Abstract
In response to the rising prevalence of hypertension due to lifestyle changes, this study introduces a novel approach for non-contact blood pressure (BP) monitoring. Recognizing the "silent killer" nature of hypertension, this research focuses on developing accessible, non-invasive BP measurement methods. This study compares two distinct non-contact BP measurement approaches: one combining the Nelder-Mead simplex method with particle swarm optimization (NM-PSO) and the other using machine learning regression analysis. In the NM-PSO method, a standard webcam captures continuous images of the palm, extracting physiological data through light wave reflection and employing independent component analysis (ICA) to remove noise artifacts. The NM-PSO achieves a verified root mean square error (RMSE) of 2.71 mmHg for systolic blood pressure (SBP) and 3.42 mmHg for diastolic blood pressure (DBP). Alternatively, the regression method derives BP values through machine learning-based regression formulas, resulting in an RMSE of 2.88 mmHg for SBP and 2.60 mmHg for DBP. Both methods enable fast, accurate, and convenient BP measurement within 10 s, suitable for home use. This study demonstrates a cost-effective solution for non-contact BP monitoring and highlights each method's advantages. The NM-PSO approach emphasizes optimization in noise handling, while the regression method leverages formulaic efficiency in BP estimation. These results offer a biomimetic approach that could replace traditional contact-based BP measurement devices, contributing to enhanced accessibility in hypertension management.