Abstract
Automating user behaviour is one of the most important challenges in Ambient Intelligence. Most of the proposed approaches to confront this are based on machine-learning algorithms. Using them, user routine tasks are inferred from user past actions and then automated when needed. However, these approaches present the cold-start problem, i.e. they cannot infer routine tasks until they gather sufficient user actions. We improve this problem by using a modelling approach. We propose two models to specify the routine tasks known at design time and a software infrastructure that automates them when needed by interpreting these models at runtime. Thus, we achieve to automate user routine tasks from the very beginning. Furthermore, we complement this infrastructure with a model-based API that allows these models to be modified at runtime. Thus, we provide a high-level repository for user behaviour information and an initial background to improve behaviour predictions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
ISTAG (2001) Scenarios for ambient intelligence in 2010
Weiser M (1991) The computer of the 21st century. Scient Am 265:94–104
Youngblood GM, Cook DJ, Holder LB (2005) Managing adaptive versatile environments. Pervasive Mobile Comput 1:373–403
Intille SS, Larson K, Tapia EM et al (2006) Using a live-in laboratory for ubiquitous computing research. In Proceeding of Pervasive
Mozer MC (1998) The neural network house: an environment that adapts to its inhabi-tants. In AAAI Spring Symposium on Intelligent Environments
Webb GI, Pazzani MJ, Billsus D (2001) Machine learning for user modeling user. Modeling User-Adapted Interact 11:19–29
Valiant LG (1984) A theory of the learnable. Commun ACM 27:1134–1142
Dey K (2001) Understanding and using context. Personal Ubiquitous Comput 5:4–7
Paternó F (2002) ConcurTaskTrees: an engineered approach to model-based design of interactive systems
Masuoka R, Parsia B, Labrou Y (2003) Task computingthe semantic web meets pervasive computing. In The Semantic WebISWC
Schein A, Popescul LH, Ungar MJ et al (2002) Methods and metrics for cold-start recommendations. In ACM SIGIR Conference
Billsus D, Pazzani M (1999) A hybrid user model for news story classification, in user modeling (Proceedings of the Seventh International Conference)
García-Herranz M, Haya PA, Esquivel A et al (2008) Easing the smart home: semi-automatic adaptation in perceptive environments. JUCS 14:1529–1544
Henricksen K, Indulska J, Rakotonirainy A (2006) Using context and preferences to implement self-adapting pervasive computing applications. Sofware: Pract Exp 36:11–12
Cook DJ, Das SK (2005) Smart environments: technologies, protocols, and applications. John Wily, New York
Serral E, Valderas P, Pelechano V (2010) Towards the Model Driven Development of context aware pervasive systems. Pervasive Mobile Comput 6:161–180
OSGI, http://www.osgi.org/
Neal DT, Wood W (2007) Automaticity in situ: the nature of habit in daily life. In: Bargh JA, Gollwitzer P, Morsella E (eds) Psychology of action: mechanisms of human action. Oxford University Press, London
Chen H, Finin T, Joshi A. An ontology for context-aware pervasive computing environments. Special Issue on Ontologies for Distributed Systems, KER, pp 197–207
Baldauf M, Dustdar S, Rosenberg F (2007) A survey on context-aware systems. Int J Ad Hoc Ubiquitous Comput 2:263–277
Smith MK, Welty C, McGuinness DL (2004) OWL Web ontology language guide, W3C Recommendation, http://www.w3.org/TR/owl-guide/
Shepherd A (2001) Hierarchical task analysis. Taylor & Francis, London
Eclipse Platform, www.eclipse.org
Horridge M, Bechhofer S, Noppens O (2007) Igniting the OWL 1.1 Touch Paper: The OWL API, OWLED
SPARQL Query Language (2008) http://www.w3.org/TR/rdf-sparql-query/
Sirin E, Parsia B, Grau BC et al (2007) Pellet: a practical OWL-DL reasoner. J Web Semantics 5:51–53
Pérez F, Valderas P (2009) Allowing end-users to actively participate within the elicitation of pervasive system requirements through immediate visualization. in Rev
Acknowledgements
This work has been developed with the support of MICINN under the project SESAMO TIN2007-62894 and co-financed with ERDF, in the grants’ program FPU.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media, LLC
About this paper
Cite this paper
Serral, E., Valderas, P., Pelechano, V. (2011). Improving the Cold-Start Problem in User Task Automation by Using Models at Runtime. In: Pokorny, J., et al. Information Systems Development. Springer, New York, NY. https://doi.org/10.1007/978-1-4419-9790-6_54
Download citation
DOI: https://doi.org/10.1007/978-1-4419-9790-6_54
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4419-9645-9
Online ISBN: 978-1-4419-9790-6
eBook Packages: Computer ScienceComputer Science (R0)