Application of Independent Component Analysis and Nelder–Mead Particle Swarm Optimization Algorithm in Non-Contact Blood Pressure Estimation

Autor: Te-Jen Su, Wei-Hong Lin, Qian-Yi Zhuang, Ya-Chung Hung, Wen-Rong Yang, Bo-Jun He, Shih-Ming Wang
Jazyk: angličtina
Rok vydání: 2024
Předmět:
Zdroj: Sensors, Vol 24, Iss 11, p 3544 (2024)
Druh dokumentu: article
ISSN: 1424-8220
DOI: 10.3390/s24113544
Popis: In recent years, hypertension has become one of the leading causes of illness and death worldwide. Changes in lifestyle among the population have led to an increasing prevalence of hypertension. This study proposes a non-contact blood pressure estimation method that allows patients to conveniently monitor their blood pressure values. By utilizing a webcam to track facial features and the region of interest (ROI) for obtaining forehead images, independent component analysis (ICA) is employed to eliminate artifact signals. Subsequently, physiological parameters are calculated using the principle of optical wave reflection. The Nelder–Mead (NM) simplex method is combined with the particle swarm optimization (PSO) algorithm to optimize the empirical parameters, thus enhancing computational efficiency and accurately determining the optimal solution for blood pressure estimation. The influences of light intensity and camera distance on the experimental results are also discussed. Furthermore, the measurement time is only 10 s. The superior accuracy and efficiency of the proposed methodology are demonstrated by comparing them with those in other published literature.
Databáze: Directory of Open Access Journals
Nepřihlášeným uživatelům se plný text nezobrazuje