Advertisement

Confidence Estimation of the State Predictor Method

  • Jan Petzold
  • Faruk Bagci
  • Wolfgang Trumler
  • Theo Ungerer
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3295)

Abstract

Pervasive resp. ubiquitous systems use context information to adapt appliance behavior to human needs. Even more convenience is reached if the appliance foresees the user’s desires. By means of context prediction systems get ready for future human activities and can act proactively.

Predictions, however, are never 100% correct. In case of unreliable prediction results it is sometimes better to make no prediction instead of a wrong prediction. In this paper we propose three confidence estimation methods and apply them to our State Predictor Method. The confidence of a prediction is computed dynamically and predictions may only be done if the confidence exceeds a given barrier. Our evaluations are based on the Augsburg Indoor Location Tracking Benchmarks and show that the prediction accuracy with confidence estimation may rise by the factor 1.95 over the prediction method without confidence estimation. With confidence estimation a prediction accuracy is reached up to 90%.

Keywords

Prediction Accuracy Correct Prediction Ubiquitous Computing Test Person Partial Match 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ashbrook, D., Starner, T.: Using GPS to learn significant locations and predict movement across multiple users. Personal and Ubiquitous Computing 7(5), 275–286 (2003)CrossRefGoogle Scholar
  2. 2.
    Grunwald, D., Klauser, A., Manne, S., Pleszkun, A.: Confidence Estimation for Speculation Control. In: Proceedings of the 29th Annual International Symposium on Computer Architecture, Barcelona, Spain, June-July 1998, pp. 122–131 (1998)Google Scholar
  3. 3.
    Jacobsen, E., Rotenberg, E., Smith, J.E.: Assigning Confidence to Conditional Branch Predictions. In: Proceedings of the 29th Annual International Symposium on Microarchitecture, Paris, France, December 1996, pp. 142–152 (1996)Google Scholar
  4. 4.
    Mozer, M.C.: The Neural Network House: An Environment that Adapts to its Inhabitants. In: AAAI Spring Symposium on Intelligent Environments, Menlo Park, CA, USA, pp. 110–114 (1998)Google Scholar
  5. 5.
    Patterson, D.J., Liao, L., Fox, D., Kautz, H.: Inferring High-Level Behavior from Low-Level Sensors. In: 5th International Conference on Ubiquitous Computing, Seattle, WA, USA, pp. 73–89 (2003)Google Scholar
  6. 6.
    Petzold, J.: Augsburg Indoor Location Tracking Benchmarks. Technical Report 2004-9, Institute of Computer Science, University of Augsburg, Germany (February 2004), http://www.informatik.uni-augsburg.de/skripts/techreports/
  7. 7.
    Petzold, J., Bagci, F., Trumler, W., Ungerer, T.: Context Prediction Based on Branch Prediction Methods. Technical Report 2003-14, Institute of Computer Science, University of Augsburg, Germany (July 2003), http://www.informatik.uniaugsburg.de/skripts/techreports/
  8. 8.
    Petzold, J., Bagci, F., Trumler, W., Ungerer, T.: Global and Local Context Prediction. In: Artificial Intelligence in Mobile Systems 2003 (AIMS 2003), Seattle, WA, USA (October 2003)Google Scholar
  9. 9.
    Petzold, J., Bagci, F., Trumler, W., Ungerer, T.: The State Predictor Method for Context Prediction. In: Adjunct Proceedings Fifth International Conference on Ubiquitous Computing, Seattle, WA, USA (October 2003)Google Scholar
  10. 10.
    Petzold, J., Bagci, F., Trumler, W., Ungerer, T., Vintan, L.: Global State Context Prediction Techniques Applied to a Smart Office Building. In: The Communication Networks and Distributed Systems Modeling and Simulation Conference, San Diego, CA, USA (January 2004)Google Scholar
  11. 11.
    Smith, J.E.: A Study of Branch Prediction Strategies. In: Proceedings of the 8th Annual Symposium on Computer Architecture, Minneapolis, MI, USA, May 1981, pp. 135–147 (1981)Google Scholar
  12. 12.
    Trumler, W., Bagci, F., Petzold, J., Ungerer, T.: Smart Doorplate. In: First International Conference on Appliance Design (1AD), Bristol, GB (May 2003); Reprinted in Pers Ubiquit Comput 7, 221-226 (2003)Google Scholar
  13. 13.
    Tyson, G., Lick, K., Farrens, M.: Limited Dual Path Execution. Technical Report CSE-TR 346-97, University of Michigan (1997)Google Scholar
  14. 14.
    van Laerhoven, K., Aidoo, K.A., Lowette, S.: Real-time Analysis of Data from Many Sensors with Neural Networks. In: Proceedings of the International Symposium on Wearable Computers (ISWC 2001), Zurich, Switzerland (October 2001)Google Scholar
  15. 15.
    van Laerhoven, K., Cakmakci, O.: What Shall We Teach Our Pants? In: Proceedings of the 4th International Symposium on Wearable Computers (ISWC 2000), Atlanta, GA, USA, pp. 77–83 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Jan Petzold
    • 1
  • Faruk Bagci
    • 1
  • Wolfgang Trumler
    • 1
  • Theo Ungerer
    • 1
  1. 1.Institute of Computer ScienceUniversity of AugsburgAugsburgGermany

Personalised recommendations