A patient-specific seizure prediction algorithm is proposed using a classifier to differentiate pre-ictal from inter-ictal EEG signals. The spectral power of EEG processed in four different fashions is used as features: raw, time-differential, space-differential, and time/space-differential EEG. The features are classified using cost-sensitive support vector machines by the double cross-validation methodology. The proposed algorithm has been applied to EEG recordings of 18 patients in the Freiburg EEG database, totaling 80 seizures and 437 h long inter-ictal recordings. Classification with the feature obtained from time/space-differential ECoG demonstrates the performance of 86.25% sensitivity and 0.1281 false positives per hour in out-of-sample testing.
Skip Nav Destination
Article navigation
Design Of Medical Devices Conference Abstracts
Seizure Prediction With Spectral Power of EEG Using Cost-Sensitive Support Vector Machines
Keshab Parhi
Keshab Parhi
University of Minnesota
Search for other works by this author on:
Yun Park
University of Minnesota
Theoden Netoff
University of Minnesota
Keshab Parhi
University of Minnesota
J. Med. Devices. Jun 2010, 4(2): 027542 (1 pages)
Published Online: August 12, 2010
Article history
Published:
August 12, 2010
Citation
Park, Y., Netoff, T., and Parhi, K. (August 12, 2010). "Seizure Prediction With Spectral Power of EEG Using Cost-Sensitive Support Vector Machines." ASME. J. Med. Devices. June 2010; 4(2): 027542. https://doi.org/10.1115/1.3455144
Download citation file:
Get Email Alerts
Cited By
Related Articles
The Relationship Between Design Outcomes and Mental States During Ideation
J. Mech. Des (May,2017)
SSVEP-Based Brain-Computer Interface for Part-Picking Robotic Co-Worker
J. Comput. Inf. Sci. Eng (April,2022)
Dry Electrode Based Wearable Wireless Brain–Computer Interface System
J. Nanotechnol. Eng. Med (August,2011)
An Approach to Seizure Onset Detection Using Fuzzy Logic Based on Seizure Evolution in Intracranial EEG
J. Med. Devices (June,2011)
Related Proceedings Papers
Related Chapters
A Review of Most Current Feature Extraction Methods for EEG Signal Processing
International Conference on Computer and Automation Engineering, 4th (ICCAE 2012)
Feature Extraction and Classification of EEG Signal
International Conference on Mechanical Engineering and Technology (ICMET-London 2011)
Acupuncture EEG Time Series Decomposition Based on State Space Method
International Symposium on Information Engineering and Electronic Commerce, 3rd (IEEC 2011)