ABSTRACT
Predicting the future actions of individuals from geospatial data has the potential to provide a basis for tailored services. This work presents the Predictive Context Tree (PCT), a new hierarchical classifier based on the Context Tree summary model [8]. The PCT is capable of predicting the future contexts and locations of individuals to provide a basis for understanding not only where a user will be, but also what type of activity they will be performing. Through a comparison to established techniques, this paper demonstrates the applicability of the PCT by showing increased accuracies for location prediction, and increased utility through context prediction.
- S. Akoush and A. Sameh. Bayesian Learning of Neural Networks for Mobile User Position Prediction. In Proc. Euro-Par, pages 1234--1239, 2007.Google Scholar
- D. Ashbrook and T. Starner. Using GPS to Learn Significant Locations and Predict Movement Across Multiple Users. Pers. Ubiquit. Comput., 7(5):275--286, 2003. Google ScholarDigital Library
- T. Bao, H. Cao, E. Chen, J. Tian, and H. Xiong. An Unsupervised Approach to Modelling Personalized Contexts of Mobile Users. Knowl. Inf. Syst., 31(2):345--370, 2011. Google ScholarDigital Library
- N. Bhyri, G. V. Kidiyoor, S. K. Varun, S. Kalambur, D. Sitaram, and C. Kollengode. Predicting the Next Move. In Proc. ICACCI, pages 2359--2365, 2015.Google Scholar
- P. Bilurkar, N. Rao, G. Krishna, and R. Jain. Application of Neural Network Techniques for Location Predication in Mobile Networking. In Proc. ICONIP, pages 2157--2161, 2002. Google ScholarCross Ref
- R. Hariharan and K. Toyama. Project Lachesis: Parsing and Modeling Location Histories. In Proc. GI-Science, pages 106--124, 2004. Google ScholarCross Ref
- A. Thomason, N. Griffiths, and V. Sanchez. Parameter Optimisation for Location Extraction and Prediction Applications. In Proc. IEEE PICom, pages 2173--2180, 2015. Google ScholarCross Ref
- A. Thomason, N. Griffiths, and V. Sanchez. Context Trees: Augmenting Geospatial Trajectories with Context. ACM T. Inform. Syst. (In Press), 2016. Google ScholarDigital Library
- J. Wang and B. Prabhala. Periodicity Based Next Place Prediction. In Proc. MDC Workshop, Pervasive, 2012.Google Scholar
- Y. Zheng. Trajectory Data Mining: An Overview. ACM T. Intell. Syst. Technol., 6(3):1: 1--1:41, 2015.Google ScholarDigital Library
Index Terms
- Predicting interactions and contexts with context trees
Recommendations
Extending Context Spaces Theory by Predicting Run-Time Context
NEW2AN '09 and ruSMART '09: Proceedings of the 9th International Conference on Smart Spaces and Next Generation Wired/Wireless Networking and Second Conference on Smart SpacesContext awareness and prediction are important for pervasive computing systems. The recently developed theory of context spaces addresses problems related to sensor data uncertainty and high-level situation reasoning. This paper proposes and discusses ...
Enhancing alignment based context prediction by using multiple context sources: experiment and analysis
CONTEXT'11: Proceedings of the 7th international and interdisciplinary conference on Modeling and using contextContext aware applications are reactive, they adapt to an entity's context when the context has changed. In order to become proactive and act before the context actually has changed future contexts have to be predicted. This will enable functionalities ...
Beyond context-awareness: context prediction in an industrial application
UbiComp '10 Adjunct: Proceedings of the 12th ACM international conference adjunct papers on Ubiquitous computing - AdjunctIn this paper, we discuss the benefits of context prediction for an industrial application in open cast mining. The goal of context prediction is not only to recognize the current context, but also to predict the future context. Context prediction ...
Comments