Multifractal Analysis for Cumulant-Based Epileptic Seizure Detection in Eeg Time Series

摘要

Multifractal analysis allows us to study scale invariance and fluctuations of the pointwise regularity of time series. A theoretically well grounded multifractal formalism, based on wavelet leaders, was applied to electroencephalography (EEG) time series measured in healthy volunteers and epilepsy patients, provided by the University of Bonn. We show that the multifractal spectrum during a seizure indicates a lower global regularity when compared to non-seizure data and that multifractal features, combined with few baseline features, can be used to train a supervised learning algorithm to discriminate well above chance ictal (i.e. seizure) versus healthy and interictal epochs (≃ 97 %) and healthy controls versus patients (≃ 92 %).