Edge-Computing AI for Medical Devices

Electronic medical devices can be implantables, wearables, and remote. These devices can collect varioius multimodal and multigrain bio-signals invasively or non-invasively. This large heterogeneous data from medical devices contains tremendous information that can be analyzed with artificial intelligence (AI). Many medical applications require edge-computing AI for real-time data processing, decision making, or feedback for unsupervised settings to seamlessly generate meaningful interpretations and actionable decisions with high degree of accuracy and reliability. Rapid progress in embedded technologies with high computing power and ubiquitous connectivity using Bluetooth, Wi-Fi, and 5G along with miniature, low-cost, flexible, and reliable sensors have paved the hardware revolution for these technologies. Advancements in edge-computing AI algorithms with machine learning (ML) and deep learning (DL) techniques with real-time interactive systems. The purpose of this collection is to address the on-going research activities in these fields with focus on edge-computing AI for a variety of applications including biomedical, assistive technologies, elderly monitoring, mobile-health, and smart-health.

This Collection supports and amplifies research related to: SDG 3