Abstract
Contact-less vital-sign monitoring is enabling in situations where traditional contact-based vital sign monitoring is prohibitive, such as neonatal and burn care where electrodes and attachments risk patient infection or complications. To make vital-sign monitoring available for the consumer market, these algorithms shall use COTS cameras and run on COTS systems. In this paper, we report upon our experience in improving the performance of a contact-less respiration algorithm on a resource-constrained COTS multi-core system, in our case a Raspberry Pi 3 running Linux. In particular, we describe how, by using a state-of-research tool to visualize the behavior of a system, performance bottlenecks and issues of the system are identified and resolved. The resulting improvements are an increase of the CPU utilization from 72% to almost 94% and an increase of the throughput of the algorithm by more than 45%.
Original language | English |
---|---|
Title of host publication | IEEE 45th Annual Conference on the Industrial Electronics Society (IECON) |
Place of Publication | Piscataway |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 3057-3062 |
Number of pages | 6 |
ISBN (Electronic) | 978-1-7281-4878-6 |
DOIs | |
Publication status | Published - Oct 2019 |
Event | 45th Annual Conference of the IEEE Industrial Electronics Society - Lisbon, Portugal Duration: 14 Oct 2019 → 17 Oct 2019 |
Conference
Conference | 45th Annual Conference of the IEEE Industrial Electronics Society |
---|---|
Country/Territory | Portugal |
City | Lisbon |
Period | 14/10/19 → 17/10/19 |