[1]纪洁维,常胜,王豪,等.基于自适应位置编码的心电图重构算法[J].中国医学物理学杂志,2023,40(10):1285-1290.[doi:DOI:10.3969/j.issn.1005-202X.2023.10.016]
　JI Jiewei,CHANG Sheng,WANG Hao,et al.Adaptive position encoding for ECG reconstruction[J].Chinese Journal of Medical Physics,2023,40(10):1285-1290.[doi:DOI:10.3969/j.issn.1005-202X.2023.10.016]
点击复制

基于自适应位置编码的心电图重构算法()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
40卷
期数:
2023年第10期
页码:
1285-1290
栏目:
医学信号处理与医学仪器
出版日期:
2023-10-27

文章信息/Info

Title:
Adaptive position encoding for ECG reconstruction
文章编号:
1005-202X（2023）10-1285-06
作者:
纪洁维; 常胜; 王豪; 黄启俊
武汉大学物理科学与技术学院， 湖北 武汉 430072
Author(s):
JI Jiewei;  CHANG Sheng;  WANG Hao;  HUANG Qijun
School of Physics and Technology, Wuhan University, Wuhan 430072, China
关键词:
心电图; 重构; 位置编码; Transformer Encoder
Keywords:
electrocardiogram reconstruction position encoding Transformer Encoder
分类号:
R318
DOI:
DOI:10.3969/j.issn.1005-202X.2023.10.016
文献标志码:
A
摘要:
可穿戴心电检测的主要挑战是较多导联影响被测者的身体活动，如果减少导联会使心电数据信息减少使检测效果变差。为了平衡被测者日常穿戴舒适性和检测准确性，笔者设计了一个基于Transformer Encoder的自适应相对位置编码重构算法，通过前后重叠的切片方式使相邻片段的信息具备关联性，相对位置编码时加入可训练参数对任意片段进行重构，从而有效地提取位置信息。用3个导联的EGG信号重构标准12导联EGG信号，实验结果表明，重构的ECG数据均方根误差低至0.027 58，平均相关系数高达98.43%，显示出本文算法在应用于可穿戴心电检测设备的应用前景。
Abstract:
The main challenge in wearable electrocardiogram (ECG) detection is that multiple leads for detection affects the subjects physical activity, but reducing leads will weaken detection performance due to the loss of ECG data. An adaptive position encoding based reconstruction algorithm using Transformer Encoder is proposed to balance wearing comfort and detection accuracy. The information of adjacent slices is correlated through slice overlapping. When encoding relative positions, trainable parameters are added to reconstruct any slice for effectively extracting position information. The standard 12-lead ECG signal is reconstructed from 3-lead ECG signals, and the experimental results show that the root mean square error and average correlation coefficient of the reconstructed ECG data are 0.027 58 and 98.43%, indicating that the proposed algorithm has high application prospect in wearable ECG monitoring equipment.

相似文献/References:

[1]白鹏飞,王利,易子川,等.一种心电图P波提取算法[J].中国医学物理学杂志,2013,30(02):4032.[doi:10.3969/j.issn.1005-202X.2013.02.017]
[2]武会江,黄启俊,常胜,等.基于多项式参数拟合和支持向量机的心肌梗死识别算法[J].中国医学物理学杂志,2017,34(7):736.[doi:10.3969/j.issn.1005-202X.2017.07.017]
　[J].Chinese Journal of Medical Physics,2017,34(10):736.[doi:10.3969/j.issn.1005-202X.2017.07.017]
[3]王凯,杨枢. 基于自适应学习的心律失常心拍分类方法[J].中国医学物理学杂志,2019,36(1):92.[doi:DOI:10.3969/j.issn.1005-202X.2019.01.018]
　WANG Kai,YANG Shu. Adaptive learning-based method for classification of arrhythmic heartbeats[J].Chinese Journal of Medical Physics,2019,36(10):92.[doi:DOI:10.3969/j.issn.1005-202X.2019.01.018]
[4]梁伟玲,吴超,林建斌,等. 基于Arduino的无线心电信号采集系统设计与实现[J].中国医学物理学杂志,2019,36(6):715.[doi:DOI:10.3969/j.issn.1005-202X.2019.06.019]
　LIANG Weiling,WU Chao,LIN Jianbin,et al. Design and implementation of wireless ECG signal acquisition system based on Arduino[J].Chinese Journal of Medical Physics,2019,36(10):715.[doi:DOI:10.3969/j.issn.1005-202X.2019.06.019]
[5]王凯,杨枢,李超. 一种基于ECG的多层共轭对称Hadamard特征变换的房颤异常信号分类方法[J].中国医学物理学杂志,2019,36(9):1068.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.014]
　WANG Kai,YANG Shu,LI Chao. ECG-based multi-level conjugate symmetric Hadamard feature transformation for classification of abnormal signals of atrial fibrillation[J].Chinese Journal of Medical Physics,2019,36(10):1068.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.014]
[6]蔚文婧,王寻,张鹏远,等.一种基于多层感知器的房颤心电图检测方法[J].中国医学物理学杂志,2020,37(3):332.[doi:DOI:10.3969/j.issn.1005-202X.2020.03.015]
　WEI Wenjing,WANG Xun,ZHANG Pengyuan,et al.Multilayer perceptron-based method for atrial fibrillation ECG detection[J].Chinese Journal of Medical Physics,2020,37(10):332.[doi:DOI:10.3969/j.issn.1005-202X.2020.03.015]
[7]文翠,赵新军,张震洪,等.冠心病患者心电图ST段改变与多排螺旋CT冠状动脉成像的关系分析[J].中国医学物理学杂志,2020,37(8):1035.[doi:DOI:10.3969/j.issn.1005-202X.2020.08.018]
　WEN Cui,ZHAO Xinjun,ZHANG Zhenhong,et al.Relationships between ECG ST-segment changes and multi-slice spiral CT coronary angiography in patients with coronary heart disease[J].Chinese Journal of Medical Physics,2020,37(10):1035.[doi:DOI:10.3969/j.issn.1005-202X.2020.08.018]
[8]胡丹琴,蔡文杰.QRS复合波检测技术综述[J].中国医学物理学杂志,2020,37(9):1208.[doi:10.3969/j.issn.1005-202X.2020.09.024]
　HU Danqin,CAI Wenjie.Review on technologies for QRS complex detection[J].Chinese Journal of Medical Physics,2020,37(10):1208.[doi:10.3969/j.issn.1005-202X.2020.09.024]
[9]林卓琛,张晋昕.基于非参数相关系数的心肌病自动诊断[J].中国医学物理学杂志,2021,38(1):80.[doi:10.3969/j.issn.1005-202X.2021.01.014]
　LIN Zhuochen,ZHANG Jinxin.Automatic diagnosis of cardiomyopathy based on nonparametric correlation coefficient[J].Chinese Journal of Medical Physics,2021,38(10):80.[doi:10.3969/j.issn.1005-202X.2021.01.014]
[10]王新峰,漆梦玲,徐洪智.基于心电图的心肌梗死识别分类研究[J].中国医学物理学杂志,2022,39(8):992.[doi:DOI:10.3969/j.issn.1005-202X.2022.08.013]
　WANG Xinfeng,QI Mengling,et al.ECG-based identification and classification of myocardial infarction[J].Chinese Journal of Medical Physics,2022,39(10):992.[doi:DOI:10.3969/j.issn.1005-202X.2022.08.013]

备注/Memo

备注/Memo:
【收稿日期】2023-05-16 【基金项目】国家自然科学基金（81971702，61874079，61774113） 【作者简介】纪洁维，硕士，研究方向：基于深度学习的ECG信号重构， E-mail: 1589544756@qq.com 【通信作者】黄启俊，教授，研究方向：医学信号处理及微电子系统设计，E-mail: huangqj@whu.edu.cn
更新日期/Last Update: 2023-10-27