Noninvasive Measurement of Vital Signs With the Optical Fiber Sensor Based on Deep Learning

Abstract

As a vital sign of human, ballistocardiography (BCG) signal is widely used to indicate the health status of an individual. It can be captured by optical fiber sensor in a non-invasive way. Besides, some significant physiological information, such as heart rate (HR) and respiration rate (RR), can also be extracted from BCG signal. As a medical instrument characterized by low power consumption, no interference, no invasion and the capability of real-time health monitoring, optical fiber sensor provides an effective solution to health care monitoring. However, when long-term monitoring of HR and RR is required for patients, it is necessary to collect a large amount of BCG data, which incurs a considerable amount of time and labor costs. To solve this problem, a novel deep learning model is proposed in this paper, namely ELA. Long-short term memory (LSTM) has the capability to memorize long-distance information states. According to this method, the improved empirical mode decomposition (EMD) algorithm (VEMD) is applied to convert the complex problem of HR and RR time series prediction into multiple sub-problems with relatively simple intrinsic mode function (IMF) component sequence prediction. Then, the proposed ELA model is adopted to model the HR and RR sub-sequences decomposed by VEMD. Accordingly, the results of IMF component subsequence prediction are obtained, with all the prediction results linearly summed to obtain the final prediction result. Moreover, experimental results are obtained to demonstrate the superiority of ELA and the R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> is 0.9946, indicating the excellent performance of the proposed model in the assessment and prediction of vital signs.