Skip to Main Content
A system of epilepsy seizure detection in real life conditions and based on inertial sensors is presented in this paper with a focus on the signal processing to recognize seizure moves. This system is based on several models of signals, one corresponding to general movements, and two others describing seizures moves. The detection algorithm evaluates for a given time window which model fits the best with the observed signals and trigger an alarm if this model is a seizure model. The signal processing algorithm is based on hidden Markov models.