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

The increasing number of edge devices with enhanced sensing capabilities,such as smartphones, wearables, and IoT devices equipped with sensors, holdsthe potential for innovative smart-edge applications in healthcare. Thesedevices generate vast amounts of multimodal data, enabling the implementationof digital biomarkers which can be leveraged by machine learning solutions toderive insights, predict health risks, and allow personalized interventions.Training these models requires collecting data from edge devices andaggregating it in the cloud. To validate and verify those models, it isessential to utilize them in real-world scenarios and subject them to testingusing data from diverse cohorts. Since some models are too computationallyexpensive to be run on edge devices directly, a collaborative framework betweenthe edge and cloud becomes necessary. In this paper, we present CLAID, anopen-source cross-platform middleware framework based on transparent computingcompatible with Android, iOS, WearOS, Linux, macOS, and Windows. CLAID enableslogical integration of devices running different operating systems into anedge-cloud system, facilitating communication and offloading between them, withbindings available in different programming languages. We provide Modules fordata collection from various sensors as well as for the deployment ofmachine-learning models. Furthermore, we propose a novel methodology, "ML-Modelin the Loop" for verifying deployed machine learning models, which helps toanalyze problems that may occur during the migration of models from cloud toedge devices. We verify our framework in three different experiments andachieve 100% sampling coverage for data collection across different sensors aswell as an equal performance of a cough detection model deployed on bothAndroid and iOS devices. We evaluate the memory and battery consumption of ourframework.

CLAID: Closing the Loop on AI & Data Collection -- A Cross-Platform  Transparent Computing Middleware Framework for Smart Edge-Cloud and Digital  Biomarker Applications