Estimation System of Blood Pressure Variation with Photo-Plethysmograph Signals using Neural Network

摘要

In this paper, a target is to improve accuracy of a blood pressure estimation system using photo-plethysmograph signals. A blood pressure estimation algorithm using multiple regression analysis is proposed and a blood pressure estimation using the neural network is studied newly. Experimental results have shown that estimation accuracy can be improved. Estimation error of systolic blood pressure value using multiple regression analysis with the proposed algorithm was reduced by approximately 16%. Furthermore, Estimation error was reduced by approximately 22% than conventional multiple regression analysis in case of a blood pressure estimation by machine learning using the neural network. It has been found that estimation accuracy is improved and shows the possibility of blood pressure estimation using the neural network.