Implementing the confidence constraint cloud-edge collaborative computing strategy for ultra-efficient arrhythmia monitoring

被引:1
作者
Chen, Jiarong [1 ]
Zhang, Xianbin [1 ]
Xu, Lin [2 ,3 ]
de Albuquerque, Victor Hugo C. [4 ]
Wu, Wanqing [1 ]
机构
[1] Sun Yat Sen Univ, Sch Biomed Engn, Guangdong Prov Key Lab Sensor Technol & Biomed Ins, Shenzhen 518107, Peoples R China
[2] Gen Hosp Southern Theatre Command, Guangzhou 510010, Peoples R China
[3] Southern Med Univ, Sch Clin Med 1, Guangzhou 510515, Peoples R China
[4] Univ Fed Ceara, Dept Teleinformat Engn, Fortaleza, CE, Brazil
关键词
ECG classification; Cloud computing; Personalized strategy; Edge computing; Collaborative intelligence; CARDIOVASCULAR-DISEASES; ATRIAL-FIBRILLATION; QRS DETECTION; HEALTH-CARE; ECG; CLASSIFICATION; ALGORITHM; INTERNET; BURDEN; IMPACT;
D O I
10.1016/j.asoc.2024.111402
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Electrocardiogram(ECG) monitoring is a critical and intricate task in cardiac healthcare. While large models supported by the remote cloud servers with abundant computational resources offers a feasible solution for this task, which still face challenges related to processing costs, privacy risks, and response time. Efforts have been made to integrate edge computing as a supplementary solution, but the current collaborative computing strategy for ECG monitoring is static and inefficient. To address these shortcomings, this study proposes an innovative confidence constraint cloud-edge collaborative computing(3CE2C) strategy. Firstly, the model implementation processes are illustrated, including an ultra-lightweight model for the edge node and a large model for the cloud server. To enhance classification performance, the personalized strategy is employed, resulting in an accuracy improvement from 0.9849 to 0.9929 in the model-cloud. For edge implementation, the optimal input length and model quantization both are explored to reduce the energy consumption. Based on the given confidence constraint, the models dynamically collaborate, with the low-confidence samples uploaded to the cloud server. This approach can achieve accuracy comparable to cloud computing, transmitting only about 17% low-confidence samples, the accuracy ratio(rmc) is 0.9985. In addition, the method is validated in SVDB, where 3CE2C outperforms state-of-the art framework with the same uploaded sample ratio, resulting in a 1.54% improvement in classification accuracy. In conclusion, the proposed method provides a practical solution in real-time arrhythmia detection applications.
引用
收藏
页数:12
相关论文
共 62 条
  • [1] [Anonymous], 2011, Cardiovascular disease
  • [2] Personalized Real-Time Federated Learning for Epileptic Seizure Detection
    Baghersalimi, Saleh
    Teijeiro, Tomas
    Atienza, David
    Aminifar, Amir
    [J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2022, 26 (02) : 898 - 909
  • [3] Design and Implementation of an Ultralow-Power ECG Patch and Smart Cloud-Based Platform
    Baraeinejad, Bardia
    Shayan, Masood Fallah
    Vazifeh, Amir Reza
    Rashidi, Diba
    Hamedani, Mohammad Saberi
    Tavolinejad, Hamed
    Gorji, Pouya
    Razmara, Parsa
    Vaziri, Kiarash
    Vashaee, Daryoosh
    Fakharzadeh, Mohammad
    [J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
  • [4] Bouthillier X., 2015, Dropout as data augmentation
  • [5] Multi-ECGNet for ECG Arrythmia Multi-Label Classification
    Cai, Junxian
    Sun, Weiwei
    Guan, Jianfeng
    You, Ilsun
    [J]. IEEE ACCESS, 2020, 8 : 110848 - 110858
  • [6] Rule-based rough-refined two-step-procedure for real-time premature beat detection in single-lead ECG
    Cai, Zhipeng
    Li, Jianqing
    Johnson, Alistair E. W.
    Zhang, Xiangyu
    Shen, Qin
    Zhang, Jian
    Liu, Chengyu
    [J]. PHYSIOLOGICAL MEASUREMENT, 2020, 41 (05)
  • [7] Edge2Analysis: A Novel AIoT Platform for Atrial Fibrillation Recognition and Detection
    Chen, Jiarong
    Zheng, Yingfang
    Liang, Yingshan
    Zhan, Zehui
    Jiang, Mingzhe
    Zhang, Xianbin
    da Silva, Daniel S. S.
    Wu, Wanqing
    de Albuquerque, Victor Hugo C.
    [J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2022, 26 (12) : 5772 - 5782
  • [8] Deep learning-based multidimensional feature fusion for classification of ECG arrhythmia
    Cui, Jianfeng
    Wang, Lixin
    He, Xiangmin
    De Albuquerque, Victor Hugo C.
    AlQahtani, Salman A.
    Hassan, Mohammad Mehedi
    [J]. NEURAL COMPUTING & APPLICATIONS, 2023, 35 (22) : 16073 - 16087
  • [9] Energy-Efficient Real-Time Heart Monitoring on Edge-Fog-Cloud Internet of Medical Things
    Demirel, Berken Utku
    Bayoumy, Islam Abdelsalam
    Al Faruque, Mohammad Abdullah
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2021, 9 (14) : 12472 - 12481
  • [10] An Open IoHT-Based Deep Learning Framework for Online Medical Image Recognition
    Dourado Jr, Carlos M. J. M.
    da Silva, Suane Pires P.
    da Nobrega, Raul Victor M.
    Reboucas Filho, Pedro P.
    Muhammad, Khan
    de Albuquerque, Victor Hugo C.
    [J]. IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2021, 39 (02) : 541 - 548