Robust learning from corrupted EEG with dynamic spatial filtering

by   Hubert Banville, et al.

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 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.


page 1

page 2

page 3

page 4


Design and Implementation of EEG-Mechatronic System Interface for Computational Intelligence

The devices that can read Electroencephalography (EEG) signals have been...

Converting Your Thoughts to Texts: Enabling Brain Typing via Deep Feature Learning of EEG Signals

An electroencephalography (EEG) based Brain Computer Interface (BCI) ena...

Optimizing Channel Selection for Seizure Detection

Interpretation of electroencephalogram (EEG) signals can be complicated ...

MYND: Unsupervised Evaluation of Novel BCI Control Strategies on Consumer Hardware

Neurophysiological studies are typically conducted in laboratories with ...

Learning Signal Representations for EEG Cross-Subject Channel Selection and Trial Classification

EEG technology finds applications in several domains. Currently, most EE...

Brain2Object: Printing Your Mind from Brain Signals with Spatial Correlation Embedding

Electroencephalography (EEG) signals are known to manifest differential ...

Learning Robust Features using Deep Learning for Automatic Seizure Detection

We present and evaluate the capacity of a deep neural network to learn r...

Please sign up or login with your details

Forgot password? Click here to reset