Advertisement

Human Activity Recognition Using Place-Based Decision Fusion in Smart Homes

  • Julien CuminEmail author
  • Grégoire Lefebvre
  • Fano Ramparany
  • James L. Crowley
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10257)

Abstract

This paper describes the results of experiments where information about places is used in the recognition of activities in the home. We explore the use of place-specific activity recognition trained with supervised learning, coupled with a decision fusion step, for recognition of activities in the Opportunity dataset. Our experiments show that using place information to control recognition can substantially improve both the error rates and the computation cost of activity recognition compared to classical approaches where all sensors are used and all activities are possible. The use of place information for controlling recognition gives an F1 classification score of \(92.70{\%} \pm 1.26{\%}\), requiring on average only 73 ms of computing time per instance of activity. These experiments demonstrate that organizing activity recognition with place-based context models can provide a scalable approach for building context-aware services based on activity recognition in smart home environments.

References

  1. 1.
    Allègre, W., Burger, T., Berruet, P., Antoine, J.Y., et al.: Modèle de supervision d’interactions non-intrusif basé sur les ontologies. In: EGC, pp. 285–290 (2012)Google Scholar
  2. 2.
    Brdiczka, O., Crowley, J.L., Reignier, P.: Learning situation models in a smart home. IEEE Trans. Syst. Man Cybern. Part B (Cybern.) 39(1), 56–63 (2009)CrossRefGoogle Scholar
  3. 3.
    Chen, L., Nugent, C.D., Wang, H.: A knowledge-driven approach to activity recognition in smart homes. IEEE Trans. Knowl. Data Eng. 24(6), 961–974 (2012)CrossRefGoogle Scholar
  4. 4.
    Cook, D.J., Krishnan, N.C., Rashidi, P.: Activity discovery and activity recognition: a new partnership. IEEE Trans. Cybern. 43(3), 820–828 (2013)CrossRefGoogle Scholar
  5. 5.
    Crowley, J.L., Coutaz, J.: An ecological view of smart home technologies. In: Ruyter, B., Kameas, A., Chatzimisios, P., Mavrommati, I. (eds.) AmI 2015. LNCS, vol. 9425, pp. 1–16. Springer, Cham (2015). doi: 10.1007/978-3-319-26005-1_1 CrossRefGoogle Scholar
  6. 6.
    Cumin, J., Lefebvre, G.: A priori data and a posteriori decision fusions for human action recognition. In: 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP) (2016)Google Scholar
  7. 7.
    Dey, A.K.: Understanding and using context. Pers. Ubiquit. Comput. 5(1), 4–7 (2001)CrossRefGoogle Scholar
  8. 8.
    Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The Weka data mining software: an update. ACM SIGKDD Explor. Newslett. 11(1), 10–18 (2009)CrossRefGoogle Scholar
  9. 9.
    Ordóñez, F.J., Roggen, D.: Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 16(1), 115 (2016)CrossRefGoogle Scholar
  10. 10.
    Ouchi, K., Doi, M.: A real-time living activity recognition system using off-the-shelf sensors on a mobile phone. In: Beigl, M., Christiansen, H., Roth-Berghofer, T.R., Kofod-Petersen, A., Coventry, K.R., Schmidtke, H.R. (eds.) CONTEXT 2011. LNCS (LNAI), vol. 6967, pp. 226–232. Springer, Heidelberg (2011). doi: 10.1007/978-3-642-24279-3_24 CrossRefGoogle Scholar
  11. 11.
    Roggen, D., Calatroni, A., Rossi, M., Holleczek, T., Forster, K., Troster, G., Lukowicz, P., Bannach, D., Pirkl, G., Ferscha, A., Doppler, J., Holzmann, C., Kurz, M., Holl, G., Chavarriaga, R., Sagha, H., Bayati, H., Creatura, M., Millan, J.d.R.: Collecting complex activity datasets in highly rich networked sensor environments. In: 2010 7th International Conference on Networked Sensing Systems (INSS), pp. 233–240, June 2010Google Scholar
  12. 12.
    Townsend, D., Knoefel, F., Goubran, R.: Privacy versus autonomy: a tradeoff model for smart home monitoring technologies. In: 2011 Annual International Conference of IEEE Engineering in Medicine and Biology Society, pp. 4749–4752. IEEE (2011)Google Scholar
  13. 13.
    Wolpert, D.H.: Stacked generalization. Neural Netw. 5(2), 241–259 (1992)CrossRefGoogle Scholar
  14. 14.
    Wu, C., Khalili, A.H., Aghajan, H.: Multiview activity recognition in smart homes with spatio-temporal features. In: Proceedings of 4th ACM/IEEE International Conference on Distributed Smart Cameras, pp. 142–149. ACM (2010)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Julien Cumin
    • 1
    • 2
    Email author
  • Grégoire Lefebvre
    • 1
  • Fano Ramparany
    • 1
  • James L. Crowley
    • 2
  1. 1.Orange LabsMeylanFrance
  2. 2.Laboratoire d’Informatique de Grenoble, Université Grenoble Alpes & InriaGrenobleFrance

Personalised recommendations