Motion artifact reduction in photoplethysmogram signals based on Periodic Component Factorization.

Continuous blood pressure measurement based on pulse transit time (PTT) is a deeply research topic over recent decades. Advanced algorithms have been proposed by scholars to give satisfactory estimation in stationary position. Nevertheless, pulse transit time (PTT) is shown to be strongly affected by hand movement and the estimation of blood pressure is no longer accurate under strenuous exercise. Because of this, a novel algorithm called Periodic Component Factorization (PCF), which is an extension of Independent Component Analysis (ICA), for better removal of motion artifact (MA) from photoplethysmography (PPG) signals is proposed in this paper. Compared to FastICA algorithm based on nongaussianity such as kurtosis and skewness, PCF is able to extract dependent source components from noisy signals when the PPG signal shows quasi-periodicity or periodicity. This newly proposed algorithm undoubtedly shows its practicality and effectiveness in removing motion artifact of PPG signals.

Continuous systolic and diastolic blood pressure estimation utilizing long short-term memory network.

A novel blood pressure estimation method based on long short-term memory neural network, one of the recurrent neural networks being commonly used nowadays, is proposed in this paper for better chronic diseases monitoring. Along with the neural network, a newly proposed ambulatory blood pressure (ABP) processing technique called Two-stage Zero-order Holding (TZH) algorithm has also been presented in the paper. The proposed methodology has the advantages over traditional blood pressure estimation algorithms which are based on Pulse Transit time (PTT). The paper addresses the effectiveness of the algorithm by computing the Root-Mean-Squared Errors (RMSE) between the BP estimated and the ground truth. Our algorithm shows precise systolic blood pressure and diastolic blood pressure estimation with the average RMSE values in 2.751 mmHg and 1.604 mmHg respectively across the sample used. Experimental results suggest that BP estimation based on LSTM has great potential to be embedded into monitoring system for better accuracy and generalization.