Noninvasive Continuous Blood Pressure Measurment Method Based on
SWT and ANN
WU Yu-dong1,
ZHONG Shun-cong1,2,
SHEN Yao-chun1,3
1.Laboratory of Optics, Terahertz and
Non-destructive Testing & Evaluation,
School of Mechanical Engineering and
Automation, Fuzhou University, Fuzhou
Fujian 350108, China; 2.Fujian Key
Laboratory of Medical Instrument and
Pharmaceutical Technology, Fuzhou
Fujian 350108, China; 3.Department of
Electrical Engineering and Electronics,
University of Liverpool, Liverpool L69
3GJ, United Kingdom
Abstract:In order to solve the problem of non-invasive continuous measurement of blood pressure in
electronic sphygmomanometer, a non-invasive blood pressure measurement method based on stationary
wavelet transform (SWT) algorithm and photoplethysmography were proposed. In the experiment, a
total of 26900 pulse wave signals from the mimic database were analyzed and subsequently the pulse
wave was decomposed by SWT. Furthermore, 10 characteristic parameters of the 5th layer high frequency
reconstruction signal were extracted as the input of artificial neural networks (ANN). The blood pressure
corresponding to the pulse wave was taken as the output of ANN to train the blood pressure model. The
error analysis of the model was carried out. The results indicated that the error of the model met the
standards of the American association for the advancement of medical instrumentation. Therefore, this
method can be employed in noninvasive continuous measurement of blood pressure.
吴育东1,钟舜聪1,2,沈耀春1,3. 基于SWT和ANN的无创连续血压测量方法研究[J]. 中国医疗设备, 2017, 32(5): 22-27.
WU Yu-dong1,
ZHONG Shun-cong1,2,
SHEN Yao-chun1,3. Noninvasive Continuous Blood Pressure Measurment Method Based on
SWT and ANN. China Medical Devices, 2017, 32(5): 22-27.