Recurrent Neural Networks for P300-based BCI
This work addresses the challenge of improving P300 detection for patients with eye control loss, though it is incremental as it builds on existing neural network methods.
The study tackled the problem of detecting P300 target events in EEG-based brain-computer interfaces using the RSVP protocol, finding that a combined CNN-RNN model outperformed alternatives like LDA in transfer learning across subjects and resilience to temporal noise.
P300-based spellers are one of the main methods for EEG-based brain-computer interface, and the detection of the P300 target event with high accuracy is an important prerequisite. The rapid serial visual presentation (RSVP) protocol is of high interest because it can be used by patients who have lost control over their eyes. In this study we wish to explore the suitability of recurrent neural networks (RNNs) as a machine learning method for identifying the P300 signal in RSVP data. We systematically compare RNN with alternative methods such as linear discriminant analysis (LDA) and convolutional neural network (CNN). Our results indicate that LDA performs as well as the neural network models or better on single subject data, but a network combining CNN and RNN has advantages when transferring learning among subejcts, and is significantly more resilient to temporal noise than other methods.