Sensing on The Edge: Smartening up Sensors

Abstract

Between the sensors gathering data and the cloud computing services processing data, there is an array of new technologies emerging. These technologies allow for complex processing and storage, closer to where data is collected – right at the edge. While Cloud Computing has received tremendous attention from both academia and industry for connecting many devices to the internet, the ever-growing number of IoT and mobile devices has created the demand for lower network latency and processing capability closer to the users. Edge computing provides an opportunity for wearable devices to access more resources without violating the constraints on weight, size, and sensing capabilities. It involves placing computing resources closer to where data originates (i.e. heart rate monitor, pumps, step counter, or other sensors) – or at the “edge.” Furthermore, edge computing provides many required on-device processing capabilities, which can then help in protecting users' private data as raw personal data (such as images and videos) don't need to be shared remotely. These computing resources may be located in the devices themselves or in hyper-local, small-scale data centres. This talk will look at the potential of edge computing for multimodal sensing while protecting users' privacy and will showcase several examples from recent work at the Smart Sensing Lab in this area.