全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于双分支时频融合的心冲击信号心率估计网络
Heart Rate Estimation Network for Ballistocardiogram Signals Based on Dual-Branch Time-Frequency Fusion

DOI: 10.12677/iae.2026.142033, PP. 282-291

Keywords: BCG,心率估计,深度学习,Attention
Ballistocardiogram (BCG)
, Heart Rate Estimation, Deep Learning, Attention

Full-Text   Cite this paper   Add to My Lib

Abstract:

文章提出了一种基于双分支时频融合架构的模型,用于从心冲击图(BCG)信号中实现高精度的心率估计。该模型以原始BCG信号为输入,通过并行的时间分支与频率分支分别提取时域波形特征与频域周期特征,其中频率分支采用快速傅里叶变换(FFT)获取频谱信息,并引入注意力机制自适应加权关键频段,使模型能够聚焦于心率基频及其谐波成分,有效提升了估计的准确性与鲁棒性。实验结果显示,该模型在平均绝对误差(3.10 BPM)、均方误差(11.23)及决定系数(0.72)等指标上均表现优异,显著优于传统单分支网络与时域回归方法。与近年来相关研究相比,本模型在BCG心率估计任务中展现了显著优势,突显了其在无接触心率监测场景中的实用价值。
This paper proposes a model based on a dual-branch time-frequency fusion architecture for high-precision heart rate estimation from ballistocardiogram (BCG) signals. The model takes raw BCG signals as input and employs parallel temporal and frequency branches to extract time-domain waveform features and frequency-domain periodic features, respectively. In the frequency branch, the fast Fourier transform (FFT) is utilized to obtain spectral information, and an attention mechanism is introduced to adaptively weigh critical frequency bands, enabling the model to focus on the fundamental frequency and its harmonics of heart rate, thereby effectively improving estimation accuracy and robustness. Experimental results show that the model achieves excellent performance in terms of mean absolute error (3.10 BPM), mean squared error (11.23), and coefficient of determination (0.72), significantly outperforming traditional single-branch networks and time-domain regression methods. Compared with recent related studies, this model demonstrates significant advantages in BCG-based heart rate estimation tasks, highlighting its practical potential in non-contact heart rate monitoring scenarios.

References

[1]  World Health Organization (2021) Cardiovascular Diseases (CVDs). WHO Fact Sheets.
[2]  Inan, O.T., Migeotte, P., Park, K., Etemadi, M., Tavakolian, K., Casanella, R., et al. (2015) Ballistocardiography and Seismocardiography: A Review of Recent Advances. IEEE Journal of Biomedical and Health Informatics, 19, 1414-1427.
https://doi.org/10.1109/jbhi.2014.2361732
[3]  Goldberger, A.L., Amaral, L.A.N., Glass, L., Hausdorff, J.M., Ivanov, P.C., Mark, R.G., et al. (2000) Physiobank, Physiotoolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation, 101, e215-e220.
https://doi.org/10.1161/01.cir.101.23.e215
[4]  Carlson, C., Turpin, V., Suliman, A., Ade, C., Warren, S. and Thompson, D.E. (2021) Bed-Based Ballistocardiography: Dataset and Ability to Track Cardiovascular Parameters. Sensors, 21, Article 156.
https://doi.org/10.3390/s21010156
[5]  Hoog Antink, C., Mai, Y., Aalto, R., Bruser, C., Leonhardt, S., Oksala, N., et al. (2020) Ballistocardiography Can Estimate Beat-to-Beat Heart Rate Accurately at Night in Patients after Vascular Intervention. IEEE Journal of Biomedical and Health Informatics, 24, 2230-2237.
https://doi.org/10.1109/jbhi.2020.2970298
[6]  Alametsä, J., Värri, A., Koivuluoma, M. and Barna, L. (2004) The Potential of EMFi Sensors in Heart Activity Monitoring. Proceedings of the 2nd OpenECG Workshop, Berlin, 1-3 April 2004, 81-85.
[7]  Wang, F., Zou, Y., Tanaka, M., Matsuda, T. and Chonan, S. (2007) Unconstrained Cardiorespiratory Monitor for Premature Infants. International Journal of Applied Electromagnetics and Mechanics, 25, 469-475.
https://doi.org/10.3233/jae-2007-751
[8]  Martin-Yebra, A., Landreani, F., Casellato, C., Pavan, E., Frigo, C., Migeotte, P., et al. (2015) Studying Heart Rate Variability from Ballistocardiography Acquired by Force Platform: Comparison with Conventional ECG. 2015 Computing in Cardiology Conference (CinC), Nice, 6-9 September 2015, 929-932.
https://doi.org/10.1109/cic.2015.7411064
[9]  Brink, M., Müller, C.H. and Schierz, C. (2006) Contact-Free Measurement of Heart Rate, Respiration Rate, and Body Movements during Sleep. Behavior Research Methods, 38, 511-521.
https://doi.org/10.3758/bf03192806
[10]  Wiard, R.M., Inan, O.T., Argyres, B., Etemadi, M., Kovacs, G.T.A. and Giovangrandi, L. (2011) Automatic Detection of Motion Artifacts in the Ballistocardiogram Measured on a Modified Bathroom Scale. Medical & Biological Engineering & Computing, 49, 213-220.
https://doi.org/10.1007/s11517-010-0722-y
[11]  Feng, J., Huang, W., Jiang, J., Wang, Y., Zhang, X., Li, Q., et al. (2023) Non-Invasive Monitoring of Cardiac Function through Ballistocardiogram: An Algorithm Integrating Short-Time Fourier Transform and Ensemble Empirical Mode Decomposition. Frontiers in Physiology, 14, Article 1201722.
https://doi.org/10.3389/fphys.2023.1201722
[12]  Bruser, C., Stadlthanner, K., de Waele, S. and Leonhardt, S. (2011) Adaptive Beat-to-Beat Heart Rate Estimation in Ballistocardiograms. IEEE Transactions on Information Technology in Biomedicine, 15, 778-786.
https://doi.org/10.1109/titb.2011.2128337
[13]  Tramontano, A., Tamburis, O., Cioce, S., Venticinque, S. and Magliulo, M. (2023) Heart Rate Estimation from Ballistocardiogram Signals Processing via Low-Cost Telemedicine Architectures: A Comparative Performance Evaluation. Frontiers in Digital Health, 5, Article 1222898.
https://doi.org/10.3389/fdgth.2023.1222898
[14]  Isfahani, R.T., Loghmani, A., Akhavan, A. and Taebi, A. (2024) Evaluation of Signal Processing and Deep Learning Methods for Inter-Beat Interval Extraction from Ballistocardiography Signals. Journal of Computational Methods in Engineering, 44, 49-61.
https://doi.org/10.47176/jcme.44.2.1056
[15]  Jiao, C., Yang, A., Zhao, H., Yi, R., Gou, S., Sha, Y., et al. (2025) Self-Supervised, Non-Contact Heartbeat Detection Based on Ballistocardiograms Utilizing Physiological Information Guidance. IEEE Journal of Biomedical and Health Informatics, 29, 2589-2602.
https://doi.org/10.1109/jbhi.2024.3509875
[16]  Morokuma, S., Saitoh, T., Kanegae, M., Motomura, N., Ikeda, S. and Niizeki, K. (2025) Prediction of ECG Signals from Ballistocardiography Using Deep Learning for the Unconstrained Measurement of Heartbeat Intervals. Scientific Reports, 15, Article No. 999.
https://doi.org/10.1038/s41598-024-84049-0
[17]  Schranz, C., Halmich, C., Mayr, S. and Heib, D.P.J. (2024) Surrogate Modelling of Heartbeat Events for Improved J-Peak Detection in BCG Using Deep Learning. Frontiers in Network Physiology, 4, Article 1425871.
https://doi.org/10.3389/fnetp.2024.1425871
[18]  Pino, E.J., Chavez, J.A.P. and Aqueveque, P. (2017) BCG Algorithm for Unobtrusive Heart Rate Monitoring. 2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT), Bethesda, 6-8 November 2017, 180-183.
https://doi.org/10.1109/hic.2017.8227614

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133