Research and Application of Artifact Identification Method for Wearable ECG Devices

被引：0
|
作者：
Shangguan W. [1 ,2 ]
Li Y. [2 ]
Wu M. [1 ]
机构：
[1] School of Software Engineering, University of Science and Technology of China, Hefei
[2] Institute of Biomedical and Health Engineering, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen
来源：
Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology | 2021年 / 41卷 / 06期
关键词：
ECG artifact; Messy degree; Mutation point; Wearable ECG acquisition;
D O I：
10.15918/j.tbit1001-0645.2020.083
中图分类号：
学科分类号：
摘要：
The electrocardiogram(ECG)signals from wearable ECG monitoring equipment usually contain movement and device artifact. In this paper, a combined artifact recognition algorithm was developed based on the mutation degree of ECG amplitude and the connectivity of mutation distribution, the disorder degree of transformed ECG maximum and minimum values, and abnormal cardiac beat characteristics, etc. Embedding three key links in ECG automatic analysis, the combined artifact recognition algorithm was carried out, and selecting four kinds of data samples from three kinds of equipment, the algorithm was verified. Test results show that the combined artifact recognition algorithm can provide an artifact recognition sensitivity up to 98. 35%, and improve QRS detection accuracy by 3. 08%, at the same time, make the ECG automatic analysis operation time no increase and no rely on specific hardware equipment. The combined artifact recognition algorithm can be applied to ECG data analysis of various wearable devices universally and efficiently. © 2021, Editorial Department of Transaction of Beijing Institute of Technology. All right reserved.
引用
收藏
页码：665 / 670
页数：5
相关论文
共 11 条
  • [1] TENG Xiaofei, ZHANG Yuanting, M-Health: trends in wearable medical devices, Chinese Journal of Medical Instrumentation, 30, 5, pp. 330-340, (2006)
  • [2] ABUKHOUSA E, MOHAMED N, ALJAROODI J., E-Health cloud: opportunities and challenges, Future Internet, 4, 4, pp. 621-645, (2012)
  • [3] SHUBHANKAR S, ROHAN J, MALAYA K H., Removal of powerline interference from ECG signal using FIR, IIT, DWT and NLMS adaptive filter, International Conference on Communication and Signal Processing, pp. 12-16, (2019)
  • [4] KALEEM A M, KOKATE R D., An efficient adaptive filter for fetal ECG extraction using neural network, Journal of Intelligent Systems, 28, 4, pp. 31-35, (2019)
  • [5] FAN Xiaomao, YAO Qihang, CAI Yunpeng, Et al., Multiscaled fusion of deep convolutional neural networks for screening atrial fibrillation from single lead short ECG recordings, IEEE Journal of Biomedical and Health Informatics, 22, 6, pp. 1744-1753, (2018)
  • [6] TIAN Xuelong, WANG Tianxing, ZHU Binglian, Et al., Exercise ECG signal denoising using unbiased risk estimate and wavelet transform, Journal of Biomedical Engineering, 22, 1, pp. 137-142, (2005)
  • [7] BIAN Yuping, YANG Hao, HE Wei, Et al., A method based on least square algorithm for discriminating artifacts in dynamic electrocardiogram signals, Journal of Biomedical Engineering, 24, 5, pp. 1031-1035, (2007)
  • [8] TU Yuewen, CHEN Hang, FU Xiuquan, Et al., Beats clustering based algorithm for fast recognition of motion artifact sections in Holter system, Journal of Zhejiang University(Engineering Science Ed.), 46, 6, pp. 1031-1035, (2012)
  • [9] FAN Xiaomao, HE Chenguang, LI Ye, Application of cloud platform in preventive healthcare, Information and Communications Technologies, 5, pp. 31-36, (2013)
  • [10] CHEN Yongli, DUAN Huilong, A QRS complex detection algorithm based on mathematical morphology and envelope, Proceedings of the 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, pp. 4654-4657, (2005)
12