Study on an online collaborative BCI to accelerate response to visual targets

Abstract

Using brain-computer interfaces (BCIs) to improve human performance has become a state-of-the-art research topic. The concept of collaborative BCIs, which aimed to use multi-brain computing to enhance human performance, was proposed recently. To further study the feasibility of collaborative BCIs, here we propose to develop an online collaborative BCI to accelerate human response to visual target stimuli by detecting multi-subjects' visual evoked potentials (VEPs). A spatial filtering algorithm which maximized the signal-to-noise ratio was used to extract VEP components from multichannel EEG. A two-layer support vector machine was subsequently used for target detection. Results of an offline analysis indicated that the system could achieve high accuracies (above 90%) at the stage before the behavioral response time (RT) (332±98ms). In online experiments with three groups of participants (each with three subjects), the system achieved significantly enhanced accuracies (79%, 82%, and 95% for three groups, respectively) at 120 ms after the target onset, which on average was 11% higher than the average individual accuracy, and 6% higher than the best individual accuracy.