Project DetailsPhotoplethysmography (PPG) is a low-cost, noninvasive, and effective method for measuring physiological parameters such as blood pressure. It is possible to obtain PPG signals from smart devices, making measurements of important vital signs more accessible than ever. However, PPG signal measurement is inherently noisy and occasionally unreliable thus posing many challenges. This project is a continuation of previous projects performed in SIPL for measuring blood pressure using smart devices. In this project report, we briefly review the theoretical background and rationale for using PPG signals, as well as describe in detail the filtering and preprocessing procedures performed on raw pairs of PPG and blood pressure signals. Furthermore, the report includes information on the deep learning stage for predicting blood pressure from PPG signals from the MIMIC III database, which contains medical information for ICU patients. The project goal is to estimate blood pressure as accurately as possible in order to provide a more accessible replacement for other existing devices. In part A of the project, we concentrated on building the entire system, whereas in part B, we focused on pre-processing the PPG signals to create a dataset with high quality signals for training the network.
