Sandra Haseloff

An Alignment Approach for Context Prediction Tasks in UbiComp Environments

The authors detail the alignment prediction approach-a time-series-estimation technique applicable to both numeric and nonnumeric data-and compare it to four other prediction approaches to determine context-prediction accuracy in ubiquitous computing environments.

Investigation of Context Prediction Accuracy for Different Context Abstraction Levels

Context prediction is the task of inferring information about the progression of an observed context time series based on its previous behaviour. Prediction methods can be applied at several abstraction levels in the context processing chain. In a theoretical analysis as well as by means of experiments we show that the nature of the input data, the quality of the output, and finally the flow of processing operations used to make a prediction, are correlated. A comprehensive discussion of basic concepts in context prediction domains and a study on the effects of the context abstraction level on the context prediction accuracy in context prediction scenarios is provided. We develop a set of formulae that link scenario-dependent parameters to a probability for the context prediction accuracy. It is demonstrated that the results achieved in our theoretical analysis can also be confirmed in simulations as well as in experimental studies.

A Novel Approach to Context Prediction in UBICOMP Environments

The ability to predict future contexts significantly expands the possibilities of context-aware computing applications. However, an incorrect prediction may also mislead the application and may result in inappropriate application behaviour. We study influences on the prediction accuracy and propose a novel approach to context prediction in ubiquitous computing environments. In our paper we introduce a context time series prediction algorithm based on local alignment techniques. Our approach has the potential to improve the prediction accuracy since it explores the observed context history in more detail than current algorithms. In conclusion, we present simulation results that support our studies

An Approach to Autonomic Deployment Decision Making

Adding autonomicity to computing systems seems to be a promising way to deal with the problem of increasing system complexity. One step along the way to self-managing computing systems --- especially with regard to distributed, modularized, service based environments --- is to solve the problem of how to autonomically decide in a most useful and resource efficient way which alternative to choose in order to deploy a service. Deploying a service means, to either copy or move it from a source to a destination device or to use it remotely. In this paper we motivate the domain of autonomic service deployment and present an approach for deployment decision making (DDM). We explain all steps of the deployment decision making process and assemble them into an algorithm accordingly. Furthermore, we define all necessary components of DDM and enumerate a set of research questions which we address in order to fully explore the concerned domain. An experiment illustrates the potential of the presented approach.

Minimising the Context Prediction Error

Context prediction mechanisms proactively provide information on future contexts. Due to this knowledge novel applications become possible that provide services with proactive knowledge to users. The most serious problem of context prediction mechanisms lies in a basic property of prediction itself. A prediction is always a guess. Since erroneous predictions may cause the application to behave insufficiently, prediction errors have to be minimised. The accuracy of prediction is seriously affected by the reliability of the context data that is utilised by the method. We study two paradigms for context prediction and compare their potential prediction accuracy. We show that the designer of context prediction architectures has to choose wisely as to which prediction paradigm to follow in order to maximise the accuracy of the whole architecture. We also introduce a simulation environment and present simulation results that support the gained insights regarding context prediction.

A study on context prediction and adaptivity

Chair for communication Technology University of Kassel Context prediction is closely related to the learning of typical user context patterns. A decrease in the learning accuracy likely reduces the context prediction quality. We study the impact of context pre-processing on the learning efficiency of context prediction schemes. In particular, influences of the context data abstraction level on the learning accuracy are analysed. This discussion is accompanied by simulations as on sampled as well as synthetic context data. In the simulation an alignment prediction algorithm is applied to low-level GPS data and to high-level location data.

The Impact of the Context Interpretation Error on the Context Prediction Accuracy

We study the impact of the context interpretation error on the context prediction accuracy. Benefits and drawbacks of current context prediction schemes are analysed and opposed to a contemporary alternative. We propose a novel context prediction scheme that has the potential to significantly improve the context prediction accuracy. The impact of the context interpretation error on the context prediction accuracy is further analysed in simulations inspired by our analytical considerations.

Context awareness in I-centric systems - Dynamic Context Learning Using a Rule-Based Approach -

Capturing contextual information, especially higher-level contexts, enables systems to understand and predict the behaviour of a mobile user. This kind of information is mostly implicit, abstracting a complex state of a situation, and can only partly be captured by sensors. Higher-level context has the potential to make user applications simpler and more intuitive. However, composing higher-level contexts from explicit, atomic contexts requires complex procedures to be used and uncertainty due to inconsistent sensor readings and incomplete information to be reduced. In this paper, we introduce a new approach that assists application developers to take higher-level contexts into account without the need to know the details of atomic contexts. To demonstrate our approach, we will introduce the Context-Aware E-Pad (CAEP) we have designed and implemented.