Open AccessComparison of EMD, VMD and EEMD Methods in Respiration Wave Extraction Based on PPG Waves
Author(s) -
Sugondo Hadiyoso,
Ervin Masita Dewi,
Inung Wijayanto
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1577/1/012040
Subject(s) - hilbert–huang transform , pattern recognition (psychology) , computer science , artificial intelligence , signal (programming language) , speech recognition , acoustics , computer vision , physics , filter (signal processing) , programming language
Plethysmographic (PPG) wave analysis can provide interesting information including heart rate and oxygen saturation. Since PPG signals are modulated by breathing waves, further analysis can provide additional information that is the respiration rate (RR). This is a way to simplify sensor devices. This paper discusses a respiration wave extraction mechanism to calculate RR using the signal decomposition approach. Decomposition methods which are applied in this study include empirical mode decomposition (EMD), variational mode decomposition (VMD) and ensemble empirical mode decomposition (EEMD). This paper specifically addresses the performance of EEMD to EMD and VMD. This proposed method has been tested on an open PPG dataset (containing PPG and RR wave signals). Test results on 20 PPG signals, each of which had a duration of 1 minute showed that the EEMD was able to estimate the RR with an accuracy of more than 90% with an average error rate of 1 rate/minute.