作者: Seung-Min Park , Pharino Chum , Kwang-Eun Ko , Kwee-Bo Sim
DOI:
关键词:
摘要: In cue based motor imagery brain computer interface (BCI) paradigm, subject was stimulated by different to distinguish imagination task and proceed tasks. These evoked the specific related frequency rhythms. But problem appears as theses rhythms change due task. While some is fast induce electrical signal rhythms, other has long latency in them. This time temporal of imagination. To boost accuracy EEG translation for reliable system, this paper, we proposed a method extracting optimal feature. First, signals were extracted apply Laplace filter band pass with 7Hz 40Hz. Channels C3, Cz, C4 applied Short-Time Fourier Transform 1Hz. R-square correlation coefficient three channels found selected best parameter. Finally, parameters, STFT feature extracted. We simulated classification linear discriminant analysis BCI competition IV, III our laboratory dataset.