Scholarlink

Healthcare 4.0 envisions intelligent hospital environments where continuous, non-invasive, and scalable patient monitoring is seamlessly integrated with advanced analytics and ultra-reliable communication. Traditional wearable cardiac monitors often suffer from performance degradation due to motion artifacts, electromagnetic interference (EMI) from nearby medical equipment, and limitations in monitoring multiple patients simultaneously. Fiber Bragg Grating (FBG) sensors, with their immunity to EMI, high multiplexing capacity, and mechanical sensitivity, offer an effective platform for distributed physiological signal acquisition. This paper presents a distributed FBG sensor network deployed across multiple patients and an edge-based Graph Neural Network (GNN) framework for robust cardiac health monitoring. The GNN leverages both temporal features of individual ballistocardiogram (BCG) signals and spatial correlations among patients to suppress artifacts and improve anomaly detection accuracy. A 5G architecture with Ultra-Reliable Low-Latency Communication (URLLC) slices is used for critical alert transmission, while enhanced Mobile Broadband (eMBB) handles periodic waveform uploads. Simulation results show that the proposed system achieves heart rate estimation with a Root Mean Square Error (RMSE) of 2.15 bpm, anomaly detection F1-score of 0.97, and end-to-end alert latency under 4 ms with 99.999% packet delivery reliability. These findings highlight the potential of combining distributed FBG sensing, edge GNN analytics, and 5G URLLC for next-generation, multi-patient cardiac monitoring in smart hospital settings.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Distributed FBG Sensor Network with Edge Graph Neural Networks for Multi-patient Cardiac Health Monitoring Over URLLC in Healthcare 4.0

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Abhimanyu Jena,
  • Ambarish G. Mohapatra,
  • Anita Mohanty,
  • Mohammed Abdul Jaleel Maktoof,
  • Aqeel Al-Hilali

摘要

Healthcare 4.0 envisions intelligent hospital environments where continuous, non-invasive, and scalable patient monitoring is seamlessly integrated with advanced analytics and ultra-reliable communication. Traditional wearable cardiac monitors often suffer from performance degradation due to motion artifacts, electromagnetic interference (EMI) from nearby medical equipment, and limitations in monitoring multiple patients simultaneously. Fiber Bragg Grating (FBG) sensors, with their immunity to EMI, high multiplexing capacity, and mechanical sensitivity, offer an effective platform for distributed physiological signal acquisition. This paper presents a distributed FBG sensor network deployed across multiple patients and an edge-based Graph Neural Network (GNN) framework for robust cardiac health monitoring. The GNN leverages both temporal features of individual ballistocardiogram (BCG) signals and spatial correlations among patients to suppress artifacts and improve anomaly detection accuracy. A 5G architecture with Ultra-Reliable Low-Latency Communication (URLLC) slices is used for critical alert transmission, while enhanced Mobile Broadband (eMBB) handles periodic waveform uploads. Simulation results show that the proposed system achieves heart rate estimation with a Root Mean Square Error (RMSE) of 2.15 bpm, anomaly detection F1-score of 0.97, and end-to-end alert latency under 4 ms with 99.999% packet delivery reliability. These findings highlight the potential of combining distributed FBG sensing, edge GNN analytics, and 5G URLLC for next-generation, multi-patient cardiac monitoring in smart hospital settings.