Many-to-One Knowledge Distillation of Real-Time Epileptic Seizure Detection for Low-Power Wearable Internet of Things Systems
This work addresses the need for efficient, comfortable, and continuous health monitoring for epilepsy patients using wearable IoT devices, representing an incremental improvement in optimizing existing methods for specific constraints.
The paper tackled the challenge of balancing high accuracy with low power consumption and patient discomfort in wearable IoT systems for epileptic seizure detection by proposing a many-to-one knowledge distillation approach that transfers knowledge from a multi-biosignal DNN to a single-biosignal DNN, achieving comparable accuracy while enabling deployment on resource-constrained edge platforms like Kendryte K210 and Raspberry Pi Zero.
Integrating low-power wearable Internet of Things (IoT) 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). There is, however, a trade-off between performance of the algorithms and the low-power requirements of IoT 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 IoT devices continuously during everyday life. To overcome these challenges, in the context of epileptic seizure detection, we propose a many-to-one signals knowledge distillation approach targeting single-biosignal processing in IoT wearable systems. The starting point is to get a highly-accurate multi-biosignal DNN, then apply our approach to develop a single-biosignal DNN solution for IoT 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 state-of-the-art edge computing platforms, such as Kendryte K210 and Raspberry Pi Zero.