Electrotechnical and Computer Engineering
Vol. 39 No. 11 (2024): Proceedings of Faculty of Technical Sciences
FEEDFORWARD NEURAL NETWORK APPROACH FOR BLOOD PRESSURE ESTIMATION FROM PPG SIGNALS
Abstract
This article addresses the procedure for estimating blood pressure, based on features extracted from PPG signals, using artificial neural networks. Multiple models have been made so as to find the best combination of characteristics, of the PPG signal, that correlate to blood pressure the most. The results from all models are then directly compared.
References
[1] M. Sharma, K. Barbosa, V. Ho, D. Griggs, T. Ghirmai, S. K. Krishnan, T. K. Hsiai, J.-C. Chiao, H. Cao, "Cuff-Less and Continuous Blood Pressure Monitoring: A Methodological Review," Wearable Technologies, 2017.
[2] T. Tamura, Y. Maeda, M. Sekine, M. Yoshida, "Wearable Photoplethysmographic Sensors—Past and Present." Electronics 2014.
[3] A. Poliński, J. Kot, A. Meresta, "Analysis of correlation between heart rate and blood pressure" Federated Conference on Computer Science and Information Systems, 2011.
[4] Y. Liang, Z. Chen, G. Liu, M. Elgendi, "A new, short-recorded photoplethysmogram dataset for blood pressure monitoring in China," Scientific Data (Sci Data), 2018.
[5] J. H.-S. Wang, M.-H. Yeh, P. C.-P. Chao, T.-Y. Tu, Y.-H. Kao, R. Pandey, "A fast digital chip implementing a real-time noise-resistant algorithm for estimating blood pressure using a non-invasive, cuffless PPG sensor" Microsystem Technologies, 2020.
[6] E. O'Brien, B. Waeber, G. Parati, J. Staessen, M.G. Myers, "Blood pressure measuring devices: Recommendations of the European Society of Hypertension." BMJ, 2001.