Ulster University Logo

Ulster Institutional Repository

Knowledge Networks for Pervasive Services

Biomedical Sciences Research Institute Computer Science Research Institute Environmental Sciences Research Institute Nanotechnology & Advanced Materials Research Institute

Bicocchi, Nicola, Castelli, G, Mamei, Marco, Rosi, A, Zambonelli, Franco, Baumgarten, Matthias and Mulvenna, Maurice (2009) Knowledge Networks for Pervasive Services. In: Proceedings ACM International Conference on Pervasive Services. IEEE Computer Society Conference Publishing Services, pp. 103-112. ISBN 978-1-60558-644-1 [Book section]

[img]
Preview
PDF
1559Kb

DOI: 10.1145/1568199.1568215

Abstract

Technologies to pervasively acquire information about the physical and social worlds – as needed by services to achieve context-awareness – are becoming increasingly available. Paradoxically, the risk is to make pervasive services overwhelmed by growing amounts of contextual data, and unable to properly exploit them. This calls for specific approaches to automatically organize and aggregate such data before delivering it to services. Contextual data items should form a sort of self-organized ecology within which they autonomously link and combine with each other into sorts of “knowledge networks”. This can produce compact and easy-to-be-managed higher-level knowledge about situations occurring in the environment, and eventually can make services able to easily acquire “situation-awareness”. In this paper, after having framed the key concepts and motivations underlying “situation-awareness” and our “knowledge networks” approach, we present the design and implementation of a “knowledge networks” prototype, intended as a tool to support self-organization and self-aggregation of contextual data item to facilitate their exploitation by pervasive services. A representative case study in the area of adaptive pervasive advertisement is introduced to clarify the concepts expressed, to exemplify the actual functioning of the toolkit and of some specific algorithms integrated within it, as well as to evaluate its effectiveness.

Item Type:Book section
Faculties and Schools:Faculty of Computing & Engineering
Faculty of Computing & Engineering > School of Computing and Mathematics
ID Code:11065
Deposited By:Professor Maurice Mulvenna
Deposited On:22 Mar 2010 16:32
Last Modified:22 Mar 2010 16:32

Repository Staff Only: item control page