Real-time human blood pressure measurement based on laser self-mixing interferometry with extreme learning machine
- PDF / 833,496 Bytes
- 4 Pages / 595.22 x 842 pts (A4) Page_size
- 39 Downloads / 185 Views
Vol.16 No.6, 1 November 2020
Real-time human blood pressure measurement based on laser self-mixing interferometry with extreme learning machine* WANG Xiu-lin (王秀琳)1, LÜ Li-ping (吕莉萍)2, HU Lu (胡路)2, and HUANG Wen-cai (黄文财)2** 1. Department of Physics, Jimei University, Xiamen 361021, China 2. Department of Electronics Engineering, Xiamen University, Xiamen 361005, China1 (Received 17 March 2020; Revised 30 May 2020) ©Tianjin University of Technology and Springer-Verlag GmbH Germany, part of Springer Nature 2020 In this paper, we present a method based on self-mixing interferometry combing extreme learning machine for real-time human blood pressure measurement. A signal processing method based on wavelet transform is applied to extract reversion point in the self-mixing interference signal, thus the pulse wave profile is successfully reconstructed. Considering the blood pressure values are intrinsically related to characteristic parameters of the pulse wave, 80 samples from the MIMIC-II database are used to train the extreme learning machine blood pressure model. In the experiment, 15 measured samples of pulse wave signal are used as the prediction sets. The results show that the errors of systolic and diastolic blood pressure are both within 5 mmHg compared with that by the Coriolis method. Document code: A Article ID: 1673-1905(2020)06-0467-4 DOI https://doi.org/10.1007/s11801-020-0050-x
Non-invasive, non-contact and high-sensitivity methods for the acquisition and monitor of biomedical signals has been the focus of today's biomedical development. Among various of biomedical signals, blood pressure is particularly important because it can intuitively reflect the physical condition of the human body. The most common blood pressure measurement method is the Coriolis method, which has the advantages of high accuracy but cannot achieve real-time value. At present, real-time blood pressure measurement methods based on pulse wave transit time and characteristic parameters prediction need to obtain pulse wave signal through electrical contact or body connection. With the development of laser technology, a technique called self-mixing interference (SMI), which is based on the interaction of a cavity field with the field backscattered from a remote target, is widely applied in many measurement fields such as vibration[1,2], displacement[3-5], velocity[6-8], distance[9,10] and biomedical signals[11-13] due to its advantages of non-contact, high accuracy, and simple structure of one arm. Recently, the laser SMI method has been successfully used to obtain the pulse wave signal[14,15]. In addition, various machine learning algorithms show many advantages in the processing of data in many fields. Extreme learning machine (ELM) is a simple and effective single hidden layer feedforward neural network learning algorithm, which has the advantages of fast learning speed and good generalization performance[16]. In this paper, we first propose a non-contact, real-time *
blood pressure measurement method based on the laser SMI with E
Data Loading...
