Toward high performance, weakly invasive Brain Computer Interfaces using selective visual attention D Rotermund1, U A Ernst1, S Mandon2, K Taylor2, Y Smiyukha2, A K Kreiter2, K Pawelzik1 |
|---|
1Institute for Theoretical Physics, University of Bremen, Germany |
| Brain–computer interfaces (BCIs) have been proposed as a solution for paralyzed persons to communicate and interact with their environment. However, the neural signals used for controlling such prostheses are often noisy and unreliable, resulting in low performance of real-world applications. Here we propose neural signatures of selective visual attention in epidural recordings as a fast, reliable, and high-performance control signal for BCIs. We recorded epidural field potentials with chronically implanted electrode arrays from two macaque monkeys engaged in a shape-tracking task. For single trials, we classified the direction of attention to one of two visual stimuli based on spectral amplitude, coherence, and phase difference. Classification performances reached up to 99.9%, and the information about attentional states could be transferred at rates exceeding 580 bits/min. Excellent classification of more than 97% correct was achieved using time windows as short as 200 ms. Classification performance changed dynamically over the trial and modulated with the task’s varying demands for attention. Information about the direction of attention was contained in the Gamma-band, with the most informative feature being spectral amplitude. Together, these findings establish a novel paradigm for constructing brain prostheses and promise a major gain in performance and robustness for human BCIs. |
| Up Home |
|---|