Improving motor imagery decoding methods for an EEG-based mobile brain-computer interface in the context of the 2024 Cybathlon.

backgroundBrain-computer interfaces (BCIs) have shown significant promise over the past decades, but often fail to meet the requirements for portability and usability in real-world scenarios. Motivated by the Cybathlon 2024 competition, we developed a modular, online EEG-based BCI system to address these challenges, thereby increasing accessibility for individuals with severe mobility impairments, such as tetraplegia.

methodsOur system uses three mental and motor imagery (MI) classes to control up to five control signals. The pipeline consists of four modules: data acquisition, preprocessing, classification, and the transfer function to map classification output to control dimensions. These modules run in parallel to optimise the online delay. The preprocessing includes a linear phase filter bandpass, artefact removal, and epoching with a sliding time window. The feature extraction was done using Morlet wavelets and the common spatial pattern. As our deep learning classifier, we use three diagonalized structured state-space sequence layers. We developed a training game for our pilot where the mental tasks control the game during quick-time events. We implemented a mobile web application for live user feedback. The components were designed with a human-centred approach in collaboration with the tetraplegic user.

resultsWe achieve up to 84% classification accuracy in offline analysis using an S4D-layer-based model. In the live Cybathlon competition setting, our pilot successfully completed one task; we attribute the reduced performance in this context primarily to factors such as stress and the challenging competition environment. Following the Cybathlon, we further validated our pipeline with the original pilot and an additional participant, achieving a success rate of 73% in real-time gameplay. We also compare our model to the EEGEncoder, which is slower in training but has a higher performance. The S4D model outperforms the reference machine learning models.

conclusionsWe provide insights into developing a framework for portable BCIs, taking a step towards bridging the gap between the laboratory and daily life. Specifically, our framework integrates modular design, real-time data processing, user-centred feedback, and low-cost hardware to deliver an accessible and adaptable BCI solution, addressing critical gaps in current BCI applications.