Details
Presenter(s)
Display Name
Tsai Chne-Wuen
- Affiliation
-
AffiliationNational University of Singapore
- Country
Abstract
This paper reviews state-of-the-art AI-on-the-edge EEG-based patient-specific epilepsy tracking System-on-Chips (SoCs). For ambulatory tracking and effective treatment of neurological disorders such as seizure and epilepsy, long-term monitoring wearable SoCs are essential to “close the loop”. The design challenges at the Analog Front-End (AFE) (noise, power, signal fidelity, and scalability), as well as various techniques of feature extraction, classification, and online tuning to improve seizure detection accuracy at the Digital Back-End (DBE) are thoroughly analyzed from a system perspective. Furthermore, future trends of the epilepsy tracking system are discussed.