Modeling Human Behavior from Simple Sensors in the Home

  • Ryan Aipperspach
  • Elliot Cohen
  • John Canny
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3968)


Pervasive sensors in the home have a variety of applications including energy minimization, activity monitoring for elders, and tutors for household tasks such as cooking. Many of the common sensors today are binary, e.g. IR motion sensors, door close sensors, and floor pressure pads. Predicting user behavior is one of the key enablers for applications. While we consider smart home data here, the general problem is one of predicting discrete human actions. Drawing on Activity Theory, the language as action principle, and speech understanding research, we argue that smoothed n-grams are very appropriate for this task. We built such a model and applied it to data gathered from 3 smart home installations. The data showed a classic Zipf or power-law distribution, similar to speech and language. We found that the predictive accuracy of the n-gram model ranges from 51% to 39%, which is significantly above the baseline for the deployments of 16, 76 and 70 sensors. While we cannot directly compare this result with other work (lack of shared data), by examination of high entropy zones in the datasets (e.g. the kitchen triangle) we argue that accuracies around 50% are best possible for this task.


Activity Recognition Smart Home Georgia Tech Zipf Distribution Simple Sensor 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Beaudin, J., Intille, S., Tapia, E.: Lessons Learned Using Ubiquitous Sensors for Data Collection in Real Homes. In: Proceedings of the ACM Conference on Human Factors in Computing Systems, CHI 2004 (2004)Google Scholar
  2. 2.
    Brumitt, B., Meyers, B., Krumm, J., Kern, A., Shafer, S.: EasyLiving: Technologies for intelligent environments. In: Thomas, P., Gellersen, H.-W. (eds.) HUC 2000. LNCS, vol. 1927, pp. 12–29. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  3. 3.
    Burke, K.: Language as Symbolic Action. University of California Press (1966)Google Scholar
  4. 4.
    Intel Corporation: Digital Home, Technology and Research at Intel,
  5. 5.
    Jelinek, F.: Statistical Methods for Speech Recognition, p. 58. MIT Press, Cambridge, Massachusetts (1997)Google Scholar
  6. 6.
    Katz, S.M.: Estimation of Probabilities from Sparse Data for the Language Model Component of a Speech Recogniser. IEEE Transactions on Acoustic, Speech and Signal Processing 35(3), 400–401 (1987)CrossRefGoogle Scholar
  7. 7.
    Liao, L., Fox, D., Kautz, H.: Learning and Inferring Transportation Routines. In: Proceedings of AAAI 2004 (2004)Google Scholar
  8. 8.
    Mozer, M.: Lessons from and Adaptive House. In: Cook, D., Das, R. (eds.) Smart Environments: Technologies, protocols, and applications, pp. 273–294. J. Wiley and Sons, Hoboken, NJ (2005)Google Scholar
  9. 9.
    Philipose, M., et al.: Inferring Activities from Interactions with Objects. In: Proceedings of the Conference on Pervasive Computing, October 2004, pp. 50–57 (2004)Google Scholar
  10. 10.
    Rao, S., Cook, D.J.: Identifying Tasks and Predicting Actions in Smart Homes using Unlabeled Data. In: Proceedings of the Machine Learning Workshop on The Continuum from Labeled to Unlabeled Data (2003)Google Scholar
  11. 11.
    Roukos, S.: Language Representation. In: Cole, R.A., et al. (eds.) Survey of the State of the Art in Human Language Technology, Center for Spoken Language Understanding CSLU, Carnegie Mellon University (1995)Google Scholar
  12. 12.
    Rowan, J.: Digital Family Portrait project,
  13. 13.
    Rowan, J., Mynatt, E.D.: Digital family portraits: Providing peace of mind for extended family members. In: Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 2001), pp. 333–340. ACM Press, Seattle, Washington (2001)Google Scholar
  14. 14.
    Roy, A., et al.: Location Aware Resource Management in Smart Homes. In: Proceedings of the Conference on Pervasive Computing (2003)Google Scholar
  15. 15.
    Shannon, C.E.: A Mathematical Theory of Communication. The Bell System Technical Journal 27, 379–423 (1948)MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Simon, H.A.: On a class of skew distribution functions. Biometrika 42, 425–440 (1955)MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Tapia, E.M., Intille, S.S., Larson, K.: Activity recognition in the home using simple and ubiquitous sensors. In: Ferscha, A., Mattern, F. (eds.) PERVASIVE 2004. LNCS, vol. 3001, pp. 158–175. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  18. 18.
    Vygotsky, L.S.: Mind in Society: The development of higher psychological processes. Cole, M., John-Steiner, V., Scribner, S., Souberman, E. (eds.) Harvard University Press (1978)Google Scholar
  19. 19.
    Wertsch, J.: Mind As Action. Oxford University Press, Oxford (1998)Google Scholar
  20. 20.
    Willis, J.C., Yule, G.U.: Some statistics of evolution and geographical distribution in plants and animals, and their significance. Nature 109, 177–179 (1922)CrossRefGoogle Scholar
  21. 21.
    Wilson, D.H., Atkeson, C.G.: Simultaneous Tracking and Activity Recognition (STAR) Using Many Anonymous, Binary Sensors. In: Gellersen, H.-W., Want, R., Schmidt, A. (eds.) PERVASIVE 2005. LNCS, vol. 3468, pp. 62–79. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  22. 22.
    Young, S., et al.: The HTK Book, Microsoft Corporation and Cambridge University, 3.2.1 edition (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ryan Aipperspach
    • 1
  • Elliot Cohen
    • 1
  • John Canny
    • 1
  1. 1.Berkeley Institute of DesignUniversity of CaliforniaBerkeleyUSA

Personalised recommendations