Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Machine Learning Methods for Detection of Epileptic Seizures with Long-Term Wearable Devices

: Houta, Salima; Bisgin, Pinar; Dulich, Pascal

Fulltext (PDF; )

Murata, Y. ; International Academy, Research, and Industry Association -IARIA-:
eTELEMED 2019, the Eleventh International Conference on eHealth, Telemedicine, and Social Medicine : February 24-28, 2019, Athens, Greece
Wilmington/Del.: IARIA, 2019
ISBN: 978-1-61208-688-0
International Conference on eHealth, Telemedicine, and Social Medicine (eTELEMED) <11, 2019, Athens>
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
16SV7482; EPItect
Conference Paper, Electronic Publication
Fraunhofer ISST ()
epilepsy; Seizures; EPItect; SUDEP; automated seizure detection; wearables; IHE; HL7; accelerometer; classification; k-NN

The detection of epileptic seizures plays a major role in patient safety and therapy. Although several research projects on mobile seizure detection have already been conducted, there are still no approaches that are able to reliably detect different seizure types in the home environment. The challenge lies in the variety of symptoms of certain seizure types. The present research describes the project EPItect, which aims to detect epileptic seizures with the help of an In-Ear sensor and to set up a networking infrastructure to exchange medical data between relevant actors. We contribute a machine learning framework for the detection of epileptic seizures and exemplify the application using the example of detection of Generalized Tonic-Clonic Seizures using acceleration data from the In-Ear sensor.