A deep learning architecture to detect events in EEG signals during sleep

Abstract : Electroencephalography (EEG) during sleep is used by clinicians to evaluate various neurological disorders. In sleep medicine, it is relevant to detect macro-events (≥ 10 s) such as sleep stages, and micro-events (≤ 2 s) such as spindles and K-complexes. Annotations of such events require a trained sleep expert, a time consuming and tedious process with a large inter-scorer variability. Automatic algorithms have been developed to detect various types of events but these are event-specific. We propose a deep learning method that jointly predicts locations, durations and types of events in EEG time series. It relies on a convolutional neural network that builds a feature representation from raw EEG signals. Numerical experiments demonstrate efficiency of this new approach on various event detection tasks compared to current state-of-the-art, event specific, algorithms.
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

Contributor : Stanislas Chambon <>
Submitted on : Friday, November 9, 2018 - 2:52:04 PM
Last modification on : Monday, February 24, 2020 - 3:01:14 PM
Long-term archiving on: Sunday, February 10, 2019 - 2:01:13 PM


Files produced by the author(s)


  • HAL Id : hal-01917529, version 1


Stanislas Chambon, Valentin Thorey, Pierrick Arnal, Emmanuel Mignot, Alexandre Gramfort. A deep learning architecture to detect events in EEG signals during sleep. MLSP 2018 - IEEE International Workshop on Machine Learning for Signal Processing, Sep 2018, Aalborg, Denmark. ⟨hal-01917529⟩



Record views


Files downloads