On Fisher Information Matrix, Array Manifold Geometry and Time Delay Estimation
Pages 307 - 317
Abstract
The Fisher information matrix is used to evaluate the minimum variance-covariance of unbiased parameter estimation. It is also used, in natural gradient descent algorithms, to improve learning of modern neural networks. We investigate the Fisher information matrix related to the reception of a signal wave on a sensor array. The signal belongs to a parametric family. The objective of the receiver is to estimate the time of arrival, the direction of arrival and the other parameters describing the signal. Based on the parametric model, Fisher information matrix, array manifold and time delay variances are calculated. With an appropriate choice of parameters, the Fisher matrix is block diagonal and easily invertible. It is possible to estimate the direction of arrival on an array of sensors and the time of arrival whatever the signal parameters are. However, some signal characteristics may have an influence on the asymptotic estimation of the time delay. We give examples with a simple parametric family from the literature.
References
[1]
Carter, G.: Time Delay estimation for passive sonar signal processing. IEEE Trans. Acoust. Speech Signal Process. ASSP 29(3), 463–470 (1981)
[2]
Scarbrough, K., Ahmed, N., Carter, G.: On the simulation of a class of time delay estimation algorithms. IEEE Trans. Acoust. Speech Signal Process. ASSP 29(3), 534–540 (1981)
[3]
Friedlander B An efficient parametric technique for doppler-delay estimation IEEE Trans. Signal Process. 2012 60 8 3953-3963
[4]
Miller, L., Lee, J.: Error analysis of time delay estimation using a finite integration time correlator. IEEE Trans. Acoust. Speech Signal Process. ASSP 29(3), 490–496 (1981)
[5]
Pallas M-A and Jourdain G Active high resolution time delay estimation for large BT signals IEEE Trans. Signal Process. 1991 39 4 781-787
[6]
Azaria, M., Hertz, D.: Time delay estimation by generalized cross correlation methods. IEEE Trans. Acoust. Speech Signal Process. ASSP 32(2), 280–285 (1984)
[7]
Knapp, C., Carter, G.: The generalized correlation method for estimation of time delay. IEEE Trans. Acoust. Speech Signal Process. ASSP 24(4), 280–285 (1976)
[8]
Manikas A, Karimi H, and Dacos I Study of the detection and resolution capabilities of a one-dimensional array of sensors by using differential geometry IEE Proc.-Radar Sonar Navig. 1994 141 2 83-92
[9]
Manikas A and Proukakis C Modeling and estimation of ambiguities in linear arrays IEEE Trans. Signal Process. 1998 46 8 2166-2179
[10]
Manikas A and Sleiman A Manifold Studies of nonlinear antenna array geometries IEEE Trans. Signal Process. 2001 49 3 497-506
[11]
Sleiman A, Manikas A, and Dacos I The impact of sensor positioning on the array manifold IEEE Trans. Ant. Propag. 2003 51 9 2227-2237
[12]
Borovkov, A.: Statistique Mathématique. Editions Mir, Moscou (1987)
[13]
Nielsen, F.: Cramér-Rao Lower Bound and Information Geometry. (2013)
[14]
Amari, S., Karakida, R., Oizumi, M.: Fisher Information and Natural Gradient Learning of Random Deep Networks.
[15]
Kaul P and Lall B Projective fisher information for natural gradient descent IEEE Trans. Artif. Intell. 2023 4 2 304-314
[16]
Friedlander, B.: On the cramer-rao bound for time delay and doppler estimation. IEEE Trans. Inf. Theory IT 30(3), 575–580 (1984)
[17]
Kopp, L., Thubert, D.: Cramer-Rao bounds and array processing.Part One Formal. Traitement du Signal 3(3), 111–125 (1986)
[18]
Kopp L and Thubert D Cramer-Rao bounds and array processing Part Two Appl. Traitement du Signal 1987 4 1 57-71
[19]
He Z, Tu X, Bao W, Hu Y, and Li F Second-order transient-extracting transform with application to time-frequency filtering IEEE Trans. Instrum. Meas. 2020 69 8 5428-5437
[20]
Oppenheim A and Schafer R Digital Signal Processing 1975 Upper Saddle River Prentice Hall
[21]
Roubine E Distributions – Signal 1999 2 Paris Eyrolles
Recommendations
Manifold studies of FDA geometries for joint angle and range estimation
AbstractDifferent from traditional phased-array, frequency diverse array (FDA) provides an angle-range-dependent and time-variant transmit beampattern that can be utilized for many promising applications. Since array manifold is critical in ...
Eigenvalue-based time delay estimation of repetitive biomedical signals
AbstractThe time delay estimation problem associated with an ensemble of misaligned, repetitive signals is revisited. Each observed signal is assumed to be composed of an unknown, deterministic signal corrupted by Gaussian, white noise. This ...
Efficient Monte Carlo computation of Fisher information matrix using prior information
PerMIS '07: Proceedings of the 2007 Workshop on Performance Metrics for Intelligent SystemsThe Fisher information matrix (FIM) is a critical quantity in several aspects of mathematical modeling, including input selection, model selection, and confidence region calculation. For example, the determinant of the FIM is the main performance metric ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Aug 2023
640 pages
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 30 August 2023
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 17 Dec 2024