%0 Conference Proceedings %B Conf Proc IEEE Eng Med Biol Soc %D 2009 %T Detection of spontaneous class-specific visual stimuli with high temporal accuracy in human electrocorticography. %A Miller, John W %A Hermes, Dora %A Gerwin Schalk %A Ramsey, Nick F %A Jagadeesh, Bharathi %A den Nijs, Marcel %A Ojemann, J G %A Rao, Rajesh P N %K Algorithms %K Electrocardiography %K Evoked Potentials, Visual %K Humans %K Male %K Pattern Recognition, Automated %K Pattern Recognition, Visual %K Photic Stimulation %K Reproducibility of Results %K Sensitivity and Specificity %K User-Computer Interface %K Visual Cortex %X Most brain-computer interface classification experiments from electrical potential recordings have been focused on the identification of classes of stimuli or behavior where the timing of experimental parameters is known or pre-designated. Real world experience, however, is spontaneous, and to this end we describe an experiment predicting the occurrence, timing, and types of visual stimuli perceived by a human subject from electrocorticographic recordings. All 300 of 300 presented stimuli were correctly detected, with a temporal precision of order 20 ms. The type of stimulus (face/house) was correctly identified in 95% of these cases. There were approximately 20 false alarm events, corresponding to a late 2nd neuronal response to a previously identified event. %B Conf Proc IEEE Eng Med Biol Soc %V 2009 %P 6465-8 %8 2009 %G eng %R 10.1109/IEMBS.2009.5333546 %0 Conference Proceedings %B Conf Proc IEEE Eng Med Biol Soc %D 2008 %T Three cases of feature correlation in an electrocorticographic BCI. %A Miller, John W %A Blakely, Timothy %A Gerwin Schalk %A den Nijs, Marcel %A Rao, Rajesh P N %A Ojemann, J G %K Adolescent %K Adult %K Algorithms %K Electrocardiography %K Evoked Potentials, Motor %K Female %K Humans %K Male %K Middle Aged %K Motor Cortex %K Pattern Recognition, Automated %K Statistics as Topic %K Task Performance and Analysis %K User-Computer Interface %X Three human subjects participated in a closed-loop brain computer interface cursor control experiment mediated by implanted subdural electrocorticographic arrays. The paradigm consisted of several stages: baseline recording, hand and tongue motor tasks as the basis for feature selection, two closed-loop one-dimensional feedback experiments with each of these features, and a two-dimensional feedback experiment using both of the features simultaneously. The two selected features were simple channel and frequency band combinations associated with change during hand and tongue movement. Inter-feature correlation and cross-correlation between features during different epochs of each task were quantified for each stage of the experiment. Our anecdotal, three subject, result suggests that while high correlation between horizontal and vertical control signal can initially preclude successful two-dimensional cursor control, a feedback-based learning strategy can be successfully employed by the subject to overcome this limitation and progressively decorrelate these control signals. %B Conf Proc IEEE Eng Med Biol Soc %P 5318-21 %8 2008 %G eng %R 10.1109/IEMBS.2008.4650415