Abstract
This paper presents a novel approach to structure determination of linear systems along with the choice of system orders and parameters. AutoRegressive (AR), Moving Average (MA) or AutoRegressive-Moving Average (ARMA) model structure can be extracted blindly from the Third Order Cumulants (TOC) of the system output measurements, where the unknown system is driven by an unobservable stationary independent identically distributed (i.i.d.) non-Gaussian signal. By means of the system order recursion, whether the system has an AR structure or has AR part of an ARMA structure is firstly investigated. MA features in the TOC domain is then applied as a threshold to decide if the system is an MA model or has MA part of an ARMA model. Numerical simulations illustrate the generality of the proposed blind structure identification methodology that may serve as a guideline for blind linear system modeling.
Similar content being viewed by others
References
J. Schoukens, R. Pintelon. Identification of Linear Systems: A Practical Guide to Accurate Modeling. New York, Pergamon, 1991, 193–213.
L. Ljung. Black-Box models from input-output measurements. Proc. IEEE Instrumentation and Measurement Technology Conference, Hungary, 2001, vol.1, 138–146.
P. Stoica, Y. Selen. Model order selection, a review of information criterion rules. IEEE Signal Processing, 21(2004)5, 36–47.
P. M. T. Broersen, S. de Waele. Finite sample properties of ARMA order selection. IEEE Trans. on Instrumentation and Measurement, 53(2004)3, 645–651.
S. Kay. Conditional model order estimation. IEEE Trans. on Signal Processing, 49(2001)9, 1910–1917.
S. Sando, A. Mitra, P. Stoica. On the Cramér-Rao bound for model-based spectral analysis. IEEE Signal Processing Letters, 9(2002)2, 68–71.
S. J. Roberts, W. D. Penny. Variational Bayes for generalized autoregressive models. IEEE Trans. on Signal Processing, 50(2002)9, 2245–2257.
P. Stocia, Y. Selen, J. Li. On information criteria and the generalized likelihood ratio test of model order selection. IEEE Signal Processing Letters, 11 (2004)10, 794–797.
C.-H. J. Ying, A. Sabharwal, R. L. Moses. A combined order selection and parameter estimation algorithm for undamped exponentials. IEEE Trans. on Signal Processing, 48(2000)3, 693–701.
C.-Y. Chi, C.-Y. Chen, C.-H. Chen, C.-C. Feng. Batch processing algorithms for blind equalization using higher-order statistics. IEEE Signal Processing, 20(2003)1, 25–49.
T. W. S. Chow, H.-Z. Tan. HOS-based nonparametric and parametric methodologies for machine fault detection. IEEE Trans. on Industrial Electronics, 47 (2000)5, 1051–1059.
H. Luo, Y. Li. The application of blind channel identification techniques to prestack seismic deconvolution. Proceedings of IEEE, 86(1998)10, 2082–2089.
C. L. Nikias, A. P. Petropulu. Higher-Order Spectra Analysis. NJ, Prentice Hall, 1993, 7–37.
T. W. S. Chow, H.-Z. Tan. Semiblind identification of nonminimum phase ARMA models via order recursion with higher-order cumulants. IEEE Trans. on Industrial Electronics, 45(1998)4, 663–671.
T. W. S. Chow, H.-Z. Tan. Order-recursive blind identification of linear models using mixed cumulants. IEE Proc.-Vision, Image and Signal Processing, 147(2000)2, 139–148.
A. K. Nandi. Blind identification of FIR systems using third-order cumulants. Signal Processing, 39 (1994)2, 131–147.
Author information
Authors and Affiliations
Additional information
Supported by the National Natural Science Foundation of China (No.60575006).
Communication author: Tan Hongzhou, born in 1965, male, Ph.D., professor. Dept of Electronics, Sun Yat-Sen University, Guangzhou 510275, China.
About this article
Cite this article
Fu, J., Tan, H. & Huang, Y. Blind and complete modeling of linear systems using third order cumulants. J. of Electron.(China) 24, 649–654 (2007). https://doi.org/10.1007/s11767-006-0033-5
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/s11767-006-0033-5
Key words
- AutoRegressive-Moving Average (ARMA) models
- The Third-Order Cumulants (TOC)
- Blind structure identification
- Order recursion