Decoding of multichannel EEG activity from the visual cortex in response to pseudorandom binary sequences of visual stimuli

• DOI: 10.1002/ima.20288
• Publication Date: 2011-05-10T17:06:54Z
• Authors: Hooman Nezamfar; Umut Orhan; Shalini Purwar; Kenneth Hild; Barry Oken; Deniz Erdogmus
• Keywords: Stimulus (psychology)

Abstract Electroencephalography (EEG) signals have been an attractive choice to build noninvasive brain computer interfaces (BCIs) for nearly three decades. Depending on the stimuli, there are different responses which one could get from EEG signals. One of them is P300 response a visually evoked that has widely studied. Steady state potential (SSVEP) oscillating stimulus with fixed frequency, detectable visual cortex. However, exists some work using m‐sequence lags as control sequence flickering stimuli. In this study, we used several m‐sequences instead intent increasing number possible command options in BCI setting. We also tested two classifiers decide between and study performance multi channel versus single classifiers. The done over frequencies, 15 30 Hz investigate effect frequency accuracy classification methods. Our shows channels correlated, although all contain useful information, but combining classifier based assumption having conditional independence will not improve accuracy. addition, were able reasonably good results comparing give us ability shorter training decision making time. © 2011 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 21, 139–147,