File(s) not publicly available
An EEMD-PCA approach to extract heart rate, respiratory rate and respiratory activity from PPG signal.
conference contribution
posted on 2023-02-27, 23:05 authored by Mohammod Motin, Marimuthu Palaniswami, Chandan KarmakarChandan KarmakarThe pulse oximeter's photoplethysmographic (PPG) signals, measure the local variations of blood volume in tissues, reflecting the peripheral pulse modulated by cardiac activity, respiration and other physiological effects. Therefore, PPG can be used to extract the vital cardiorespiratory signals like heart rate (HR), respiratory rate (RR) and respiratory activity (RA) and this will reduce the number of sensors connected to the patient's body for recording vital signs. In this paper, we propose an algorithm based on ensemble empirical mode decomposition with principal component analysis (EEMD-PCA) as a novel approach to estimate HR, RR and RA simultaneously from PPG signal. To examine the performance of the proposed algorithm, we used 45 epochs of PPG, electrocardiogram (ECG) and respiratory signal extracted from the MIMIC database (Physionet ATM data bank). The ECG and capnograph based respiratory signal were used as the ground truth and several metrics such as magnitude squared coherence (MSC), correlation coefficients (CC) and root mean square (RMS) error were used to compare the performance of EEMD-PCA algorithm with most of the existing methods in the literature. Results of EEMD-PCA based extraction of HR, RR and RA from PPG signal showed that the median RMS error (quartiles) obtained for RR was 0 (0, 0.89) breaths/min, for HR was 0.62 (0.56, 0.66) beats/min and for RA the average value of MSC and CC was 0.95 and 0.89 respectively. These results illustrated that the proposed EEMD-PCA approach is more accurate in estimating HR, RR and RA than other existing methods.
History
Pagination
3817 - 3820Location
Orlando, FL, USAPublisher DOI
Start date
2016-08-16End date
2016-08-20ISSN
1557-170XISBN-13
978-1-4577-0220-4Language
engPublication classification
E1.1 Full written paper - refereedTitle of proceedings
2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC