Title: A domain-independent methodology to analyze IoT data streams in real-time. A proof of concept implementation for anomaly detection from environmental data
Citation: INTERNATIONAL JOURNAL OF DIGITAL EARTH vol. 10 no. 1 p. 103-120
Publication Year: 2017
JRC N°: JRC102378
ISSN: 1753-8947
URI: http://www.tandfonline.com/doi/full/10.1080/17538947.2016.1209583
DOI: 10.1080/17538947.2016.1209583
Type: Articles in periodicals and books
Abstract: Pushed by the Internet of Things (IoT) paradigm modern sensor networks monitor a wide range of phenomena, in areas such as environmental monitoring, health care, industrial processes, and smart cities. These networks provide a continuous pulse of the almost infinite activities that are happening in the physical space and are thus, key enablers for a Digital Earth Nervous System. Nevertheless, the rapid processing of these sensor data streams still continues to challenge traditional data handling solutions and new approaches are being requested. We propose a generic answer to this challenge, which has the potential to support any form of distributed real-time analysis. This neutral methodology follows a brokering approach to work with different kinds of data sources and uses web-based standards to achieve interoperability. As a proof of concept, we implemented the methodology to detect anomalies in real-time and applied it to the area of environmental monitoring. The developed system is capable of detecting anomalies, generating notifications, and displaying the recent situation to the user.
JRC Directorate:Growth and Innovation

Files in This Item:
There are no files associated with this item.

Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.