A Robust Markovian Block Sparse Adaptive Algorithm With Its Convergence Analysis
Zahra Habibi, Hadi Zayyani, Mehdi Korki
Abstract
In this brief, a robust Markovian adaptive filter is proposed for block sparse system identification problem. To make Markovian adaptive filter robust against impulsive noise, a Generalized Gaussian Distribution (GGD) model is utilized for the impulsive noise. Then, a Maximum A Posteriori (MAP) adaptive estimator of the system impulse response is devised in the presence of GGD impulsive noise. A moment-based parameter estimation method is also presented for estimating the scale parameter of GGD noise. Moreover, the convergence analysis of the suggested robust Markovian algorithm is derived. Simulation results show the effectiveness of the proposed robust algorithm compared to some state-of-the-art algorithms in the literature, especially from the computational complexity viewpoint.