PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Using semantic annotation for knowledge extraction from geographical distributed and heterogeneous sensor data
Alexandra Moraru, Carolina Fortuna and Dunja Mladenić
In: 16th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 25 - 28 July 2010, Washington, DC, USA.

Abstract

Using semantic technologies for enriching sensor data description in scalable and heterogeneous sensor network are intended as a solution for better interoperability and easier maintainability. Through semantic annotations it is possible to provide context for sensor networks, which will improve knowledge extractions from sensor data streams and will facilitate reasoning capabilities. We propose an architecture for a system able to automatically annotate sensors descriptions, as provided by the publishers, with semantic concepts. The annotated sensor data become more meaningful and machine understandable, enabling better analysis and processing from heterogeneous streams of data. Based on the system proposed, we provide illustrative examples for demonstrating the improvements that semantic context brings and we discuss a real-world scenario of Participatory Sensing.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Information Retrieval & Textual Information Access
ID Code:7482
Deposited By:Jan Rupnik
Deposited On:17 March 2011