Improvement of Classification Accuracy in a Phase-Tagged Steady-State Visual Evoked Potential-Based Brain–Computer Interface Using Adaptive Neuron-Fuzzy Classifier

摘要: Steady-state visual evoked potential (SSVEP) has been used to design brain–computer interface (BCI) for a variety of applications, due its advantages high accuracy, fewer electrodes, and information transfer rate. In recent years, researchers developed phase-tagged SSVEP-based BCI overcome the problem amplitude–frequency preference in traditional frequency-coded SSVEPs. However, phase SSVEP could be affected by subject’s attention emotion, which sometimes causes ambiguity discerning gazed targets when fixed margins were class classification. this study, we adopted adaptive neuron-fuzzy classifier (ANFC) improve gaze-target detections. The features polar coordinates first transformed into Cartesian coordinates, then ANFC was utilized accuracy gazed-target proposed ANFC-based approach achieved 63.07 ± 8.13 bits/min.