English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Robust learning from corrupted EEG with dynamic spatial filtering

Banville, H., Wood, S. U., Aimone, C., Engemann, D. A., & Gramfort, A. (2022). Robust learning from corrupted EEG with dynamic spatial filtering. NeuroImage, 251: 118994. doi:10.1016/j.neuroimage.2022.118994.

Item is

Basic

show hide
Genre: Journal Article

Files

show Files
hide Files
:
Banville_pre.pdf (Preprint), 8MB
Name:
Banville_pre.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Banville, Hubert1, 2, Author
Wood, Sean U.N.2, Author
Aimone, Chris2, Author
Engemann, Denis A.1, 3, Author              
Gramfort, Alexandre1, Author
Affiliations:
1Université Paris-Saclay, France, ou_persistent22              
2InteraXon Inc., Toronto, ON, Canada, ou_persistent22              
3Department Neurology, MPI for Human Cognitive and Brain Sciences, Max Planck Society, ou_634549              

Content

show
hide
Free keywords: Electroencephalography; Mobile EEG; Deep learning; Machine learning; Noise robustness
 Abstract: Building machine learning models using EEG recorded outside of the laboratory setting requires methods robust to noisy data and randomly missing channels. This need is particularly great when working with sparse EEG montages (1-6 channels), often encountered in consumer-grade or mobile EEG devices. Neither classical machine learning models nor deep neural networks trained end-to-end on EEG are typically designed or tested for robustness to corruption, and especially to randomly missing channels. While some studies have proposed strategies for using data with missing channels, these approaches are not practical when sparse montages are used and computing power is limited (e.g., wearables, cell phones). To tackle this problem, we propose dynamic spatial filtering (DSF), a multi-head attention module that can be plugged in before the first layer of a neural network to handle missing EEG channels by learning to focus on good channels and to ignore bad ones. We tested DSF on public EEG data encompassing 4,000 recordings with simulated channel corruption and on a private dataset of 100 at-home recordings of mobile EEG with natural corruption. Our proposed approach achieves the same performance as baseline models when no noise is applied, but outperforms baselines by as much as 29.4% accuracy when significant channel corruption is present. Moreover, DSF outputs are interpretable, making it possible to monitor the effective channel importance in real-time. This approach has the potential to enable the analysis of EEG in challenging settings where channel corruption hampers the reading of brain signals.

Details

show
hide
Language(s): eng - English
 Dates: 2022-02-032021-09-292022-02-112022-02-162022-05-01
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1016/j.neuroimage.2022.118994
Other: epub 2022
PMID: 35181552
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: NeuroImage
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Orlando, FL : Academic Press
Pages: - Volume / Issue: 251 Sequence Number: 118994 Start / End Page: - Identifier: ISSN: 1053-8119
CoNE: https://pure.mpg.de/cone/journals/resource/954922650166