M2SKD: Multi-to-Single Knowledge Distillation of Real-Time Epileptic Seizure Detection for Low-Power Wearable Systems

Integrating low-power wearable systems into routine health monitoring is an ongoing challenge. Recent advances in the computation capabilities of wearables make it possible to target complex scenarios by exploiting multiple biosignals and using high-performance algorithms, such as Deep Neural Networ...

Descripción completa

Detalles Bibliográficos
Autores: Baghersalimi, S., Amirshahi, A., Forooghifar, F., Teijeiro, T., Aminifar, A., Atienza, D.
Tipo de recurso: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2024
País:España
Institución:Basque Center for Applied Mathematics (BCAM)
Repositorio:BIRD. BCAM's Institutional Repository Data
OAI Identifier:oai:bird.bcamath.org:20.500.11824/1938
Acceso en línea:http://hdl.handle.net/20.500.11824/1938
Access Level:acceso abierto
Palabra clave:deep learning
Edge computing
electrocardiography
Descripción
Sumario:Integrating low-power wearable systems into routine health monitoring is an ongoing challenge. Recent advances in the computation capabilities of wearables make it possible to target complex scenarios by exploiting multiple biosignals and using high-performance algorithms, such as Deep Neural Networks (DNNs). However, there is a tradeoff between the algorithms' performance and the low-power requirements of platforms with limited resources. Besides, physically larger and multi-biosignal-based wearables bring significant discomfort to the patients. Consequently, reducing power consumption and discomfort is necessary for patients to use wearable devices continuously during everyday life. To overcome these challenges, in the context of epileptic seizure detection, we propose the Multi-to-Single Knowledge Distillation (M2SKD) approach targeting single-biosignal processing in wearable systems. The starting point is to train a highly-accurate multi-biosignal DNN, then apply M2SKD to develop a single-biosignal DNN solution for wearable systems that achieves an accuracy comparable to the original multi-biosignal DNN. To assess the practicality of our approach to real-life scenarios, we perform a comprehensive simulation experiment analysis on several edge computing platforms.