A lightweight convolutional neural network hardware implementation for wearable heart rate anomaly detection

被引:23
作者
Gu, Minghong [1 ]
Zhang, Yuejun [1 ]
Wen, Yongzhong [1 ]
Ai, Guangpeng [1 ]
Zhang, Huihong [1 ]
Wang, Pengjun [2 ]
Wang, Guoqing [3 ]
机构
[1] Ningbo Univ, Fac Elect Engn & Comp Sci, Ningbo 315211, Zhejiang, Peoples R China
[2] Wenzhou Univ, Elect & Elect Engn, Wenzhou 325035, Zhejiang, Peoples R China
[3] Zhejiang Suosi Technol Co Ltd, Wenzhou 325000, Zhejiang, Peoples R China
基金
中国国家自然科学基金;
关键词
Convolutional neural networks; ECG detection; Data reuse; Hardware efficiency; ECG; CLASSIFICATION;
D O I
10.1016/j.compbiomed.2023.106623
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
In this article, we propose a lightweight and competitively accurate heart rhythm abnormality classification model based on classical convolutional neural networks in deep neural networks and hardware acceleration techniques to address the shortcomings of existing wearable devices for ECG detection. The proposed approach to build a high-performance ECG rhythm abnormality monitoring coprocessor achieves a high degree of data reuse in time and space, which reduces the number of data flows, provides a more efficient hardware implementation and reduces hardware resource consumption than most existing models. The designed hardware circuit relies on 16-bit floating-point numbers for data inference at the convolutional, pooling, and fully connected layers, and implements acceleration of the computational subsystem through a 21-group floating-point multiplicative-ad-ditive computational array and an adder tree. The front-and back-end design of the chip was completed on the TSMC 65 nm process. The device has an area of 0.191 mm2, a core voltage of 1 V, an operating frequency of 20 MHz, a power consumption of 1.1419 mW, and requires 5.12 kByte of storage space. The architecture was evaluated using the MIT-BIH arrhythmia database dataset, which showed a classification accuracy of 97.69% and a classification time of 0.3 ms for a single heartbeat. The hardware architecture offers high accuracy with a simple structure, low resource footprint, and the ability to operate on edge devices with relatively low hardware configurations.
引用
收藏
页数:13
相关论文
共 37 条
  • [1] Abdelsalam A.M., 2018, 2018 International Conference on ReConFigurable Computing and FPGAs (ReConFig), P1, DOI [10.1109/MOCAST.2018.8376632, 10.1109/reconfig.2018.8641735, DOI 10.1109/CDE.2018.8597131]
  • [2] Apu M.R.H., 2021, 2021 JOINT 10 INT C, P1, DOI 10.1109/ICIEVicIVPR52578.2021.9564201
  • [3] Hardware Implementation of Deep Network Accelerators Towards Healthcare and Biomedical Applications
    Azghadi, Mostafa Rahimi
    Lammie, Corey
    Eshraghian, Jason K.
    Payvand, Melika
    Donati, Elisa
    Linares-Barranco, Bernabe
    Indiveri, Giacomo
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS, 2020, 14 (06) : 1138 - 1159
  • [4] Low-Power ECG-Based Processor for Predicting Ventricular Arrhythmia
    Bayasi, Nourhan
    Tekeste, Temesghen
    Saleh, Hani
    Mohammad, Baker
    Khandoker, Ahsan
    Ismail, Mohammed
    [J]. IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2016, 24 (05) : 1962 - 1974
  • [5] Cao YX, 2020, PROCEEDINGS OF 2020 IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND INFORMATION SYSTEMS (ICAIIS), P66, DOI [10.1109/ICAIIS49377.2020.9194894, 10.1109/icaiis49377.2020.9194894]
  • [6] Temporal abstraction and inductive logic programming for arrhythmia recogniton from electrocardiograms
    Carrault, G
    Cordier, MO
    Quiniou, R
    Wang, F
    [J]. ARTIFICIAL INTELLIGENCE IN MEDICINE, 2003, 28 (03) : 231 - 263
  • [7] Accurate iris segmentation and recognition using an end-to-end unified framework based on MADNet and DSANet
    Chen, Ying
    Gan, Huimin
    Chen, Huiling
    Zeng, Yugang
    Xu, Liang
    Heidari, Ali Asghar
    Zhu, Xiaodong
    Liu, Yuanning
    [J]. NEUROCOMPUTING, 2023, 517 : 264 - 278
  • [8] Generative Adversarial Networks in Medical Image augmentation: A review
    Chen, Yizhou
    Yang, Xu-Hua
    Wei, Zihan
    Heidari, Ali Asghar
    Zheng, Nenggan
    Li, Zhicheng
    Chen, Huiling
    Hu, Haigen
    Zhou, Qianwei
    Guan, Qiu
    [J]. COMPUTERS IN BIOLOGY AND MEDICINE, 2022, 144
  • [9] Home Monitoring for Fetal Heart Rhythm During Anti-Ro Pregnancies
    Cuneo, Bettina F.
    Sonesson, Sven-Erik
    Levasseur, Stephanie
    Moon-Grady, Anita J.
    Krishnan, Anita
    Donofrio, Mary T.
    Raboisson, Marie-Josee
    Hornberger, Lisa K.
    Van Eerden, Peter
    Sinkovskaya, Elena
    Abuhamad, Alfred
    Arya, Bhawna
    Szwast, Anita
    Gardiner, Helena
    Jacobs, Katherine
    Freire, Grace
    Howley, Lisa
    Lam, Aimee
    Kaizer, Alexander M.
    Benson, D. Woodrow
    Jaeggi, Edgar
    [J]. JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY, 2018, 72 (16) : 1940 - 1951
  • [10] Participation in Cardiac Rehabilitation, Readmissions, and Death After Acute Myocardial Infarction
    Dunlay, Shannon M.
    Pack, Quinn R.
    Thomas, Randal J.
    Killian, Jill M.
    Roger, Veronique L.
    [J]. AMERICAN JOURNAL OF MEDICINE, 2014, 127 (06) : 538 - 546