基于自动机器学习的运动过程心电检测算法

宋群; 袁青霞; 王俊江

doi:10.16152/j.cnki.xdxbzr.2023-05-009

您当前的位置：

首页 >

文章列表页 >

基于自动机器学习的运动过程心电检测算法

人工智能交叉应用 | 更新时间：2023-10-30

- 基于自动机器学习的运动过程心电检测算法
- Automated machine learning-based algorithm for ECG monitoring during exercise
- 西北大学学报（自然科学版） 2023年53卷第5期页码：771-781
- 作者机构：
  
  1.西北工业大学　自动化学院，陕西　西安　710072
  2.中科锐眼(天津)科技有限公司，天津　300350
  3.天津城建大学　体育部，天津　300384
- 作者简介：
  
  宋群，男，博士，副研究员，从事模式识别研究，songqun@nwpu.edu.cn。
  王俊江，男，副教授，从事运动科学和运动健康等研究，Feim1126@126.com。
- 基金信息：
  
  国家自然科学基金(62006192)
- DOI：10.16152/j.cnki.xdxbzr.2023-05-009
  中图分类号：
扫描看全文
宋群, 袁青霞, 王俊江. 基于自动机器学习的运动过程心电检测算法[J]. 西北大学学报（自然科学版）, 2023,53(5):771-781.

SONG Qun, YUAN Qingxia, WANG Junjiang. Automated machine learning-based algorithm for ECG monitoring during exercise[J]. Journal of Northwest University (Natural Science Edition), 2023,53(5):771-781.
宋群, 袁青霞, 王俊江. 基于自动机器学习的运动过程心电检测算法[J]. 西北大学学报（自然科学版）, 2023,53(5):771-781. DOI： 10.16152/j.cnki.xdxbzr.2023-05-009.

SONG Qun, YUAN Qingxia, WANG Junjiang. Automated machine learning-based algorithm for ECG monitoring during exercise[J]. Journal of Northwest University (Natural Science Edition), 2023,53(5):771-781. DOI： 10.16152/j.cnki.xdxbzr.2023-05-009.

摘要

心电图(ECG)是一种常规的身体监测手段，通过分析人体在不同状态下心电活动的变化，评估其心血管健康状况。考虑到人体生理特征的差异，以及不同状态下心电活动规律的变化，如何设计一种自动适应各种场景的心电信号分类模型具有重要的现实意义。该文创新性地将心电信号转化为图像数据，并采用可微分神经网络架构搜索算法(PC-DARTS)对不同分布的心电检测数据自动搭建最优神经网络模型，实现了不同场景下心电信号的精准分类。分别在心律失常数据集PhysioNet MIT-BIH和诊断性心电图数据集PTB上进行心电信号分类实验，以验证所提方法在不同应用场景下的辨识性能。实验结果表明，与其他方法相比，该文算法具备更高的准确度和更强的鲁棒性，同时，能够应对不同采集设备、实验环境以及被试人群所带来的分类辨识挑战，具备较强的泛化性能。未来，该研究成果有望与新型心电监测设备相结合，实现高效精准的心电检测功能，加速心电检测在更多领域中的落地与应用。

Abstract

Electrocardiogram (ECG) is a commonly used method for monitoring the body. The analysis of alterations in electrocardiographic activity during physical exercise can evaluate an individual’s cardiovascular health status. Designing an automatic adaptive ECG signal classification model that can accommodate different physiological characteristics and changes in ECG activity patterns in different states is of great practical significance. In this study, we proposed an innovative approach that transformed ECG signals into image data and automatically constructed optimal neural network models for different distributions of ECG detection data using the differentiable neural architecture search algorithm (PC-DARTS). This approach achieved accurate ECG signal classification in various scenarios. In this paper, ECG signal classification experiments were conducted on the PhysioNet MIT-BIH arrhythmia dataset and the PTB diagnostic ECG dataset, respectively, to verify the discrimination performance of the proposed method in different application scenarios. The results indicate that the algorithm proposed in this paper has higher accuracy and greater robustness compared to other methods. At the same time, the proposed method is able to cope with the classification challenges posed by different acquisition devices, different experimental environments and different subject populations, and has sufficient generalization performance. In the future, the research results are expected to be combined with new ECG monitoring devices to achieve efficient and accurate ECG detection and accelerate the application of ECG detection in more fields.

关键词

心电检测运动健康神经网络自动机器学习神经架构搜索

Keywords

electrocardiogramsports healthneural networksautomated machine learningneural architecture search

references

郭航远. 我国心脏康复的困境与对策[J]. 中国全科医学, 2019, 22(12): 1381-1384.

GUO H Y. Difficulties and countermeasures of cardiac rehabilitation in China[J]. Chinese General Practice, 2019, 22(12): 1381-1384.

张和君, 张跃, 周炳坤. 远程心电监护软件系统的设计与实现[J]. 计算机工程与应用, 2006, 42(15): 219-224.

ZHANG H J, ZHANG Y, ZHOU B K. Design and implementation of software system for remote electrocardiogr aphic monitoring[J]. Computer Engineering and Applications, 2006, 42(15): 219-224.

雷靳灿, 廖彦剑, 郑小林, 等. 模块式多功能运动心电检测系统的设计[J]. 仪器仪表学报, 2010, 31(7): 1484-1489.

LEI J C, LIAO Y J, ZHENG X L, et al. Design of modular and multi-function exercise ECG diagnosis system[J]. Chinese Journal of Scientific Instrument, 2010, 31(7): 1484-1489.

高锦炜. 面向离散小波变换的处理器低功耗技术研究[D]. 杭州: 浙江大学, 2015.

杨宇, 司玉娟, 宋晓洋. 基于小波变换和支持向量机的心电信号ST段分类[J]. 吉林大学学报(信息科学版), 2016, 34(3): 315-319.

YANG Y, SI Y J, SONG X Y. ST segment classification of ECG signals based on wavelet transform and support vector machine[J]. Journal of Jilin University (Information Science Edition), 2016, 34(3): 315-319.

PARK J S, LEE S W, PARK U. R peak detection method using wavelet transform and modified Shannon energy envelope[J]. Journal of Healthcare Engineering, 2017, 2017: 1-4.

朱俊江, 张远辉. 面向心电信号去噪的正交小波构造方法[J]. 中国生物医学工程学报, 2017, 36(1): 109-113.

ZHU J J, ZHANG Y H. Construction of orthogonal wavelet for ECG signal processing[J]. Chinese Journal of Biomedical Engineering, 2017, 36(1): 109-113.

王凤. 心电数据的预处理与分类算法研究[D]. 太原: 中北大学, 2018.

马金伟. 基于深度学习的心电信号识别分类算法研究[D]. 重庆: 重庆理工大学, 2019.

PRAKASH A J, ARI S. AAMI standard cardiac arrhythmia detection with random forest using mixed features[C]//2019 IEEE 16th India Council International Conference (INDICON). Rajkot: IEEE, 2020: 1-4.

孟琭, 葛康, 宋阳, 等. TSCNN：面向可穿戴心电信号监测与分析的卷积神经网络[J]. 中国图象图形学报, 2020, 25(10): 2281-2292.

MENG L, GE K, SONG Y, et al. TSCNN: A convolutional neural network for the monitoring and analysis of the electrical signals of the heart from wearable devices[J]. Journal of Image and Graphics, 2020, 25(10): 2281-2292.

吴佳全. 基于神经网络的ECG分类算法及高能效架构研究[D]. 杭州: 浙江大学, 2020.

孟瑶. 基于可穿戴传感器的实时心电检测方法研究[J]. 信息技术与网络安全, 2021, 40(4): 75-79.

MENG Y. Study of real-time electrocardiogram detection based on wearable sensors[J]. Cyber Security and Data Governance, 2021, 40(4): 75-79.

汪成亮, 宋军, 胡炳权, 等. 智能神经网络在时序信号预测上的应用[J]. 重庆大学学报(自然科学版), 2003, 26(1): 34-37.

WANG C L, SONG J, HU B Q, et al. Application of intelligent neural network on prediction of time series signal[J]. Journal of Chongqing University, 2003, 26(1): 34-37.

LIU H X, SIMONYAN K, YANG Y M. DARTS: Differentiable architecture search[EB/OL]. (2019-04-23)[2023-03-25]. https://arxiv.org/abs/1806.09055https://arxiv.org/abs/1806.09055.

PHAM H, GUAN M Y, ZOPH B, et al. Efficient neural architecture search via parameters sharing[EB/OL]. (2018-02-12)[2023-03-25]. https://arxiv.org/abs/1802.03268https://arxiv.org/abs/1802.03268.

CHEN X, XIE L X, WU J, et al. Progressive differentiable architecture search: Bridging the depth gap between search and evaluation[C]//2019 IEEE/CVF International Conference on Computer Vision(ICCV). Seoul: IEEE, 2020: 1294-1303.

CAI H, ZHU L G, HAN S. ProxylessNAS: Direct neural architecture search on target task and hardware[EB/OL]. (2019-02-23)[2023-03-25]. https://arxiv.org/abs/1812.00332https://arxiv.org/abs/1812.00332.

BROCK A, LIM T, RITCHIE J M, et al. SMASH: One-shot model architecture search through HyperNetworks[EB/OL]. (2017-08-17)[2023-03-25]. https://arxiv.org/abs/1708.05344https://arxiv.org/abs/1708.05344.

SHEN B L, XIAO A Q, TIAN J, et al. PP-NAS: Searching for plug-and-play blocks on convolutional neural network[C]//2021 IEEE/CVF International Conference on Computer Vision Workshops(ICCVW). Montreal: IEEE, 2021: 365-372.

WU B C, DAI X L, ZHANG P Z, et al. FBNet: Hardware-aware efficient ConvNet design via differentiable neural architecture search[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Long Beach: IEEE, 2020: 10734-10742.

LIU H X, SIMONYAN K, VINYALS O, et al. Hierarchical representations for efficient architecture search[EB/OL]. (2018-08-22)[2023-03-25]. https://arxiv.org/abs/1711.00436https://arxiv.org/abs/1711.00436.

HUANG S Y, CHU W T. Ponas: Progressive one-shot neural architecture search for very efficient deployment[C]//2021 International Joint Conference on Neural Networks (IJCNN). Shenzhen: IEEE, 2021: 1-9.

TAN M X, PANG R M, LE Q V. EfficientDet: Scalable and efficient object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Seattle: IEEE, 2020: 10778-10787.

WANG Z G, OATES T. Encoding time series as images for visual inspection and classification using tiled convolutional neural networks[C]//Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence.Austin: AAAI, 2015: 40-46.

ECKMANN J P, KAMPHORST S O, RUELLE D. Recurrence plots of dynamical systems[J]. Europhysics Letters(EPL), 1987, 4(9): 973-977.

XU Y H, XIE L X, ZHANG X P, et al. PC-DARTS: Partial channel connections for memory-efficient architecture search[EB/OL]. (2020-04-07)[2023-03-25]. https://arxiv.org/abs/1907.05737https://arxiv.org/abs/1907.05737.

SHAYAN F. ECG heartbeat categorization dataset[DB/OL]. (2018-05-31)[2023-03-05]. https://www.kaggle.com/shayanfazeli/heartbeathttps://www.kaggle.com/shayanfazeli/heartbeat.

GOLDBERGER A L, AMARAL L A, GLASS L, et al. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals[J]. Circulation, 2000, 101(23): E215-E220.

AAMI.Testing and reporting performance results of cardiac rhythm and ST segment measurement algorithms: AAMI EC57[S]. Arlington: AAMI, 2012.

CHAWLA N V, BOWYER K W, HALL L O, et al. SMOTE: Synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2002, 16: 321-357.

BOUSSELJOT R, KREISELER D, SCHNABEL A. Nutzung der EKG-signaldatenbank CARDIODAT der PTB über das internet[J]. Biomedizinische Technik, 1995, 40(s1): 317-318.

KACHUEE M, FAZELI S, SARRAFZADEH M. ECG heartbeat classification: A deep transferable representation[C]//2018 IEEE International Conference on Healthcare Informatics (ICHI). New York: IEEE; 2018: 443-444.

ACHARYA U R, OH S L, HAGIWARA Y, et al. A deep convolutional neural network model to classify heartbeats[J]. Computers in Biology and Medicine, 2017, 89: 389-396.

MARTIS R J, ACHARYA U R, LIM C M, et al. Application of higher order cumulant features for cardiac health diagnosis using ECG signals[J]. International Journal of Neural Systems, 2013, 23(4): 1350014.

LI T Y, ZHOU M. ECG classification using wavelet packet entropy and random forests[J]. Entropy, 2016, 18(8): 285.

GANGULY B, GHOSAL A, DAS A, et al. Automated detection and classification of arrhythmia from ECG signals using feature-induced long short-term memory network[J]. IEEE Sensors Letters, 2020, 4(8): 1-4.

PHAM B T, LE P T, TAI T C, et al. Electrocardiogram heartbeat classification for arrhythmias and myocardial Infarction[J]. Sensors, 2023, 23(6): 2993.

SAFDARIAN N, DABANLOO N J, AtTARODI G. A new pattern recognition method for detection and localization of myocardial infarction using T-wave integral and total integral as extracted features from one cycle of ECG signal[J]. Journal of Biomedical Science and Engineering, 2014, 7(10): 818-824.

KOJURI J, BOOStANI R, DEHgHANI P, et al. Prediction of acute myocardial infarction with artificial neural networks in patients with nondiagnostic electrocardiogram[J]. Journal of Cardiovascular Disease Research, 2015, 6(2): 51-59.

LIU B, LIU J, WANG G Q, et al. A novel electrocardiogram parameterization algorithm and its application in myocardial infarction detection[J]. Computers in Biology and Medicine, 2015, 61: 178-184.

SHARMA L N, TRIPATHY R K, DANDAPAT S. Multiscale energy and eigenspace approach to detection and localization of myocardial infarction[J]. IEEE Transactions on Biomedical Engineering, 2015, 62(7): 1827-1837.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据