Method for Artefact Detection and Suppression Using Alpha-Stable Distributions
This paper describes a method for artefact detection and suppression based on a-Stable distributions. The reason for choosing the a-stable distribution is, that it is heavy-tailed distribution ideal for modeling of data polluted by outliers. A method for on-line data processing is emphasized. The artefact suppression is based on the idea that data are modeled by a Symmetric α-Stable distribution, parameters of which are estimated. Then the data are regenerated from the Gaussian distribution with parameters, that correspond to the original parameters of the α-Stable distribution. The new data is free of any outliers.
KeywordsWeighted Median Impulsive Noise Cauchy Distribution Outlier Removal Artefact Detection
Unable to display preview. Download preview PDF.
- C. L. Nikias and M. Shao, Signal processing with alpha-stable distributions and applications. Adaptive and learning systems for signal processing, communications, and control, Chicester: Wiley, 1995.Google Scholar
- G. A. Tsihrintzis and C. L. Nikias, “Fast estimation of the parameters of alpha-stable impulsive interference” IEEE Transactions on Signal Processing, vol. 44, pp. 1492–1503, June 1996.Google Scholar
- X. Ma and C. L. Nikias, “Parameter estimation and blind channel identification in impulsive signal environments” IEEE Transactions on Signal Processing, vol. 43, pp. 2884–2897, December 1995.Google Scholar
- V. Peterka, “Bayesian approach to system identification” in Trends and Progress in System Identification (P. Eykhoff, ed.), ch. 8, pp. 239–304, Oxford: Pergamon Press, 1981.Google Scholar