A Dynamic Bayesian Multichannel Fusion Scheme for Heart Rate Monitoring With Ballistocardiograph Signals in Free-Living Environments
Jun Qi, Ruilin Cai, Qing Liu, Wei Wang, Jieming Ma, Jianjun Chen
Abstract
Ballistocardiograph (BCG) stands out as a noncontact technology for heart monitoring, offering a wealth of cardiovascular parameter information. Its applications have overshadowed traditional electrocardiogram particularly for free-living environment, such as home monitoring, in recent years. However, challenges arise from the susceptibility of BCG signals to positional variations, bodily movements, and systemic noise, posing formidable obstacles for detection algorithms. In this article, we propose a novel interbeat interval detection approach with the dynamic Bayesian network for multichannel fusion, in terms of five unique indicators for the precise localization of cardiac activity from extracted features. We also introduce a peak detection method to locate the positions of all HIJK complex within BCG segment and evaluate the generalization of the proposed method in the simulated environment of different noise generation. The results from the dataset comprising 36 healthy subjects and four cardiovascular disease patients show that the proposed method exhibits average coverage rate up to 96.15%; the mean square error is 0.04 compared with single-channel measures, which suggest the potential of our method in assisting the long-term heartbeat monitoring in free-living environments.