IoT Analytics

Analytics @ the Edge

Bringing analytics and intelligence to the edge, where smart things reside

AGT’s edge analytics lab introduces advances in analytics, such us behavior learning, anomaly detection, pattern learning and preprocessing close to the edge, or to the field, where the things we monitor and manage reside. By operating at the edge, we are able to limit the amount of time between detection and reaction for a number of applicable domains.

The number of smart things is growing exponentially. By 2020, tens of billions of things will be deployed worldwide, collecting a wealth of diverse data. Traditional computing models collect in-field data and then transmit it to a central data center where analytics are applied to it—but this is no longer a sustainable model. A new approach is needed to transform enormous amounts of collected data into meaningful information.

AGT’s edge analytics lab is developing new technologies that will enable the deployment of complex analytics in smart objects where real events are happening—on the edge.

AGT_Web_Analytics at the edge_07Oct2014

Our approach uses the processing power of smart things to create a distributed intelligence net, and with that, minimize the elapsed time between detection and reaction. We transmit only the analyzed information—not the raw data—thereby ensuring the end-to-end security and privacy of the system. Such analytics can be deployed in cameras, gateways and other edge devices.

Examples for edge analytics include face detection and recognition, understanding the behaviors of people and other objects in complex environments, optimizing smart grids and bringing self-consciousness to devices.





Share this: