English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Integrating low-power wearable Internet of Things (IoT) systems into routinehealth monitoring is an ongoing challenge. Recent advances in the computationcapabilities of wearables make it possible to target complex scenarios byexploiting multiple biosignals and using high-performance algorithms, such asDeep Neural Networks (DNNs). There is, however, a trade-off between performanceof the algorithms and the low-power requirements of IoT platforms with limitedresources. Besides, physically larger and multi-biosignal-based wearables bringsignificant discomfort to the patients. Consequently, reducing powerconsumption and discomfort is necessary for patients to use IoT devicescontinuously during everyday life. To overcome these challenges, in the contextof epileptic seizure detection, we propose a many-to-one signals knowledgedistillation approach targeting single-biosignal processing in IoT wearablesystems. The starting point is to get a highly-accurate multi-biosignal DNN,then apply our approach to develop a single-biosignal DNN solution for IoTsystems that achieves an accuracy comparable to the original multi-biosignalDNN. To assess the practicality of our approach to real-life scenarios, weperform a comprehensive simulation experiment analysis on severalstate-of-the-art edge computing platforms, such as Kendryte K210 and RaspberryPi Zero.

Many-to-One Knowledge Distillation of Real-Time Epileptic Seizure Detection for Low-Power Wearable Internet of Things Systems