Integrating video and accelerometer signals for nocturnal epileptic seizure detection

Authors:
Kris Cuppens;Chih-Wei Chen;Kevin Bing-Yung Wong;Anouk Van de Vel;Lieven Lagae;Berten Ceulemans;Tinne Tuytelaars;Sabine Van Huffel;Bart Vanrumste;Hamid Aghajan
Affiliations:
K. H. Kempen, KU Leuven & IBBT, Leuven, Belgium;Stanford University, Stanford, CA, USA;Stanford University, Stanford, CA, USA;University Hospital of Antwerp, Antwerp, Belgium;University Hospital Leuven, Leuven, Belgium;University Hospital of Antwerp, Antwerp, Belgium;KU Leuven, Leuven, Belgium;KU Leuven & IBBT, Leuven, Belgium;K. H. Kempen, KU Leuven & IBBT, Leuven, Belgium, Belgium;Stanford University, Stanford, CA, USA
Venue:
Proceedings of the 14th ACM international conference on Multimodal interaction
Year:
2012

Citing 4
Cited 0

Original Contribution: Stacked generalization

Neural Networks
Probability Estimates for Multi-class Classification by Pairwise Coupling

The Journal of Machine Learning Research
On Space-Time Interest Points

International Journal of Computer Vision
Time-frequency analysis of accelerometry data for detection of myoclonic seizures

IEEE Transactions on Information Technology in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

Epileptic seizure detection is traditionally done using video/electroencephalogram (EEG) monitoring, which is not applicable in a home situation. In recent years, attempts have been made to detect the seizures using other modalities. In this paper we investigate if a combined usage of accelerometers attached to the limbs and video data would increase the performance compared to a single modality approach. Therefore, we used two existing approaches for seizure detection in accelerometers and video and combined them using a linear discriminant analysis (LDA) classifier. The results for a combined detection have a better positive predictive value (PPV) of 95.00% compared to the single modality detection and reached a sensitivity of 83.33%.