PREDICTION OF CONTEXT TIME SERIES

Context awareness is a key feature of modern computing applications, allowing application behaviour to be adapted to context. The power and quality of context-aware applications can significantly be increased by not only considering past and present contexts for adaptation, but by also predicting and reacting to future contexts. This paper deals with fundamental challenges of context prediction. After an introduction to context prediction and a clarification of the basic terms associated with it, the paper proposes solutions concerning prediction algorithms and describes an architecture for context-aware computing, including context prediction, we have developed. The findings described in the paper are illustrated and verified by simulations using different types of context data and different prediction algorithms.

[1]  Bill N. Schilit,et al.  Disseminating active map information to mobile hosts , 1994, IEEE Network.

[2]  Stephan Sigg,et al.  Minimising the Context Prediction Error , 2007, 2007 IEEE 65th Vehicular Technology Conference - VTC2007-Spring.

[3]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[4]  Alexander De Luca,et al.  Analysis of Built-in Mobile Phone Sensors for Supporting Interactions with the Real World , 2005, PERMID.

[5]  Richard A. Davis,et al.  Introduction to time series and forecasting , 1998 .

[6]  Stephan Sigg,et al.  The Impact of the Context Interpretation Error on the Context Prediction Accuracy , 2006, 2006 3rd Annual International Conference on Mobile and Ubiquitous Systems - Workshops.

[7]  Michael C. Mozer,et al.  Neural net architectures for temporal sequence processing , 2007 .

[8]  Mika Raento,et al.  Adaptive On-Device Location Recognition , 2004, Pervasive.

[9]  S. Martin,et al.  Using context prediction for self-management in ubiquitous computing environments , 2006, CCNC 2006. 2006 3rd IEEE Consumer Communications and Networking Conference, 2006..

[10]  Rene Mayrhofer,et al.  An architecture for context prediction , 2004 .

[11]  Stephan Sigg,et al.  The Quick Step to Foxtrot , 2006 .

[12]  Gregory D. Abowd,et al.  Providing architectural support for building context-aware applications , 2000 .

[13]  Petteri Nurmi,et al.  Enabling proactiveness through context prediction , 2005 .

[14]  Alois Ferscha,et al.  Pervasive Computing , 2004, Lecture Notes in Computer Science.

[15]  Eric Horvitz,et al.  Coordinates: Probabilistic Forecasting of Presence and Availability , 2002, UAI.

[16]  Peter Brown.  Context-awareness: some compelling applications , 2000 .

[17]  Kishan G. Mehrotra,et al.  Elements of artificial neural networks , 1996 .

[18]  Nicholas R. Jennings,et al.  Intelligent agents: theory and practice , 1995, The Knowledge Engineering Review.

[19]  Se-Hak Chun,et al.  Impact of momentum bias on forecasting through knowledge discovery techniques in the foreign exchange market , 2003, Expert Syst. Appl..

[20]  Stephan Sigg,et al.  A Novel Approach to Context Prediction in UBICOMP Environments , 2006, 2006 IEEE 17th International Symposium on Personal, Indoor and Mobile Radio Communications.

[21]  Thad Starner,et al.  Learning Significant Locations and Predicting User Movement with GPS , 2002, Proceedings. Sixth International Symposium on Wearable Computers,.

[22]  Michael C. Mozer,et al.  The Neural Network House: An Environment that Adapts to its Inhabitants , 1998 .

[23]  Brian D. Davison,et al.  Predicting Sequences of User Actions , 1998 .

[24]  Jani Mäntyjärvi,et al.  Sensor-based context recognition for mobile applications , 2003 .

[25]  Se-Hak Chun,et al.  Data mining for financial prediction and trading: application to single and multiple markets , 2004, Expert Syst. Appl..

[26]  Alois Ferscha,et al.  Recognizing and Predicting Context by Learning from User Behavior 1 , 2003 .

[27]  P. A. Blight.  The Analysis of Time Series: An Introduction , 1991 .