TY - GEN
T1 - Epileptic seizure prediction using the spatiotemporal correlation structure of intracranial EEG
AU - Williamson, James R.
AU - Bliss, Daniel W.
AU - Browne, David W.
PY - 2011/8/18
Y1 - 2011/8/18
N2 - A patient-specific seizure prediction algorithm is proposed that extracts novel multivariate signal coherence features from ECoG recordings and classifies a patient's pre-seizure state. The algorithm uses space-delay correlation and covariance matrices at several delay scales to extract the spatiotemporal correlation structure from multichannel ECoG signals. Eigenspectra and amplitude features are extracted from the correlation and covariance matrices, followed by dimensionality reduction using principal components analysis, classification using a support vector machine, and temporal integration to produce a seizure prediction score. Evaluation on the Freiburg EEG database produced a sensitivity of 90.8% and false positive rate of.094.
AB - A patient-specific seizure prediction algorithm is proposed that extracts novel multivariate signal coherence features from ECoG recordings and classifies a patient's pre-seizure state. The algorithm uses space-delay correlation and covariance matrices at several delay scales to extract the spatiotemporal correlation structure from multichannel ECoG signals. Eigenspectra and amplitude features are extracted from the correlation and covariance matrices, followed by dimensionality reduction using principal components analysis, classification using a support vector machine, and temporal integration to produce a seizure prediction score. Evaluation on the Freiburg EEG database produced a sensitivity of 90.8% and false positive rate of.094.
KW - EEG Signal Processing
KW - Epilepsy
KW - Multivariate Features
KW - Seizure Prediction
KW - Support Vector Machines
UR - http://www.scopus.com/inward/record.url?scp=80051641173&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80051641173&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2011.5946491
DO - 10.1109/ICASSP.2011.5946491
M3 - Conference contribution
AN - SCOPUS:80051641173
SN - 9781457705397
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 665
EP - 668
BT - 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings
T2 - 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
Y2 - 22 May 2011 through 27 May 2011
ER -