Frequency estimation of sinusoidal signals in alpha-stable noise using subspace techniques

In the frequency estimation of sinusoidal signals observed in impulsive noise environments, techniques based on Gaussian noise assumption are unsuccessful. One possible way to find better estimates is to model the noise as an alpha-stable process and to use the fractional lower order statistics of the data to estimate the signal parameters. Noise and signal subspace methods, namely the MUSIC and principal component-Bartlett methods, are applied to fractional lower order statistics of sinusoids embedded in alpha-stable noise. The simulation results show that techniques based on lower order statistics are superior to their second order statistics-based counterparts, especially when the noise exhibits a strong impulsive attitude.