On parameter estimation of symmetric alpha-stable distribution

In this paper, a novel approach has been proposed for estimating the parameters of symmetric alpha-stable distribution with 1 ≤ α ≤ 2. Alpha-stable distribution can model the statistical behavior of non-Gaussian heavy tailed signals and noises with impulsive components. There are some serious consideration in parameter estimation with stable random variable due to the lack of expression in analytic form for its distribution. In this method, the closed-form expression for parameter estimators is achieved by means of the values of characteristic function (CF) in two different points. We also establish a framework to determine these points in the general case. Performance comparison between the proposed method and the other methods is performed through several simulations and numerical results confirm that our method is efficient and has better performance even with a few number of samples.

[1]  Yan-ling Hao,et al.  Parameter estimation of alpha-stable distributions based on MCMC , 2011, 2011 3rd International Conference on Advanced Computer Control.

[2]  Juan Manuel Górriz,et al.  Parameterization of the distribution of white and grey matter in MRI using the αα-stable distribution , 2013, Comput. Biol. Medicine.

[3]  Chrysostomos L. Nikias,et al.  Parameter estimation and blind channel identification in impulsive signal environments , 1995, IEEE Trans. Signal Process..

[6]  Tianshuang Qiu,et al.  Parameter estimation based on fractional power spectrum under alpha-stable distribution noise environment in wideband bistatic MIMO radar system , 2013 .

[7]  Ercan E. Kuruoglu,et al.  Density parameter estimation of skewed α-stable distributions , 2001, IEEE Trans. Signal Process..

[8]  Harish Bhaskar,et al.  Video Foreground Detection Based on Symmetric Alpha-Stable Mixture Models , 2010, IEEE Transactions on Circuits and Systems for Video Technology.

[9]  Pengyu Gao,et al.  Research on Parameter Estimation Methods for Alpha Stable Noise in a Laser Gyroscope’s Random Error , 2015, Sensors.

[10]  Hiroyoshi Yamada,et al.  Stable parameter estimation of compound Wishart distribution for polarimetric SAR data modeling , 2013, 2013 Proceedings of the International Symposium on Antennas & Propagation.

[11]  Konstantinos N. Plataniotis,et al.  Accurate kernel-based spectrum sensing for Gaussian and non-Gaussian noise models , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[12]  Estimation method for weak sinusoidal amplitude in alpha noise , 2014, 2014 12th International Conference on Signal Processing (ICSP).

[13]  Claudio R. C. M. da Silva,et al.  Detection of Digital Amplitude-Phase Modulated Signals in Symmetric Alpha-Stable Noise , 2012, IEEE Transactions on Communications.