Login / Signup

Design of Edge-IoMT Network Architecture with Weight-Based Scheduling.

Li-Min TsengPing-Feng ChenChih-Yu Wen
Published in: Sensors (Basel, Switzerland) (2023)
Population health monitoring based on the Internet of Medical Things (IoMT) is becoming an important application trend healthcare improvement. This work aims to develop an autonomous network architecture, collecting sensor data with a cluster topology, forwarding information through relay nodes, and applying edge computing and transmission scheduling for network scalability and operational efficiency. The proposed distributed network architecture incorporates data compression technologies and effective scheduling algorithms for handling the transmission scheduling of various physiological signals. Compared to existing scheduling mechanisms, the experimental results depict the network performance and show that in analyzing the delay and jitter, the proposed WFQ-based algorithms have reduced the delay and jitter ratio by about 40% and 19.47% compared to LLQ with priority queueing scheme, respectively. The experimental results also demonstrate that the proposed network topology is more effective than the direct path transmission approach in terms of energy consumption, which suggests that the proposed network architecture may improve the development of medical applications with body area networks such that the goal of self-organizing population health monitoring can be achieved.
Keyphrases
  • healthcare
  • machine learning
  • physical activity
  • deep learning
  • big data
  • weight loss
  • artificial intelligence
  • social media
  • body weight