Abstract
The photoplethysmography(PPG) waveform is a pulsatile physiological waveform reflecting the blood volume changes attributed to cardiac synchronous activities. The waveforms components below normal heart beat (less than 0.8Hz) are mainly contributed by respiration, sympatho-adrenal response and body regulatory system. Therefore, PPG waveforms are commonly used as non-invasive approach to extract cardiorespiratory signals such as heartbeat and respiration rate. The existing methods either only estimate the respiration rate or sensitive to noises. Hence we propose a novel method to both recover the respiration signal (RS) and estimate respiration rate (RR) by combining the variational mode decomposition and principal component analysis (VMDPCA) simultaneously. Some 80 PPG samples provided by Physiobank, i.e. the MIMIC database were used to validate the performance of our algorithm. The results were examined with respect to the golden truth respiration signal sampled by capnography. The performance measurement matrix was composed of mean normalized root mean square deviation (NRMSD), magnitude squared coherence (MSC) and Pearson's correlation coefficient (PCC) with values of 0.434, 0.392 and 0.213 respectively. The proposed method had also achieved 6.67 and 3.34 times faster than EEMDPCA and EWTPCA algorithms respectively.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
