A novel non-contact heart rate measurement method based on EEMD combined with FastICA

被引：9

作者：

Shi, Yingli ^{[1
,2
]}

Qiu, Jian ^{[1
,2
]}

Peng, Li ^{[1
,2
]}

Han, Peng ^{[1
,2
]}

Luo, Kaiqing ^{[1
,2
]}

Liu, Dongmei ^{[1
,2
]}

机构：

[1] South China Normal Univ, Sch Phys & Telecommun Engn, Guangzhou 510006, Guangdong, Peoples R China

[2] South China Normal Univ, Qingyuan Inst Sci & Technol Innovat, Qingyuan 511517, Guangdong, Peoples R China

来源：

PHYSIOLOGICAL MEASUREMENT | 2023年 / 44卷 / 05期

基金：

中国国家自然科学基金;

关键词：

imaging photoplethysmography (IPPG); modified EEMD; modified FastICA; heart rate (HR); multi-region ROI; EMPIRICAL MODE DECOMPOSITION; IMAGE SENSOR; ROBUST;

D O I：

10.1088/1361-6579/accefd

中图分类号：

Q6 [生物物理学];

学科分类号：

071011 ;

摘要：

Objective. The imaging photoplethysmography (IPPG), which is applied to heart rate measurement, is susceptible to interference caused by illumination variations during photography. To improve the accuracy, robustness, and real-time performance of IPPG, a new method combined with modified ensemble empirical mode decomposition (EEMD) and fast independent component analysis (FastICA) was proposed. Approach. On the modified EEMD, to reduce the error caused by the residual white noise of the algorithm, it was characterized by recurrently updating zero-mean white noise for ensemble averaging based on the standard deviation of the input signal. On the modified FastICA, its constructed nonlinear function was superseded by Huber's approximation function to improve the robustness and running speed. Main results. Comparison experiments were conducted between the MAHNOB-HCI database and own collected data. In the hybrid natural light and computer screen light scenario, the mean absolute error (MAE) of heart rate amounted to 0.93 beats per minute and the correlation coefficient r

引用

页数：15

共 35 条

[11]

Hyvarinen A, 1998, ADV NEUR IN, V10, P273

[12] One-unit contrast functions for independent component analysis: A statistical analysis [J].