Extraction of Respiration from PPG Signals Using Hilbert Vibration Decomposition

Abstract

A new approach using the Hilbert vibration decomposition (HVD) for extracting the respiration from the photoplethysmographic (PPG) signal is proposed. It is suggested that the largest energy component of the PPG signal acquired using the HVD is analogous to the respiratory signal. The proposed PPG-derived respiration (PDR) technique is examined over the Capnobase and MIMIC datasets by evaluating the correlation and respiratory rate errors calculated between the derived and reference respiratory rates (RRs). Upon comparing the performance of the proposed approach with the existing techniques, the proposed approach is seen to be yielding better correlation and smaller errors in the RRs computed from the PDR and recorded respiration signals on both the datasets. The experimental analysis suggests that the proposed technique can be employed for efficacious computation of the respiration from the PPG signal. Efficient and reliable extraction of the respiratory signal from PPG will help in the improvement of low-cost and less discomfort mobile-based healthcare systems.