

[3]  D. Cochran,et al.  Non-parametric multiple channel detection in deep ocean noise , 1997, Conference Record of the Thirty-First Asilomar Conference on Signals, Systems and Computers (Cat. No.97CB36136).

[4]  A. Leshem,et al.  Multichannel detection of Gaussian signals with uncalibrated receivers , 2001, IEEE Signal Processing Letters.

[5]  Phillipp Meister,et al.  Statistical Signal Processing Detection Estimation And Time Series Analysis , 2016 .

[6]  Mahmood R. Azimi-Sadjadi,et al.  Detection in multiple disparate systems using multi-channel coherence analysis , 2012, IEEE Transactions on Aerospace and Electronic Systems.

[7]  Gregory S. Wagner,et al.  Signal detection using multi-channel seismic data , 1996 .

[8]  R. Muirhead.  Aspects of Multivariate Statistical Theory , 1982, Wiley Series in Probability and Statistics.

[9]  Pedro M. Crespo,et al.  Asymptotically Equivalent Sequences of Matrices and Hermitian Block Toeplitz Matrices With Continuous Symbols: Applications to MIMO Systems , 2008, IEEE Transactions on Information Theory.

[10]  Bin Liu,et al.  A GLRT for multichannel radar detection in the presence of both compound Gaussian clutter and additive white Gaussian noise , 2005, Digit. Signal Process..

[11]  J. Stoyanov.  Saddlepoint Approximations with Applications , 2008 .

[12]  Herbert Gish,et al.  A geometric approach to multiple-channel signal detection , 1995, IEEE Trans. Signal Process..

[13]  Eric R. Ziegel,et al.  Time Series: Theory and Methods (2nd ed,) , 2012 .

[14]  G. Box,et al.  A general distribution theory for a class of likelihood criteria. , 1949, Biometrika.

[15]  A. Erdélyi,et al.  Higher Transcendental Functions , 1954 .

[16]  N. R. Goodman.  The Distribution of the Determinant of a Complex Wishart Distributed Matrix , 1963 .

[17]  T. MacRobert.  Higher Transcendental Functions , 1955, Nature.

[18]  Richard A. Davis,et al.  Time Series: Theory and Methods (2nd ed.). , 1992 .

[19]  Kai Li,et al.  Multisensor collaboration in wireless sensor networks for detection of spatially correlated signals , 2006 .

[20]  W. Marsden.  I and J , 2012 .

[21]  W. G. Cochran,et al.  The distribution of quadratic forms in a normal system, with applications to the analysis of covariance , 1934, Mathematical Proceedings of the Cambridge Philosophical Society.

[22]  Richard A. Davis,et al.  Time Series: Theory and Methods , 2013 .