Non-invasive hypertension monitoring in smart furniture
Hypertension is a silent killer as it is difficult to be detected. Daily monitoring blood pressure is a good way for early diagnose hypertension. The common commercial hypertension monitoring device only consists of local data storage and normally equipped with cuff The data from the device is diffi...
| Main Author: | |
|---|---|
| Format: | Undergraduates Project Papers |
| Language: | English |
| Published: |
2017
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/25928/ http://umpir.ump.edu.my/id/eprint/25928/ http://umpir.ump.edu.my/id/eprint/25928/1/Non-invasive%20hypertension%20monitoring.pdf |
| Summary: | Hypertension is a silent killer as it is difficult to be detected. Daily monitoring blood pressure is a good way for early diagnose hypertension. The common commercial hypertension monitoring device only consists of local data storage and normally equipped with cuff The data from the device is difficult to be retrieved automatically and the repetition of pressure inflation during measurement may cause trauma. Recently, application of Internet of Things (loT) with home health monitoring system becomes a trend. This project proposed a cuffless hypertension monitoring, which embedded in the armchair, with a feature of automatically upload the recorded blood pressure and pulse rate readings to a cloud storage. An optical sensor is used to detect the photoplethysmography (PPG) wave from the fingertip of the patient. The raw PPG wave is filtered and amplified. Three parameters are taken from the PPG wave, including, systolic upstroke time (ST), diastolic time (DT), and time taken between systolic peak and diastolic peak (P2P) to estimate systolic blood pressure (SBP), diastolic blood pressure (DBP), and pulse rate (PR). Correlation and linear regression analysis are used to correlate this PPG parameter with blood pressure. The pulse rate is estimated by using the time taken between two successive optimum peaks in PPG wave. The mean difference of estimated SBP and DBP comparing to reference is 3.5909 ± 0.5478 mmHg and 3.6769 ± 0.6095 mmHg respectively. The mean difference of estimated PR comparing to reference is 5.914 ± 0.6970 BPM. The output, SBP, DBP, and PR, is uploaded to a cloud storage, Azure Blob Storage, and presented in Power BI dashboard. By providing cuffless blood pressure and pulse rate measurement and instantaneous upload BP and PR readings to cloud storage, the proposed solution has overcome the problem of common hypertension monitoring device. |
|---|