Non-Invasive Heart Rate Estimation From Ballistocardiograms Using Bidirectional LSTM Regression


Non-invasive heart rate estimation is of great importance in daily monitoring of cardiovascular diseases. In this paper, a bidirectional long short term memory (bi-LSTM) regression network is developed for non-invasive heart rate estimation from the ballistocardiograms (BCG) signals. The proposed deep regression model provides an effective solution to the existing challenges in BCG heart rate estimation, such as the mismatch between the BCG signals and ground-truth reference, multi-sensor fusion and effective time series feature learning. Allowing label uncertainty in the estimation can reduce the manual cost of data annotation while further improving the heart rate estimation performance. Compared with the state-of-the-art BCG heart rate estimation methods, the strong fitting and generalization ability of the proposed deep regression model maintains better robustness to noise ( e.g. , sensor noise) and perturbations ( e.g. , body movements) in the BCG signals and provides a more reliable solution for long term heart rate monitoring.




C. Jiao, C. Chen, S. Gou, D. Hai, B. Su, M. Skubic, L. Jiao, A. Zare and K.C. Ho, "Non-Invasive Heart Rate Estimation from Ballistocardiograms using Bidirectional LSTM Regression," in IEEE Journal of Biomedical and Health Informatics, 2021.
Title = {Non-Invasive Heart Rate Estimation from Ballistocardiograms using Bidirectional LSTM Regression}, 
Author = {Changzhe Jiao and Chao Chen and Shuiping Gou and Dong Hai and Bo-Yu Su and Marjorie Skubic and Licheng Jiao and Alina Zare and K.C. Ho},  
Journal = {IEEE Journal of Biomedical and Health Informatics}, 
Volume = {25},
Page= {3396-3407},
Print ISSN= {2168-2194},
Online ISSN= {2168-2208},
Digital Object Identifier= {10.1109/JBHI.2021.3077002},  
Year = {2021},