Compact Convolutional Neural Networks for Multi-Class, Personalised, Closed-Loop EEG-BCI

Abstract

For many people suffering from motor disabilities, assistive devices controlled with only brain activity are the only way to interact with their environment [1]. Natural tasks often require different kinds of interactions, involving different controllers the user should be able to select in a self-paced way. We developed a Brain-Computer Interface (BCI) allowing users to switch between four control modes in a self-paced way in real-time. Since the system is devised to be used in domestic environments in a user-friendly way, we selected non-invasive electroencephalographic (EEG) signals and convolutional neural networks (CNNs), known for their ability to find the optimal features in classification tasks. We tested our system using the Cybathlon BCI computer game, which embodies all the challenges inherent to real-time control. Our preliminary results show that an efficient architecture (SmallNet), with only one convolutional layer, can classify 4 mental activities chosen by the user. The BCI system is run and validated online. It is kept up-to-date through the use of newly collected signals along playing, reaching an online accuracy of 47.6% where most approaches only report results obtained offline. We found that models trained with data collected online better predicted the behaviour of the system in real-time. This suggests that similar (CNN based) offline classifying methods found in the literature might experience a drop in performance when applied online. Compared to our previous decoder of physiological signals relying on blinks, we increased by a factor 2 the amount of states among which the user can transit, bringing the opportunity for finer control of specific subtasks composing natural grasping in a self-paced way. Our results are comparable to those showed at the Cybathlon's BCI Race but further improvements on accuracy are required.

The combination of brain-computer interfaces and artificial intelligence: applications and challenges

“…The present review highlights current research in the BCI field based on AI, which has grown rapidly over the last 15 years (76)(77)(78). The combination of BCIs and AI offers a powerful way to investigate brain function by providing direct knowledge and control of neurons controlling behavior, which will help scientists know more about the human brain and promote developments in rehabilitation medicine (8).…”

Inter-subject Deep Transfer Learning for Motor Imagery EEG Decoding

“…Additionally, we have collected our own online recorded dataset using the Cybathlon 2020 BCI game (https://cybathlon.ethz.ch/en/event/disciplines/bci) with the same hardware set up as our previous work in Cybathlon 2016 [16]. The experimental procedures involving human subjects described in this paper were approved by the Science Engineering Technology Research Ethics Committee of Imperial College London.…”

EEG decoding for datasets with heterogenous electrode configurations using transfer learning graph neural networks

“…Deep learning advances have enabled end-to-end learning without prior feature extraction from raw EEG signals in recent years. Most existing MI-EEG studies employ deep learning methods based on two kinds of basic computational models, convolutional neural network (CNN) [13][14][15][16][17] and recurrent neural network (RNN) [18,19], that outperformed conventional BCI classifiers [20,21]. More recently, spatial and temporal attention mechanisms [4,22] have also been introduced to EEG deep learning models to encourage the model to focus on more discriminative parts instead of processing the entire input equally.…”