A Fast Robust and Simple Algorithm for Estimating Parameters of Polynomial Phase Signals.
Une Méthode Rapide Robuste et Simple pour L’Estimation des Paramètres d’un Signal À Phase Polynomiale
OPEN ACCESS
Polynomial phase signals belong to a wide class of signals used for modeling but processing associated to them are always difficult since they are non-stationary signals.In the method introduced in this paper,we take benefits of some advances in robust estimation in order to build a new algorithm for estimating the phasis parameters of polynomial phase signal.This algorithm has the advantages of being fast and being able to deal with signal whose phase is a polynomial of unknown order.The structure of this algorithm is robust to the shape of the noise.
Résumé
Les signaux à phase polynomiale constituent une vaste classe de signaux utilisés en modélisation mais leurs traitements se révèlent difficiles en raison de leur caractère non-stationnaire. Dans la méthode présentée dans cet article,nous mettons à profit de récents travaux en matière d’estimation robuste afin de réaliser un nouvel algorithme d’estimation des paramètres de la phase d’un signal. Cet algorithme présente les avantages d’être rapide et capable de traiter des signaux dont la phase est d’ordre inconnu. La structure de cet algorithme reste indépendante par le type de bruit car il est résistant à la forme de la distribution du bruit.
Polynomial phase signals,Instantaneous frequency,Robust estimation,Parametric estimation,Impulse noise.
Mots clés
Signaux à phase polynomiale,Fréquence instantanée,Estimation robuste,Estimation paramétrique, Bruit impulsif.
[1] S.BARBAROSSA, R.MAMELI, A.SCAGLIONE. Adaptive detection of polynomial-phase signals embedded in noise using high order ambiguity functions. In 31st Asilomar Conf. Signals, Syst. Comput., Pacific Grove, November 1997.
[2] S.BARBAROSSA, A.PORCHIA, A.SCAGLIONE. Multiplicative multilag higher-order ambiguity function. In Proc. Int. Conf. Acoustics, Speech and Signal Processing, May 1996.
[3] Sergio BARBAROSSA, Anna SCAGLIONE, Georgios GIANNAKIS. Product high-order ambiguity function for multicomponent polynomial-phase signal modeling. IEEE Transactions on Signal Processing, 46(3):691-708, march 1998.
[4] Mounir DJEDDI. Approches pour l’analyse des signaux à phase polynomiale dans un environement non gaussien. PhD thesis, Université Paris-Sud, Laboratoire des Signaux et Systèmes Supélec, may 2005.
[5] MarkH. HANSEN, Bin YU. Model selection and the principle of minimum description length. Journal of the American Statistical Association, 96(454):746-774, 2001.
[6] Cornel IOANA, Cedric CORNU, André QUINQUIS. Polynomial phase signal processing via warped high-order ambiguity function. In EUSIPCO, 2004.
[7] PeterJ. KOOTSOOKOS. A review of the frequency estimation and tracking problems. Technical report, CRASys Australian National University, 1993.
[8] BrianC. LOVELL, RobertC. WILLAMSON. The statistical performance of some instantaneous frequency estimators. IEEE Transactions on Signal Processing, 40(7):1708-1723, July 1992.
[9] S.MARCOS. Les méthodes à haute résolution. Hermès, 1998.
[10] Lamine MILI, ClintW. COAKLEY. Robust estimation in structured linear regression. The Annals of Statistics, 24(6):2593-2607, 1996.
[11] S.NANDI, D.KUNDU. Asymptotic properties of the least squares estimators of the parameters of the chirp signals. Annals of the Institute of Statistical Mathematics, 56(3):529-544, 2004.
[12] Sokol SALIU. Definition of instantaneous frequency on real signals. In EUSIPCO, 2000.
[13] Anna SCAGLIONE, Sergio BARBAROSSA. Statistical analysis of the product high-order ambiguity function. IEEE Transactions on Information Theory, 45(1):343-356, january 1999.
[14] P.STOICA, A.NEHORAI, P.HINDEL. Improved sequential music. IEEE Transactions on Aerospace and Electronic Systems, 31:12301239, October 1995.
[15] Petre STOICA, Arye NEHORAI. Music, maximum likelihood, and cramer-rao bound. IEEE Transactions on Acoustics, Speech and Signal Processing, 37(5):720-741, May 1989.
[16] Petre STOICA, Arye NEHORAI. Music, maximum likelihood, and cramer-rao bound: Further results and comparisons. IEEE Transactions on Acoustics, Speech and Signal Processing, 38(12):2140-2150, December 1990.
[17] Zhengyou ZHANG. Parameter estimation techniques:A tutorial with applications to conic fitting. Technical Report 2676, INRIA, October 1995.