Noninvasive Human Ballistocardiography Assessment Based on Deep Learning
Qing Wang, Weimin Lyu, Shuyang Chen, Changyuan Yu
Abstract
Ballistocardiography (BCG) is a vibration signal of human cardiac activity, which can be obtained by an optical fiber sensor (OFS) in a noninvasive way. The proposed OFS, as a low power consumption, noncontact, noninvasive real-time health monitoring instrument, has been developed into an effective health care monitoring method. However, when people need to monitor BCG for a long time, a large number of BCG data needs to be collected, which is time-consuming, costly, and labor-intensive. To solve this problem, in this article, we proposed a novel deep learning model, termed BCGNET. First, a convolutional neural network (CNN) is used to extract the short-term dependence between multivariate loads. Then, the recurrent neural network (RNN) model is used to capture the long-term dependence of load sequence, and the ultra-long-term repetitive pattern of load sequence is fully studied by using the long-short term memory (LSTM) network with a recurrent skip. Finally, the autoregressive layer and full connection layer are used for combined prediction. Extensive experimental results demonstrate the superiority of BCGNET; the accuracy is 91.43% achieved by the proposed BCGNET compared with CNN (89.61%), RNN (89.88%) and multihead attention network (MHA-Net) (90.22%), and also show the proposed model has good performance in BCG prediction and assessment.