Geoedge: A Real-time Analytics Framework for Geospatial Applications

Abstract

In many real-world applications, data looses its value if its not analyzed in real-time. Examples include natural disasters, crop disease identification and bioterrorism, traffic monitoring, monitoring human activities and public places, gas pipeline monitoring for leaks. Edge computing refers to pushing computing power to the edge of the network or bringing it closer to the sensors. We envision that an integrated framework (sensors + edge computers + analytics) allows near realtime analytics at the edge, which is critical for first responders to national security agencies alike. In addition to the generation of real-time actionable knowledge, edge computing allows compressing/reducing big geospatial data that need to be transmitted to centralized cloud or data centers. In this study, we present the vision behind geoEdge, and show feasibility results using feature extraction and unsupervised learning on an edge computing device.