@proceedings {2241, title = {Detection of spontaneous class-specific visual stimuli with high temporal accuracy in human electrocorticography.}, volume = {2009}, year = {2009}, month = {2009}, pages = {6465-8}, abstract = {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.}, keywords = {Algorithms, Electrocardiography, Evoked Potentials, Visual, Humans, Male, Pattern Recognition, Automated, Pattern Recognition, Visual, Photic Stimulation, Reproducibility of Results, Sensitivity and Specificity, User-Computer Interface, Visual Cortex}, issn = {1557-170X}, doi = {10.1109/IEMBS.2009.5333546}, author = {Miller, John W and Hermes, Dora and Gerwin Schalk and Ramsey, Nick F and Jagadeesh, Bharathi and den Nijs, Marcel and Ojemann, J G and Rao, Rajesh P N} } @proceedings {2240, title = {Three cases of feature correlation in an electrocorticographic BCI.}, year = {2008}, month = {2008}, pages = {5318-21}, abstract = {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.}, keywords = {Adolescent, Adult, Algorithms, Electrocardiography, Evoked Potentials, Motor, Female, Humans, Male, Middle Aged, Motor Cortex, Pattern Recognition, Automated, Statistics as Topic, Task Performance and Analysis, User-Computer Interface}, issn = {1557-170X}, doi = {10.1109/IEMBS.2008.4650415}, author = {Miller, John W and Blakely, Timothy and Gerwin Schalk and den Nijs, Marcel and Rao, Rajesh P N and Ojemann, J G} } @article {2173, title = {Electrocorticography-based brain computer interface--the Seattle experience.}, journal = {IEEE Trans Neural Syst Rehabil Eng}, volume = {14}, year = {2006}, month = {06/2006}, pages = {194-8}, abstract = {

Electrocorticography (ECoG) has been demonstrated to be an effective modality as a platform for brain-computer interfaces (BCIs). Through our experience with ten subjects, we further demonstrate evidence to support the power and flexibility of this signal for BCI usage. In a subset of four patients, closed-loop BCI experiments were attempted with the patient receiving online feedback that consisted of one-dimensional cursor movement controlled by ECoG features that had shown correlation with various real and imagined motor and speech tasks. All four achieved control, with final target accuracies between 73\%-100\%. We assess the methods for achieving control and the manner in which enhancing online control can be accomplished by rescreening during online tasks. Additionally, we assess the relevant issues of the current experimental paradigm in light of their clinical constraints.

}, keywords = {Cerebral Cortex, Electroencephalography, Epilepsy, Evoked Potentials, Humans, Therapy, Computer-Assisted, User-Computer Interface, Washington}, issn = {1534-4320}, doi = {10.1109/TNSRE.2006.875536}, url = {http://www.ncbi.nlm.nih.gov/pubmed/16792292}, author = {Leuthardt, E C and Miller, John W and Gerwin Schalk and Rao, Rajesh P N and Ojemann, J G} }