Graph denoising of impulsive EEG signals and the effect of their graph representation

As the field of brain monitoring is evolving rapidly, there is an increasing demand for innovative approaches to handle relevant signals. Recently, graph signal processing, which enables the treatment of signal ensembles, emerges as a powerful alternative to a per-signal analysis. This is especially the case for electroencephalogram (EEG) signals that naturally admit graph representations, with each electrode corresponding to one graph node. These signals are often corrupted by impulsive noise best characterized by heavy-tailed statistics, thus driving conventional denoising techniques to failure. To address this problem, we propose an efficient regularized graph filtering method based on fractional lower-order moments, which better adapt to heavy-tailed statistics. An experimental evaluation on real EEG measurements, including the publicly available P300 dataset and epilepsy signals, reveals a superior denoising performance of our method when compared against well-established EEG signal denoising methods.