Independent component analysis and high-order statistics for automatic artifact rejection

One of the aims of biomedical signal processing is to extract some features from the data in order to make diagnosis and to understand the biological phenomena but, often, a preprocessing step is essential because some unwelcome signals, the artifacts, are superimposed to the useful signals we want to analyse. Automatic artifact detection is a key topic, because we aim to automatically analyse and extract features from the data. In literature, independent component analysis (ICA) has been exploited for artifact isolation and the joint use of some high order statistics, kurtosis and Shannon's entropy has been exploited to automatically detect the artifacts. In this paper we propose the joint use of kurtosis and Renyi's entropy as a new tool for automatic detection and we show that it outperforms the other tool thanks to the features of the Renyi's entropy.