Lightweight Machine Learning for Seizure Detection on Wearable Devices

Baichuan Huang; Azra Abtahi; Amir Aminifar

ICASSP 2023accepted0 citations

Lightweight Machine Learning for Seizure Detection on Wearable Devices

Baichuan Huang, Azra Abtahi, Amir Aminifar

Abstract

For patients with epilepsy, automatic epilepsy monitoring, i.e., the process of direct observation of the patient’s health status in real time, is crucial. Wearable systems provide the possibility of real-time epilepsy monitoring and alerting caregivers upon the occurrence of a seizure. In the context of the ICASSP 2023 Seizure Detection Challenge, we propose a lightweight machine-learning framework for real-time epilepsy monitoring on wearable devices. We evaluate our proposed framework on the SeizeIT2 dataset from the wearable SensorDot (SD) of Byteflies. The experimental results show that our proposed framework achieves a sensitivity of 73.6% and a specificity of 96.7% in seizure detection.

BibTeX

@inproceedings{icassp2023_lightweightmachi,
  title = {Lightweight Machine Learning for Seizure Detection on Wearable Devices},
  author = {Baichuan Huang and Azra Abtahi and Amir Aminifar},
  booktitle = {ICASSP 2023},
  year = {2023}
}