Instantaneous Gaze-Target Detection by Empirical Mode Decomposition: Application to Brain Computer Interface

摘要: This paper presents an Empirical mode decomposition (EMD) approach for achieving high-speed frequency-tagged steady state visual evoked potential (SSVEP) brain computer interface (BCI) system. has been demonstrated as a local and fully data-driven technique the data processing of nonlinear non-stationary time-series. It allows frequency amplitude time-series to be evaluated with excellent time resolution. The proposed system utilized flickering sources high rate acting cursor purpose alternatively communication Induced EEG signal were decomposed into different scale oscillation components namely intrinsic functions. In order find out SSVEP-related IMFs, instantaneous computed by generalized zero crossing (GZC). After identification power quadrature detection, result shows achieved 51.46 bits/min average ITR. Compare FFT approaches, EMD method provide better temporal sensitivity in detection cognitive neuron activities.