Decoding Phase-based Information from SSVEP Recordings with Use of Complex-Valued Neural Network

摘要

In this paper, we report on decoding of phase-based information from steady-state visual evoked potential (SSVEP) recordings with use of complex-valued neural network. The networks of this kind has inputs and output well fitted for the considered task. The dependency of the decoding accuracy from the number of targets and the decoding window size is discussed. Comparing the existing phase-based SSVEP decoding methods with the proposed approach, we show that the latter performs better for bigger amount of target classes and sufficient length of time window used in the decoding procedure. The necessity of the proper frequency selection for each subject is discussed.