High Noise Tolerant R-Peak Detection Method Based on Deep Convolution Neural Network

Menghan JIA; Feiteng LI; Zhijian CHEN; Xiaoyan XIANG; Xiaolang YAN

doi:10.1587/transinf.2019EDL8097

High Noise Tolerant R-Peak Detection Method Based on Deep Convolution Neural Network

Menghan JIA, Feiteng LI, Zhijian CHEN, Xiaoyan XIANG, Xiaolang YAN

Full Text Views

0

Cite this

Summary :

An R-peak detection method with a high noise tolerance is presented in this paper. This method utilizes a customized deep convolution neural network (DCNN) to extract morphological and temporal features from sliced electrocardiogram (ECG) signals. The proposed network adopts multiple parallel dilated convolution layers to analyze features from diverse fields of view. A sliding window slices the original ECG signals into segments, and then the network calculates one segment at a time and outputs every point's probability of belonging to the R-peak regions. After a binarization and a deburring operation, the occurrence time of the R-peaks can be located. Experimental results based on the MIT-BIH database show that the R-peak detection accuracies can be significantly improved under high intensity of the electrode motion artifact or muscle artifact noise, which reveals a higher performance than state-of-the-art methods.

Publication: IEICE TRANSACTIONS on Information Vol.E102-D No.11 pp.2272-2275

Publication Date: 2019/11/01

Publicized: 2019/08/02

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2019EDL8097

Type of Manuscript: LETTER

Category: Biological Engineering

Authors

Menghan JIA
  Zhejiang University
Feiteng LI
  Zhejiang University
Zhijian CHEN
  Zhejiang University
Xiaoyan XIANG
  Fudan University
Xiaolang YAN
  Zhejiang University

Keyword

electrocardiograph, noise tolerance, convolution neural network, dilated convolution

Cite this

Copy

Menghan JIA, Feiteng LI, Zhijian CHEN, Xiaoyan XIANG, Xiaolang YAN, "High Noise Tolerant R-Peak Detection Method Based on Deep Convolution Neural Network" in IEICE TRANSACTIONS on Information, vol. E102-D, no. 11, pp. 2272-2275, November 2019, doi: 10.1587/transinf.2019EDL8097.
Abstract: An R-peak detection method with a high noise tolerance is presented in this paper. This method utilizes a customized deep convolution neural network (DCNN) to extract morphological and temporal features from sliced electrocardiogram (ECG) signals. The proposed network adopts multiple parallel dilated convolution layers to analyze features from diverse fields of view. A sliding window slices the original ECG signals into segments, and then the network calculates one segment at a time and outputs every point's probability of belonging to the R-peak regions. After a binarization and a deburring operation, the occurrence time of the R-peaks can be located. Experimental results based on the MIT-BIH database show that the R-peak detection accuracies can be significantly improved under high intensity of the electrode motion artifact or muscle artifact noise, which reveals a higher performance than state-of-the-art methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8097/_p

Copy

@ARTICLE{e102-d_11_2272,
author={Menghan JIA, Feiteng LI, Zhijian CHEN, Xiaoyan XIANG, Xiaolang YAN, },
journal={IEICE TRANSACTIONS on Information},
title={High Noise Tolerant R-Peak Detection Method Based on Deep Convolution Neural Network},
year={2019},
volume={E102-D},
number={11},
pages={2272-2275},
abstract={An R-peak detection method with a high noise tolerance is presented in this paper. This method utilizes a customized deep convolution neural network (DCNN) to extract morphological and temporal features from sliced electrocardiogram (ECG) signals. The proposed network adopts multiple parallel dilated convolution layers to analyze features from diverse fields of view. A sliding window slices the original ECG signals into segments, and then the network calculates one segment at a time and outputs every point's probability of belonging to the R-peak regions. After a binarization and a deburring operation, the occurrence time of the R-peaks can be located. Experimental results based on the MIT-BIH database show that the R-peak detection accuracies can be significantly improved under high intensity of the electrode motion artifact or muscle artifact noise, which reveals a higher performance than state-of-the-art methods.},
keywords={},
doi={10.1587/transinf.2019EDL8097},
ISSN={1745-1361},
month={November},}

Copy

TY - JOUR
TI - High Noise Tolerant R-Peak Detection Method Based on Deep Convolution Neural Network
T2 - IEICE TRANSACTIONS on Information
SP - 2272
EP - 2275
AU - Menghan JIA
AU - Feiteng LI
AU - Zhijian CHEN
AU - Xiaoyan XIANG
AU - Xiaolang YAN
PY - 2019
DO - 10.1587/transinf.2019EDL8097
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2019
AB - An R-peak detection method with a high noise tolerance is presented in this paper. This method utilizes a customized deep convolution neural network (DCNN) to extract morphological and temporal features from sliced electrocardiogram (ECG) signals. The proposed network adopts multiple parallel dilated convolution layers to analyze features from diverse fields of view. A sliding window slices the original ECG signals into segments, and then the network calculates one segment at a time and outputs every point's probability of belonging to the R-peak regions. After a binarization and a deburring operation, the occurrence time of the R-peaks can be located. Experimental results based on the MIT-BIH database show that the R-peak detection accuracies can be significantly improved under high intensity of the electrode motion artifact or muscle artifact noise, which reveals a higher performance than state-of-the-art methods.
ER -