Recursive estimation of exponential signals in impulsive noise using M-estimation

This paper proposes a robust method for recursive estimating the frequencies and amplitudes of an exponential signal model under impulsive noise. Using the concept of M-estimation, a recursive algorithm based on the recursive least M-estimate (RLM) is developed. Simulation results show that the proposed method performs better than that of the conventional least square method under impulsive noise environment. The algorithm also possesses low arithmetic complexity due to its recursive nature.