Conference Publication Details
Mandatory Fields
R. Ahmed, A. Temko, W. Marnane, G. Boylan, G. Lightbody
34th Annual International IEEE EMBS Conference
Dynamic Time Warping Based Neonatal Seizure Detection System
2012
August
Published
1
Scopus: 3 ()
Optional Fields
4919
4922
San Diego, CA, USA
28-AUG-12
01-SEP-12
Neonatal seizures patterns evolve with changing frequency, morphology and propagation. This study is an initial attempt to incorporate the characteristics of temporal evolution of neonatal seizures into our developed neonatal seizure detector. The previously designed SVM-based neonatal seizure detector is modified by substituting the Gaussian kernel with the Gaussian dynamic time warping kernel, to enable the SVM to classify variable length sequences of feature vectors of neonatal seizures. The preliminary results obtained compare favourably with the conventional SVM. The fusion of the two approaches is expected to improve the current state of the art neonatal seizure detection system
10.1109/EMBC.2012.6347097
Grant Details
Science Foundation Ireland
10/IN.1/B3036