Efficient Learning of Healthcare Data from IoT Devices by Edge Convolution Neural Networks

被引:13
作者
He, Yan [1 ,2 ]
Fu, Bin [1 ,2 ]
Yu, Jian [1 ,2 ]
Li, Renfa [1 ,2 ]
Jiang, Rucheng [1 ,2 ]
机构
[1] Hunan Univ, Coll Comp Sci & Elect Engn, Changsha 410082, Hunan, Peoples R China
[2] Key Lab Embedded & Network Comp Hunan Prov, Changsha 410082, Hunan, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2020年 / 10卷 / 24期
基金
中国国家自然科学基金;
关键词
deep convolutional generative adversarial network; deep learning; edge computing; electrocardiograms; DEEP; ANALYTICS; MOBILE;
D O I
10.3390/app10248934
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Wireless and mobile health applications promote the development of smart healthcare. Effective diagnosis and feedbacks of remote health data pose significant challenges due to streaming data, high noise, network latency and user privacy. Therefore, we explore efficient edge and cloud design to maintain electrocardiogram classification performance while reducing the communication cost. These contributions include: (1) We introduce a hybrid smart medical architecture named edge convolutional neural networks (EdgeCNN) that balances the capability of edge and cloud computing to address the issue for agile learning of healthcare data from IoT devices. (2) We present an effective deep learning model for electrocardiogram (ECG) inference, which can be deployed to run on edge smart devices for low-latency diagnosis. (3) We design a data enhancement method for ECG based on deep convolutional generative adversarial network to expand ECG data volume. (4) We carried out experiments on two representative datasets to evaluate the effectiveness of the deep learning model of ECG classification based on EdgeCNN. EdgeCNN shows superior to traditional cloud medical systems in terms of network Input/Output (I/O) pressure, architecture cost and system high availability. The deep learning model not only ensures high diagnostic accuracy, but also has advantages in aspect of inference time, storage, running memory and power consumption.
引用
收藏
页码:1 / 19
页数:19
相关论文
共 35 条
  • [1] Deep learning for decentralized parking lot occupancy detection
    Amato, Giuseppe
    Carrara, Fabio
    Falchi, Fabrizio
    Gennaro, Claudio
    Meghini, Carlo
    Vairo, Claudio
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2017, 72 : 327 - 334
  • [2] The Role of Electrocardiography in Occupational Medicine, from Einthoven's Invention to the Digital Era of Wearable Devices
    Baldassarre, Antonio
    Mucci, Nicola
    Padovan, Martina
    Pellitteri, Alessia
    Viscera, Silvia
    Lecca, Luigi Isaia
    Galea, Raymond P.
    Arcangeli, Giulio
    [J]. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH, 2020, 17 (14) : 1 - 28
  • [3] A novel data augmentation method to enhance deep neural networks for detection of atrial fibrillation
    Cao, Ping
    Li, Xinyi
    Mao, Kedong
    Lu, Fei
    Ning, Gangmin
    Fang, Luping
    Pan, Qing
    [J]. BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2020, 56
  • [4] Chauhan S., P IEEE INT C DAT SCI
  • [5] Goodfellow IJ, 2014, ADV NEUR IN, V27, P2672
  • [6] Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network
    Hannun, Awni Y.
    Rajpurkar, Pranav
    Haghpanahi, Masoumeh
    Tison, Geoffrey H.
    Bourn, Codie
    Turakhia, Mintu P.
    Ng, Andrew Y.
    [J]. NATURE MEDICINE, 2019, 25 (01) : 65 - +
  • [7] Identity Mappings in Deep Residual Networks
    He, Kaiming
    Zhang, Xiangyu
    Ren, Shaoqing
    Sun, Jian
    [J]. COMPUTER VISION - ECCV 2016, PT IV, 2016, 9908 : 630 - 645
  • [8] Detection of frequently overlooked electrocardiographic lead reversals using artificial neural networks
    Heden, B
    Ohlsson, M
    Holst, H
    Mjoman, M
    Rittner, R
    Pahlm, O
    Peterson, C
    Edenbrandt, L
    [J]. AMERICAN JOURNAL OF CARDIOLOGY, 1996, 78 (05) : 600 - &
  • [9] Ioffe S., 2015, PMLR, P448, DOI DOI 10.48550/ARXIV.1502.03167
  • [10] Khairuddin AM, 2017, INT CONF RES INNOV