Abstract
While often presented as promising assistive technologies for motor-impaired users, electroencephalography (EEG)-based Brain-Computer Interfaces (BCIs) remain barely used outside laboratories due to low reliability in real-life conditions. There is thus a need to design long-term reliable BCIs that can be used outside-of-the-lab by end-users, e.g., severely motor-impaired ones. Therefore, we propose and evaluate the design of a multi-class Mental Task (MT)-based BCI for longitudinal training (20 sessions over 3 months) of a tetraplegic user for the CYBATHLON BCI series 2019. In this BCI championship, tetraplegic pilots are mentally driving a virtual car in a racing video game. We aimed at combining a progressive user MT-BCI training with a newly designed machine learning pipeline based on adaptive Riemannian classifiers shown to be promising for real-life applications. We followed a two step training process: the first 11 sessions served to train the user to control a 2-class MT-BCI by performing either two cognitive tasks (REST and MENTAL SUBTRACTION) or two motor-imagery tasks (LEFT-HAND and RIGHT-HAND). The second training step (9 remaining sessions) applied an adaptive, session-independent Riemannian classifier that combined all 4 MT classes used before. Moreover, as our Riemannian classifier was incrementally updated in an unsupervised way it would capture both within and between-session non-stationarity. Experimental evidences confirm the effectiveness of this approach. Namely, the classification accuracy improved by about 30% at the end of the training compared to initial sessions. We also studied the neural correlates of this performance improvement. Using a newly proposed BCI user learning metric, we could show our user learned to improve his BCI control by producing EEG signals matching increasingly more the BCI classifier training data distribution, rather than by improving his EEG class discrimination. However, the resulting improvement was effective only on synchronous (cue-based) BCI and it did not translate into improved CYBATHLON BCI game performances. For the sake of overcoming this in the future, we unveil possible reasons for these limited gaming performances and identify a number of promising future research directions. Importantly, we also report on the evolution of the user's neurophysiological patterns and user experience throughout the BCI training and competition.
Highlights
A Brain-Computer Interface (BCI) processes a user’s brain activity often measured using Electroencephalography (EEG), and translates it into commands for an interactive application (Clerc et al, 2016)
We report on the evolution of the CYBATHLON pilot BCI classification performances, neurophysiological patterns and User eXperience (UX) along the training sessions
As the CYBATHLON BCI series 2019 was a first experience for both the pilot and the research team, during the first 7 sessions we explored a suitable set of mental tasks and EEG sensors to use
Summary
A Brain-Computer Interface (BCI) processes a user’s brain activity often measured using Electroencephalography (EEG), and translates it into commands for an interactive application (Clerc et al, 2016). Only a small number of studies focused on BCI end-users (e.g., users with severe motor impairment, Kauhanen et al, 2007; Conradi et al, 2009; Daly et al, 2013) in real-life testing environments outside the labs (Brandl et al, 2015; Statthaler et al, 2017; Perdikis et al, 2018; Perdikis and Millan, 2020) It is in this context that we decided to participate in the CYBATHLON BCI series competition in Graz in 2019. The CYBATHLON BCI series 2019, that we participated in, was held in Graz (Austria) alongside the 8th International Graz Brain-Computer Interface conference, allowing the racing teams to present their technologies and methods to the whole BCI community For this event, a computer racing game mimicking a real-life application was designed (Novak et al, 2018). In this BCI game, tetraplegic pilots are asked to use up to four mental commands of their choice to control a virtual car
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have