Context-aware systems adapt their behaviour based on the context a user is in. Since context is potentially privacy sensitive information, users should be empowered to control how much of their context they are willing to share, under what conditions and for what purpose. We propose an interactive consent mechanism that allows this. It is interactive in the sense that users are asked for consen...

Many context-aware systems have been demonstrated in lab environments; however, due to some difficulties such as the scalability and privacy issues, they are not yet practical for deployment on a large scale. This paper addresses these two issues with particular interest in user’s privacy protection and spontaneous system association. A person-centric service infrastructure is proposed together...

In this paper, the event concept is applied to support the interaction between mobile users and distributed location-aware systems. Taking a number of examples, the components of an event specification language are derived that can be used beyond the domain of location-aware systems.

This paper presents the context-aware deployment of user-assistant services in public spaces, e.g., museums. Using location-sensing systems, it detects the locations of users and deploys user-assistant services, e.g., visitor guides, at computers near to the their current locations. When users move between exhibits in a museum, it enables agents to follow users to annotate the exhibits in perso...

Limitations of sensors and the situation of a specific measurement can affect the quality of context information that is implicitly collected in pervasive environments. The lack of information about Quality of Context (QoC) can result in degraded performance of context-aware systems in pervasive environments, without knowing the actual problem. Context-aware systems can take advantage of QoC if...

Ubiquitous environments facilitate the collection of information pieces from sensors, databases, or mobile devices in order to compose the context of entities like users, places, or things. The context obtained in this way can be used to automatically adapt the behavior of services, which results in the new paradigm of context-aware services (CASs). In recent years, a lot of research has covere...

Matrix factorization has now become a dominant solution for personalized recommendation on the Social Web. To alleviate the cold start problem, previous approaches have incorporated various additional sources of information into traditional matrix factorization models. These upgraded models, however, achieve only “marginal” enhancements on the performance of personalized recommendation. Therefo...

Context-aware recommender systems try to adapt to users’ preferences across different contexts and have been proven to provide better predictive performance in a number of domains. Emotion is one of the most popular contextual variables, but few researchers have explored how emotions take effect in recommendations – especially the usage of the emotional variables other than the effectiveness al...

This article presents the iTransIT framework for building context-aware pervasive services in large-scale ambient environments. The iTransIT framework provides an architecture for conceptually integrating the independent systems underlying an ambient environment and a data model for capturing the contextual information generated by these systems. The data model is based on a hybrid approach to ...

Research in advanced context-aware systems has clearly shown a need to capture the inherent uncertainty in the physical world, especially in human behavior. Modelling approaches that employ the concept of probability, especially in combination with Bayesian methods, are promising candidates to solve the pending problems. This paper analyzes the requirements for such models in order to enable us...