[1]张培玲,裴前勇.改进轻量化残差网络的心律失常分类方法[J].中国医学物理学杂志,2023,40(12):1531-1539.[doi:DOI:10.3969/j.issn.1005-202X.2023.12.012]
　ZHANG Peiling,PEI Qianyong.Arrhythmia classification method using modified lightweight residual network[J].Chinese Journal of Medical Physics,2023,40(12):1531-1539.[doi:DOI:10.3969/j.issn.1005-202X.2023.12.012]
点击复制

改进轻量化残差网络的心律失常分类方法()
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12期
页码:
1531-1539
栏目:
医学信号处理与医学仪器
出版日期:
2023-12-27

文章信息/Info

Title:
Arrhythmia classification method using modified lightweight residual network
文章编号:
1005-202X（2023）12-1531-09
作者:
张培玲; 裴前勇
河南理工大学物理与电子信息学院， 河南 焦作 454003
Author(s):
ZHANG Peiling;  PEI Qianyong
School of Physics and Electronic Information Engineering, Henan Polytechnic University, Jiaozuo 454003, China
关键词:
轻量化; 心律失常; ResNet34; ShuffleNet V2
Keywords:
Keywords: lightweight arrhythmia ResNet34 ShuffleNet V2
分类号:
R318；R541.7
DOI:
DOI:10.3969/j.issn.1005-202X.2023.12.012
文献标志码:
A
摘要:
在保证系统准确率的前提下，轻量化分类模型以便于其在硬件资源有限的嵌入式设备或移动终端上部署，提出基于改进轻量化残差网络的心律失常分类方法。该方法首先将一维心电信号通过格拉姆角和场转换成二维图像作为模型输入，接着使用ShuffleNet V2卷积单元替换ResNet34基本残差块中传统卷积，降低模型参数量，并结合高效通道注意力模块使模型专注于重要特征区域，提升模型的准确率，最终实现心律失常自动分类。基于MIT-BIH心律失常数据库的实验结果表明，所提方法的准确率达到99.78%，与传统ResNet34模型相比，Params减少95%，FLOPs和MAdd均降低91%，表明该方法具有轻量化、高准确率的特点，为其在后续的移动端部署提供可能。
Abstract:
On the premise of ensuring system accuracy, lightweight models can be deployed on embedded devices or mobile terminals with limited hardware resources. Therefore, a method using modified lightweight residual network is proposed for arrhythmia classification. The method transforms one-dimensional electrocardiogram data into Gramian angular summation field maps which are then taken as the model input, and reduces the number of model parameters by substituting ShuffleNet V2 convolutional units for the traditional convolution inside the ResNet34 basic residual blocks. In addition, the network incorporating efficient channel attention module makes the model focus on important feature regions, thereby improving model accuracy and realizing the automatic arrhythmia classification. The proposed model has an accuracy of 99.78% on MIT-BIH arrhythmia database, and it reduces the number of parameters, FLOPs and MAdd by 95%, 91% and 91%, as compared with the traditional ResNet34 model, demonstrating its characteristics of lightweight and high accuracy, and proving the possibility of deployment on mobile devices.

相似文献/References:

[1]陆宏伟,钟高艳,龙芋帆,等. 全数据库评估概率密度函数法利用R-R间期检测房颤精度[J].中国医学物理学杂志,2018,35(3):333.[doi:DOI:10.3969/j.issn.1005-202X.2018.03.016]
　LU Hongwei,ZHONG Gaoyan,LONG Yufan,et al. Evaluation of the precision of probability density function method using R-R intervals for detecting atrial fibrillation from the whole MIT-BIH arrhythmia database[J].Chinese Journal of Medical Physics,2018,35(12):333.[doi:DOI:10.3969/j.issn.1005-202X.2018.03.016]
[2]王自强,刘洪运,石金龙,等.基于卷积神经网络的心电图心博识别[J].中国医学物理学杂志,2019,36(8):938.[doi:DOI:10.3969/j.issn.1005-202X.2019.08.015]
　WANG Ziqiang,LIU Hongyun,SHI Jinlong,et al.ECG heartbeat recognition based on convolution neural network[J].Chinese Journal of Medical Physics,2019,36(12):938.[doi:DOI:10.3969/j.issn.1005-202X.2019.08.015]
[3]李亮,钟元利,阮红,等.动态与常规心电图诊断冠心病心肌缺血、心律失常、心绞痛的比较分析[J].中国医学物理学杂志,2021,38(8):946.[doi:DOI:10.3969/j.issn.1005-202X.2021.08.005]
　LI Liang,ZHONG Yuanli,RUAN Hong,et al.Comparison of dynamic and routine electrocardiograms for diagnosing myocardial ischemia, arrhythmia and angina pectoris of coronary heart disease[J].Chinese Journal of Medical Physics,2021,38(12):946.[doi:DOI:10.3969/j.issn.1005-202X.2021.08.005]
[4]冀常鹏,邓伟,代巍.基于马尔可夫转移场与改进MobileNetV2的心律失常分类方法[J].中国医学物理学杂志,2023,40(11):1395.[doi:DOI:10.3969/j.issn.1005-202X.2023.11.013]
　JI Changpeng,DENG Wei,DAI Wei.Markov transfer field combined with modified MobileNetV2 for arrhythmia classification[J].Chinese Journal of Medical Physics,2023,40(12):1395.[doi:DOI:10.3969/j.issn.1005-202X.2023.11.013]

备注/Memo

备注/Memo:
【收稿日期】2023-05-19 【基金项目】国家自然科学基金（41904078） 【作者简介】张培玲，博士，副教授，研究方向：通信技术和信号处理，E-mail: plzhang@hpu.edu.cn
更新日期/Last Update: 2023-12-27