Fronto-Parietal Gamma-Oscillations are a Cause of Performance Variation in Brain-Computer Interfacing
5th International IEEE/EMBS Conference on Neural Engineering (NE 2011)
In recent work, we have provided evidence that fronto-parietal gamma-oscillations of the electromagnetic field of the brain modulate the sensorimotor-rhythm. It is unclear, however, what impact this effect may have on explaining and addressing within-subject performance variations of braincomputer interfaces (BCIs). In this paper, we provide evidence that on a group-average classification accuracies in a two-class motor-imagery paradigm differ by up to 22.2% depending on the state of fronto-parietal g -power. As such, this effect may have a large impact on the design of future BCI-systems. We further investigate whether adapting classification procedures to the current state of gamma-power improves classification accuracy, and discuss other approaches to exploiting this effect.