University of Twente Student Theses
Deep Learning Method for ABP Estimattion Using PPG During Daily Activities
Mahmoud, Moustafa (2024) Deep Learning Method for ABP Estimattion Using PPG During Daily Activities.
|
PDF
4MB |
| Abstract: | The advances in Machine Learning (ML) models widened the capabilities of biomedical signal processing. One application of ML that garnered recent interest is the estimation of physiological parameters using Deep Neural Networks (DNN). With Cardiovascular Diseases (CVD) posing a global health, recent literature has explored the utility of Deep Neural Networks in estimating Arterial Blood Pressure (ABP) waveforms using Biosignals such as Photoplethysmography (PPG). PPG’s advantage is that it is portable and noninvasive, however, it is heavily influenced by motion artifacts (MA). In this report, the common themes in this avenue of literature will be explored. The advantages and disadvantages of using DNN will be analyzed. From these findings, a DNN model that estimates ABP waveforms from PPG signals will be implemented and evaluated. The data that the system will be tested with are acquired from an experimental protocol that includes static and dynamic activities. The dynamic activities are included as most of the proposed ABP models in the literature are trained on ABP and PPG data from the MIMIC III biosignals database which contains data from ICU patients exclusively. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Programme: | Electrical Engineering BSc (56953) |
| Link to this item: | https://purl.utwente.nl/essays/98124 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page