Evaluating Edge Computing and Compression for Remote Cuff-Less Blood Pressure Monitoring
Remote health monitoring systems play an important role in the healthcare sector. Edge computing is a key enabler for realizing these systems, where it is required to collect big data while providing real-time guarantees. In this study, we focus on remote cuff-less blood pressure (BP) monitoring thr...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Journal of Sensor and Actuator Networks |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2224-2708/12/1/2 |
| _version_ | 1797619904977829888 |
|---|---|
| author | Ward Goossens Dino Mustefa Detlef Scholle Hossein Fotouhi Joachim Denil |
| author_facet | Ward Goossens Dino Mustefa Detlef Scholle Hossein Fotouhi Joachim Denil |
| author_sort | Ward Goossens |
| collection | DOAJ |
| description | Remote health monitoring systems play an important role in the healthcare sector. Edge computing is a key enabler for realizing these systems, where it is required to collect big data while providing real-time guarantees. In this study, we focus on remote cuff-less blood pressure (BP) monitoring through electrocardiogram (ECG) as a case study to evaluate the benefits of edge computing and compression. First, we investigate the state-of-the-art algorithms for BP estimation and ECG compression. Second, we develop a system to measure the ECG, estimate the BP, and store the results in the cloud with three different configurations: (i) estimation in the edge, (ii) estimation in the cloud, and (iii) estimation in the cloud with compressed transmission. Third, we evaluate the three approaches in terms of application latency, transmitted data volume, and power usage. In experiments with batches of 64 ECG samples, the edge computing approach has reduced average application latency by 15%, average power usage by 19%, and total transmitted volume by 85%, confirming that edge computing improves system performance significantly. Compressed transmission proved to be an alternative when network bandwidth is limited and edge computing is impractical. |
| first_indexed | 2024-03-11T08:34:40Z |
| format | Article |
| id | doaj.art-82d987b3427349a8b4c26255cc281602 |
| institution | Directory Open Access Journal |
| issn | 2224-2708 |
| language | English |
| last_indexed | 2024-03-11T08:34:40Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Sensor and Actuator Networks |
| spelling | doaj.art-82d987b3427349a8b4c26255cc2816022023-11-16T21:34:41ZengMDPI AGJournal of Sensor and Actuator Networks2224-27082022-12-01121210.3390/jsan12010002Evaluating Edge Computing and Compression for Remote Cuff-Less Blood Pressure MonitoringWard Goossens0Dino Mustefa1Detlef Scholle2Hossein Fotouhi3Joachim Denil4Faculty of Applied Engineering, University of Antwerp, 2020 Antwerp, BelgiumEmbedded Systems, ALTEN Sweden AB, 118 46 Stockholm, SwedenEmbedded Systems, ALTEN Sweden AB, 118 46 Stockholm, SwedenSchool of Innovation, Design, and Engineering, Mälardalen University, 722 20 Västerås, SwedenFaculty of Applied Engineering, University of Antwerp, 2020 Antwerp, BelgiumRemote health monitoring systems play an important role in the healthcare sector. Edge computing is a key enabler for realizing these systems, where it is required to collect big data while providing real-time guarantees. In this study, we focus on remote cuff-less blood pressure (BP) monitoring through electrocardiogram (ECG) as a case study to evaluate the benefits of edge computing and compression. First, we investigate the state-of-the-art algorithms for BP estimation and ECG compression. Second, we develop a system to measure the ECG, estimate the BP, and store the results in the cloud with three different configurations: (i) estimation in the edge, (ii) estimation in the cloud, and (iii) estimation in the cloud with compressed transmission. Third, we evaluate the three approaches in terms of application latency, transmitted data volume, and power usage. In experiments with batches of 64 ECG samples, the edge computing approach has reduced average application latency by 15%, average power usage by 19%, and total transmitted volume by 85%, confirming that edge computing improves system performance significantly. Compressed transmission proved to be an alternative when network bandwidth is limited and edge computing is impractical.https://www.mdpi.com/2224-2708/12/1/2healthedgecloudcompressionblood pressure estimationcuff-less |
| spellingShingle | Ward Goossens Dino Mustefa Detlef Scholle Hossein Fotouhi Joachim Denil Evaluating Edge Computing and Compression for Remote Cuff-Less Blood Pressure Monitoring Journal of Sensor and Actuator Networks health edge cloud compression blood pressure estimation cuff-less |
| title | Evaluating Edge Computing and Compression for Remote Cuff-Less Blood Pressure Monitoring |
| title_full | Evaluating Edge Computing and Compression for Remote Cuff-Less Blood Pressure Monitoring |
| title_fullStr | Evaluating Edge Computing and Compression for Remote Cuff-Less Blood Pressure Monitoring |
| title_full_unstemmed | Evaluating Edge Computing and Compression for Remote Cuff-Less Blood Pressure Monitoring |
| title_short | Evaluating Edge Computing and Compression for Remote Cuff-Less Blood Pressure Monitoring |
| title_sort | evaluating edge computing and compression for remote cuff less blood pressure monitoring |
| topic | health edge cloud compression blood pressure estimation cuff-less |
| url | https://www.mdpi.com/2224-2708/12/1/2 |
| work_keys_str_mv | AT wardgoossens evaluatingedgecomputingandcompressionforremotecufflessbloodpressuremonitoring AT dinomustefa evaluatingedgecomputingandcompressionforremotecufflessbloodpressuremonitoring AT detlefscholle evaluatingedgecomputingandcompressionforremotecufflessbloodpressuremonitoring AT hosseinfotouhi evaluatingedgecomputingandcompressionforremotecufflessbloodpressuremonitoring AT joachimdenil evaluatingedgecomputingandcompressionforremotecufflessbloodpressuremonitoring |