Feature Selection Method for Estimating Systolic Blood Pressure Using the Taguchi Method

This paper proposes a method for selecting photoplethysmogram features for estimating systolic blood pressure (SBP), which uses the signal-to-noise ratio (SNR) obtained from the Taguchi method. Cuffless estimation of blood pressure using just one photoplethysmograph was carried out based on the photoplethysmogram features. However, these features are highly vulnerable to noise generated by sources such as individual variability, resulting from factors such as age and gender. Therefore, features need to be robust against such noise for accurate estimation of blood pressure. In this study, we used an orthogonal array and the SNR from the Taguchi method for selecting features of multiple regression analysis that are robust against noise. We estimated SBP from two datasets by applying the proposed feature selection method to multiple regression analysis. The obtained results show that the correlation coefficients between the actual measurement values and the estimated values were 0.88 and 0.87 for datasets 1 and 2, which are higher than those of similar methods used for comparison purposes. This confirms the effectiveness of the proposed method in estimating SBP.