Use of multi scale PCA for extraction of respiratory activity from photoplethysmographic signals

Abstract

The fact that the photoplethysmographic (PPG) signal caries respiratory information in addition to arterial blood oxygen saturation attracted the researchers to extract the respiratory information from it. In this current work, we present an efficient algorithm, based on the multi scale principal component analysis (MSPCA) technique to extract the respiratory activity from the PPG signals. MSPCA is a powerful combination of wavelets and principal component analysis (PCA). In MSPCA technique, PCA is used in computing coefficients of wavelet at each scale, and finally combining all the results at relevant scales. Experiments carried on the data records drawn from the MIMIC database of Physionet archives revealed a very high degree of coherence between the PPG derived respiratory (PDR) signal and the recorded respiratory signal. Results demonstrated that MSPCA performed exceptionally well for extraction of respiratory activity from PPG signals with high correlation coefficient and accuracy rates of above 98%.