Estimation of Time-Varying Autoregressive Symmetric Alpha Stable Processes by Particle Filters

In this work, we propose a novel method to model time-varying autoregressive impulsive signals, which possess Symmetric Alpha Stable distributions. The proposed method is composed of a particle filter, which is capable of estimating the unknown, timevarying autoregressive coefficients and a Hybrid Monte Carlo method that is used for estimating the unknown statistical parameters of the Symmetric Alpha Stable Process. The performance of the proposed method is tested for different parameter values where the time variation of the autoregressive coefficients is taken to be as sinusoidal or random jumps. The successful performance of the developed method serves as a promising contribution in the modeling of impulsive signals, which are frequently seen in many areas, such as teletraffic in computer communications, radar and sonar applications and mobile communications.