Peer-Reviewed Journal Details
Mandatory Fields
Ahmed, R;Temko, A;Marnane, WP;Boylan, G;Lightbody, G
2017
March
Computers In Biology and Medicine
Exploring temporal information in neonatal seizures using a dynamic time warping based SVM kernel
Validated
WOS: 23 ()
Optional Fields
SUPPORT VECTOR MACHINES HYPOXIC-ISCHEMIC ENCEPHALOPATHY SPEAKER VERIFICATION EEG CLASSIFICATION RECOGNITION PERFORMANCE MODELS ALGORITHM SERIES
82
100
110
Seizure events in newborns change in frequency, morphology, and propagation. This contextual information is explored at the classifier level in the proposed patient-independent neonatal seizure detection system. The system is based on the combination of a static and a sequential SVM classifier. A Gaussian dynamic time warping based kernel is used in the sequential classifier. The system is validated on a large dataset of EEG recordings from 17 neonates. The obtained results show an increase in the detection rate at very low false detections per hour, particularly achieving a 12% improvement in the detection of short seizure events over the static RBF kernel based system.
OXFORD
0010-4825
10.1016/j.compbiomed.2017.01.017
Grant Details