COMEC: Computation Offloading for Video-based Heart Rate Detection APP in Mobile Edge Computing

Medical data is invaluable in medical diagnosis. With the recent advance in Internet of Things (IoT) and non-invasive sensing, massive medical data can be gathered in real-time but how to process them efficiently becomes a big challenge for e-Health applications. In this demo paper, we investigate the idea of employing Mobile Edge Computing (MEC) which can provide computing resources close to the end devices with a variety of computation offloading models to facilitate real-time medical data processing. To evaluate this idea and find out which computation offloading model can achieve the best performance, we implement COMEC where a video-based heart rate detection APP is running in a MEC environment based on Open Air Interface (OAI). Experimental results have shown that the best performance is achieved under multi-layer offloading model where both the edge server and the cloud server are employed.