Title :
Electrocorticogram as the basis for a direct brain interface: Opportunities for improved detection accuracy
Author :
Huggins, J.E. ; Levine, S.P. ; Fessler, J.A. ; Sowers, W.M. ; Pfurtscheller, G. ; Graimann, B. ; Schloegl, A. ; Minecan, D.N. ; Kushwaha, R.K. ; BeMent, S.L. ; Sagher, O. ; Schuh, L.A.
Author_Institution :
Michigan Univ., Ann Arbor, MI, USA
Abstract :
A direct brain interface (DBI) based on the detection of event-related potentials (ERPs) in human electrocorticogram (ECoG) is under development. Accurate detection has been demonstrated with this approach (near 100% on a few channels) using a single-channel cross-correlation template matching (CCTM) method. Several opportunities for improved detection accuracy have been identified. Detection using a multiple-channel CCTM method and a variety of detection methods that take advantage of the simultaneous occurrence of ERPs and event-related desynchronization/synchronization (ERD/ERS) have been demonstrated to offer potential for improved detection accuracy.
Keywords :
autoregressive processes; bioelectric potentials; correlation methods; electroencephalography; handicapped aids; medical signal processing; user interfaces; adaptive autoregressive modeling; brain-computer interface; cortical neural-networks; cross-correlation template matching; direct brain interface; event-related desynchronization; event-related potentials; event-related synchronization; genetic algorithms; human electrocorticogram; human-computer interface; improved detection accuracy; motor imagery; multiple-channel method; quadratic model; single-channel method; voluntary action; wavelet packet analysis; Biomedical engineering; Biomedical informatics; Brain computer interfaces; Electrodes; Enterprise resource planning; Feedback; Hospitals; Humans; Muscles; Testing;
Conference_Titel :
Neural Engineering, 2003. Conference Proceedings. First International IEEE EMBS Conference on
Print_ISBN :
0-7803-7579-3
DOI :
10.1109/CNE.2003.1196896
