GeoSensor: On-line Scalable Change and Event Detection over Big Data

Giorgos Argyriou, George Papadakis, George Stamoulis, Efi Karra Taniskidou, Nikiforos Pittaras, George Giannakopoulos, Sergio Albani, Michele Lazzarini, Emanuele Angiuli, Anca Popescu, Argyros Argyridis, Manolis Koubarakis

Abstract: GeoSensor is a novel system that enriches change detection over satellite images with event detection over news items and social media content. GeoSensor faces the major challenges of Big Data: volume (a single satellite image may be a few GBs), variety (its data sources include two different types of satellite images and various types of user-generated content) and veracity, as the accuracy of the end result is crucial for the usefulness of our system. To overcome these three challenges, while offering on-line functionality, GeoSensor comprises a complex architecture that is based on the open-source platform developed in the H2020 project Big Data Europe. Through the presented demonstration, both the effectiveness and the efficiency of GeoSensor's functionalities are highlighted.