Skip to Main content Skip to Navigation
Conference papers

Multifractal analysis for cumulant-based epileptic seizure detection in eeg time series

Abstract : 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 electroencephalogra-phy (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 %).
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download

https://hal.inria.fr/hal-02108099
Contributor : Philippe Ciuciu <>
Submitted on : Wednesday, April 24, 2019 - 7:21:20 AM
Last modification on : Sunday, June 14, 2020 - 3:28:05 AM

File

ISBI19_0369_FI.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02108099, version 1

Citation

Omar Domingues, Philippe Ciuciu, Daria La Rocca, Patrice Abry, Herwig Wendt. Multifractal analysis for cumulant-based epileptic seizure detection in eeg time series. ISBI 2019 - IEEE International Symposium on Biomedical Imaging, Apr 2019, Venise, Italy. ⟨hal-02108099⟩

Share

Metrics

Record views

212

Files downloads

344