iMuseum: A scalable context-aware intelligent museum system

A context-aware intelligent museum system can capture the information of the visitor and surroundings, recognize the visitor's purpose, and then assist visiting in the museum. It is noted that not only the devices in the museum cannot be easily predicted, but the available applications may change over time. Therefore infinite entities and dynamic context knowledge are necessarily managed by a system with good scalability. This paper proposes a scalable context-aware intelligent museum system called iMuseum. The system is based on a new context model, 2*3CM (2 Sets and 3 Layers Context Model) that integrates the advantages of ontology-based model and hierarchical model. The iMuseum system has two novel features: distributed acquisition of context knowledge on demand and centralized sharing of context knowledge with double-repository. With the two mechanisms, the system is able to support defining new concepts, synthesizing high-level context, and querying application-oriented context at run-time. As a result, the third parties can independently develop their own applications or context providers, and also add or end them optionally. The preliminary experimental results have demonstrated the scalability and acceptance of the system.

[1]  Diego Calvanese,et al.  The Description Logic Handbook: Theory, Implementation, and Applications , 2003, Description Logic Handbook.

[2]  Mirjana Spasojevic,et al.  Rememberer: A Tool for Capturing Museum Visits , 2002, UbiComp.

[3]  Tgk Toon Calders,et al.  A Framework for Guiding the Museum Tour Personalization , 2007 .

[4]  Andreas Schmidt.  A Layered Model for User Context Management with Controlled Aging and Imperfection Handling , 2005, MRC@IJCAI.

[5]  Lora Aroyo,et al.  Personalized Museum Experience: The Rijksmuseum Use Case , 2007 .

[6]  Liz Sonenberg,et al.  Using multimedia content in intelligent mobile services , 2004, WebMedia and LA-Web, 2004. Proceedings.

[7]  Xingshe Zhou,et al.  TV Program Recommendation for Multiple Viewers Based on user Profile Merging , 2006, User Modeling and User-Adapted Interaction.

[8]  Matthias Baldauf,et al.  A survey on context-aware systems , 2007, Int. J. Ad Hoc Ubiquitous Comput..

[9]  Xingshe Zhou,et al.  User Preference Learning for Multimedia Personalization in Pervasive Computing Environment , 2005, KES.

[10]  Robert Cole,et al.  Computer Communications , 1982, Springer New York.

[11]  M. Zancanaro,et al.  Group Communication for Real-time Role Coordination and Ambient Intelligence , 2003 .

[12]  Ian Horrocks,et al.  OWL Web Ontology Language Reference-W3C Recommen-dation , 2004 .

[14]  Lora Aroyo,et al.  Determining user interests about museum collections , 2006, WWW '06.

[15]  Xingshe Zhou,et al.  Supporting Context-Aware Media Recommendations for Smart Phones , 2006, IEEE Pervasive Computing.

[16]  D. Marples,et al.  The Open Services Gateway Initiative: an introductory overview , 2001, IEEE Commun. Mag..

[17]  L. Stein,et al.  OWL Web Ontology Language - Reference , 2004 .

[18]  Javier Jaén Martínez,et al.  MoMo: enabling hybrid museums , 2005, IEE Proc. Softw..

[19]  H. Lan,et al.  SWRL : A semantic Web rule language combining OWL and ruleML , 2004 .

[20]  Boi Faltings,et al.  Inferring User's Preferences using Ontologies , 2006, AAAI.

[21]  Shing-Chi Cheung,et al.  Inconsistency detection and resolution for context-aware middleware support , 2005, ESEC/FSE-13.

[22]  Mahadev Satyanarayanan,et al.  Pervasive computing: vision and challenges , 2001, IEEE Wirel. Commun..

[23]  Tao Gu,et al.  Ontology based context modeling and reasoning using OWL , 2004, IEEE Annual Conference on Pervasive Computing and Communications Workshops, 2004. Proceedings of the Second.