Methods for Continuous Blood Pressure Estimation Using Temporal Convolutional Neural Networks and Ensemble Empirical Mode Decomposition

Arterial blood pressure is not only an important index that must be measured in routine physical examination but also a key monitoring parameter of the cardiovascular system cardiac surgery, drug testing, and intensive care. To improve measurement accuracy continuous pressure, this paper uses photoplethysmography (PPG) signals to estimate diastolic systolic based on ensemble empirical mode decomposition (EEMD) temporal convolutional network (TCN). In method, clean PPG signal decomposed by EEMD obtain n-order intrinsic functions (IMF), then IMF original are input into constructed TCN neural model, results output. The show has better performance than CNN, CNN-LSTM, CNN-GRU. Using data added with IMF, above model those as input, which (SBP) (DBP) EEMD-TCN ?1.55 ± 9.92 mmHg 0.41 4.86 mmHg. According estimation results, DBP meets requirements AAMI standard, BHS evaluates it Grade A, SD SBP close standard AAMI, B.