Blood Pressure Estimation based on Gaussian Mixture Model

Abstract

This paper proposes a new method to determine the systolic and diastolic blood pressure ratios (SBPR and DBPR) utilizing a Gaussian mixture model (GMM). The relevant features, which clearly discriminate the SBPR and DBPR according to the targeted groups, are selected in a feature pool. The selected feature is then represented by the GMM. The SBPR and DBPR are subsequently estimated with the help of the Gaussian mixture model regression (GMR) and then mapped back to SBP and DBP values that are more accurate than those obtained with the conventional method.