Convolutional neural network, personalised, closed-loop Brain-Computer Interfaces for multi-way control mode switching in real-time

Abstract

Abstract-Brain-Computer Interfaces are communication systems that use brain signals as commands to a device. Despite being the only means by which severely paralysed people can interact with the world most effort is focused on improving and testing algorithms offline, not worrying about their validation in real life conditions. The Cybathlon's BCI-race offers a unique opportunity to apply theory in real life conditions and fills the gap. We present here a Neural Network architecture for the 4-way classification paradigm of the BCI-race able to run in real-time. The procedure to find the architecture and best combination of mental commands best suiting this architecture for personalised used are also described. Using spectral power features and one layer convolutional plus one fully connected layer network we achieve a performance similar to that in literature for 4-way classification and prove that following our method we can obtain similar accuracies online and offline closing this well-known gap in BCI performances.

Deep Learning Based BCI Control of a Robotic Service Assistant Using Intelligent Goal Formulation

“…Taken together, these advances make deep ConvNets a viable alternative for brain-signal decoding in brain-computer interfaces. A first attempt at using shallow ConvNets for online BCI has recently been reported [22]. To the best of our knowledge, apart from our previous paper [23], there is no other work, which uses a deep ConvNet-based online control to implement an EEG-based brain-computer interface.…”