Novel Data Augmentation Employing Multivariate Gaussian Distribution for Neural Network-Based Blood Pressure Estimation

In this paper, we propose a novel data augmentation technique employing multivariate Gaussian distribution (DA-MGD) for neural network (NN)-based blood pressure (BP) estimation, which incorporates the relationship between features in multi-dimensional feature vector to describe correlated real-valued random variables successfully. To verify proposed algorithm against conventional algorithm, compare results terms of mean error (ME) with standard deviation and Pearson correlation using 110 subjects contributed database (DB) includes systolic BP (SBP), diastolic (DBP), photoplethysmography (PPG) signal, electrocardiography (ECG) signal. For each subject, 3 times (or 6 times) measurements are accomplished PPG ECG signals recorded 20 s. And, performance estimation (BPE) algorithms, train BPE model two-stage system, called stacked NN. Since can express properly than errors turn out lower compared shows superiority our approach.