| Title | Detection of spontaneous class-specific visual stimuli with high temporal accuracy in human electrocorticography. |
| Publication Type | Conference Proceedings |
| Year of Conference | 2009 |
| Authors | Miller, JW, Hermes, D, Schalk, G, Ramsey, NF, Jagadeesh, B, den Nijs, M, Ojemann, JG, Rao, RPN |
| Conference Name | Conf Proc IEEE Eng Med Biol Soc |
| Volume | 2009 |
| Pagination | 6465-8 |
| Date Published | 2009 |
| ISBN | 1557-170X |
| 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 |
| 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.
|
| DOI | 10.1109/IEMBS.2009.5333546 |
| PubMed ID | 19964434 |
