Estimating Blood Pressure based PPG signals by using Artificial Neural Networks.

• Main Authors: Kotagiri Naga Gowri Priyanka, 郭力
• Other Authors: Chao, Paul C. P.
• Format: Others
• Language: en_US
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/9aqaf8

碩士 === 國立交通大學 === 電機資訊國際學程 === 107 === A new approach for estimating blood pressure from photoplethysmography (PPG) signals is developed using artificial neural networks (ANNs). The valuable information needed for monitoring individual health condition is provided by the condition of blood pressure (BP). It is one of among the vital parameters needed for early detection of many cardiovascular diseases. Regular blood pressure monitoring is necessary and a part of personal healthcare. A reflective PPG sensor module is developed for the cuffless, non-invasive BP measurement based on PPG at wrist on radial artery. Blood Pressure is in a relation with the pulse duration of the PPG. Artificial Intelligence approach is an amazing opportunity to make healthcare system more efficient for medical workers and patients. In this thesis, we propose to estimate blood pressure from PPG signal by using artificial neural networks approach. This is the study reported to consider varied temporal periods of PPG waveforms as features for application of artificial neural networks to estimate blood pressure. The results obtained by comparing the output results with reference device OMRON data is very encouraging as overall SBP and DBP regression (R) as 0.98666.