Energy-efficient Sensor-based EEG Features’ Extraction for Epilepsy Detection

The deployment of wireless body sensor (WBS) in e-health systems represents an attractive solution due to the low-cost and the wearability of these devices. WBS(s) can be used for automatic detection of epileptic seizures which can considerably improve the patients’ quality of life. However, the main challenge that faces the sensor-based solution is the energy efficiency. In this context, this paper proposes a new energy efficient scheme for onset epilepsy seizure detection for non-invasive EEG using wireless body sensor networks. This new scheme is based on local features’ extraction using Haar wavelet transform of the segmented EEG signal. If the epilepsy seizure is detected, a notification is then transmitted to a remote server. The paper discusses the design of this scheme. It also presents the performances’ analysis for epilepsy detection and its energy efficiency when implemented in sensors. The results show that for 10 sec segments, the proposed scheme has sensitivity of 97% and it saves 46% sensor energy compared to full streaming of the raw EEG data to remote server.