Fog-Assisted wIoT: A Smart Fog Gateway for End-to-End Analytics in\n Wearable Internet of Things

Abstract

Today, wearable internet-of-things (wIoT) devices continuously flood the\ncloud data centers at an enormous rate. This increases a demand to deploy an\nedge infrastructure for computing, intelligence, and storage close to the\nusers. The emerging paradigm of fog computing could play an important role to\nmake wIoT more efficient and affordable. Fog computing is known as the cloud on\nthe ground. This paper presents an end-to-end architecture that performs data\nconditioning and intelligent filtering for generating smart analytics from\nwearable data. In wIoT, wearable sensor devices serve on one end while the\ncloud backend offers services on the other end. We developed a prototype of\nsmart fog gateway (a middle layer) using Intel Edison and Raspberry Pi. We\ndiscussed the role of the smart fog gateway in orchestrating the process of\ndata conditioning, intelligent filtering, smart analytics, and selective\ntransfer to the cloud for long-term storage and temporal variability\nmonitoring. We benchmarked the performance of developed prototypes on\nreal-world data from smart e-textile gloves. Results demonstrated the usability\nand potential of proposed architecture for converting the real-world data into\nuseful analytics while making use of knowledge-based models. In this way, the\nsmart fog gateway enhances the end-to-end interaction between wearables (sensor\ndevices) and the cloud.\n