Research On Blood Pressure Sensing Technology Based On Continuous Wave Radar

Blood pressure is an important physiological parameter reflecting human health,which can prove whether the cardiovascular function of human body is healthy.The researches on non-invasive blood pressure measurement are always the hot topics in clinical medicine.Traditional blood pressure measurement instruments all need to contact patients,or even invade patients,causing discomfort to patients,which cannot be monitored for a long time,cannot get rid of the bondage of airbag,and cannot continuously achieve high-precision blood pressure value.However,non-contact blood pressure estimation technology can overcome these drawbacks.One of these techniques named biotic radar technology has many advantages,including insensitivity to the environment and powerful penetration.Therefore,it is more suitable for monitoring of pulse wave signal compared with other non-contact monitoring techniques,such as infrared detection technology and video tracking technology.This paper uses the continuous wave radar sensor to detect the pulse wave signal,extracts the features of pulse wave signal and then adopts linear regression and machine learning regression algorithm to estimate blood pressure,which can continuously achieve high-precision blood pressure value.At the same time,this paper completes the calculation of cardiovascular characteristic parameters and finishes the study of blood pressure variability.Anyway,the application of this study prospect is bright,and it can be applied in the field of clinical medicine assisted diagnosis and family telemedicine diagnosis.The main work is as follows:1.The hardware platform of continuous wave radar system was introduced,the theoretical analysis for pulse wave signal acquisition and the extraction of feature points were explained.The paper also designs a comparative test to verify that the radar measurement signal is pulse wave signal rather than heartbeat signal.2.A pulse wave characteristic point extraction method based on EMD algorithm was proposed because of the characteristics of periodic non-stationary complex vibration of pulse wave.The method can accurately identify the characteristic points by analyzing non-linear and non-stationary signals.According to the extracted pulse wave characteristic points,the pulse wave conduction time was calculated,and the accuracy of the continuous wave radar system in measuring the pulse wave conduction time was verified by the control experiment.3.For estimating the individual measurement of blood pressure,this paper completed the blood pressure estimation based on the linear regression model.Then,the method based on Gaussian process regression was advanced,which can complete the complex nonlinear regression calculation without prior conditions.The measurement accuracy of the algorithm had been verified by the experiments,which realized the high precision continuous blood pressure monitoring.4.This paper studied the extraction method of cardiovascular characteristic parameters based on pulse wave.For estimating the group measurement of blood pressure,this paper completed the blood pressure estimation based on neural network regression model.Then,the method based on support vector regression model was advanced.The algorithm can solve nonlinear problems,which has the quicker running speed and the litter request of data sample.The measurement accuracy of the algorithm had been verified by the experiments.In the end,the long-term blood pressure variability,short-term blood pressure variability and ultra-short-term blood pressure variability were studied.