Advertisement

Dynamic Real-Time Segmentation and Recognition of Activities Using a Multi-feature Windowing Approach

  • Ahmad Shahi
  • Brendon J. Woodford
  • Hanhe Lin
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10526)

Abstract

Segmenting sensor events for activity recognition has many key challenges due to its unsupervised nature, the real-time requirements necessary for on-line event detection, and the possibility of having to recognise overlapping activities. A further challenge is to achieve robustness of classification due to sub-optimal choice of window size. In this paper, we present a novel real-time recognition framework to address these problems. The proposed framework is divided into two phases: off-line modeling and on-line recognition. In the off-line phase a representation called Activity Features (AFs) are built from statistical information about the activities from annotated sensory data and a Naïve Bayesian (NB) classifier is modeled accordingly. In the on-line phase, a dynamic multi-feature windowing approach using AFs and the learnt NB classifier is introduced to segment unlabeled sensor data as well as predicting the related activity. How this on-line segmentation occurs, even in the presence of overlapping activities, diverges from many other studies. Experimental results demonstrate that our framework can outperform the state-of-the-art windowing-based approaches for activity recognition involving datasets acquired from multiple residents in smart home test-beds.

Keywords

Human activity recognition On-line stream mining Real-time Machine learning Classification 

References

  1. 1.
    Abdallah, Z.S., Gaber, M.M., Srinivasan, B., Krishnaswamy, S.: Adaptive mobile activity recognition system with evolving data streams. Neurocomputing 150, 304–317 (2015)CrossRefGoogle Scholar
  2. 2.
    Bao, L., Intille, S.S.: Activity recognition from user-annotated acceleration data. In: Ferscha, A., Mattern, F. (eds.) Pervasive 2004. LNCS, vol. 3001, pp. 1–17. Springer, Heidelberg (2004). doi: 10.1007/978-3-540-24646-6_1 CrossRefGoogle Scholar
  3. 3.
    Cook, D.J.: Learning setting-generalized activity models for smart spaces. IEEE Intell. Syst. 27(1), 32–38 (2012)CrossRefGoogle Scholar
  4. 4.
    Cook, D.J., Schmitter-Edgecombe, M.: Assessing the quality of activities in a smart environment. Methods Inf. Med. 48(5), 480–485 (2009)CrossRefGoogle Scholar
  5. 5.
    Gu, T., Wu, Z., Tao, X., Pung, H.K., Lu, J.: epsicar: an emerging patterns based approach to sequential, interleaved and concurrent activity recognition. In: IEEE International Conference on Pervasive Computing and Communications (PerCom 2009), pp. 1–9. IEEE (2009)Google Scholar
  6. 6.
    He, H., Garcia, E.A.: Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 21(9), 1263–1284 (2009)CrossRefGoogle Scholar
  7. 7.
    Huỳnh, T., Blanke, U., Schiele, B.: Scalable recognition of daily activities with wearable sensors. In: Hightower, J., Schiele, B., Strang, T. (eds.) LoCA 2007. LNCS, vol. 4718, pp. 50–67. Springer, Heidelberg (2007). doi: 10.1007/978-3-540-75160-1_4 CrossRefGoogle Scholar
  8. 8.
    Johnson, N.L., Kemp, A.W., Kotz, S.: Univariate Discrete Distributions, vol. 444. Wiley, Hoboken (2005)CrossRefMATHGoogle Scholar
  9. 9.
    Krishnan, N.C., Cook, D.J.: Activity recognition on streaming sensor data. Pervasive Mob. Comput. 10, 138–154 (2014)CrossRefGoogle Scholar
  10. 10.
    Needleman, S.B., Wunsch, C.D.: A general method applicable to the search for similarities in the amino acid sequence of two proteins. J. Mol. Biol. 48(3), 443–453 (1970)CrossRefGoogle Scholar
  11. 11.
    Nguyen, H.M., Cooper, E.W., Kamei, K.: Online learning from imbalanced data streams. In: 2011 International Conference of Soft Computing and Pattern Recognition (SoCPaR), pp. 347–352. IEEE (2011)Google Scholar
  12. 12.
    Okeyo, G., Chen, L., Wang, H., Sterritt, R.: Dynamic sensor data segmentation for real-time knowledge-driven activity recognition. Pervasive Mob. Comput. 10, 155–172 (2014)CrossRefGoogle Scholar
  13. 13.
    Peterek, T., Penhaker, M., Gajdoš, P., Dohnálek, P.: Comparison of classification algorithms for physical activity recognition. In: Abraham, A., Krömer, P., Snášel, V. (eds.) Innovations in Bio-inspired Computing and Applications. Advances in Intelligent Systems and Computing, vol. 237, pp. 123–131. Springer, Cham (2014). doi: 10.1007/978-3-319-01781-5_12 CrossRefGoogle Scholar
  14. 14.
    Preece, S.J., Goulermas, J.Y., Kenney, L.P., Howard, D., Meijer, K., Crompton, R.: Activity identification using body-mounted sensorsa review of classification techniques. Physiol. Meas. 30(4), R1–R33 (2009)CrossRefGoogle Scholar
  15. 15.
    Shahi, A., Woodford, B.J., Deng, J.D.: Event classification using adaptive cluster-based ensemble learning of streaming sensor data. In: Pfahringer, B., Renz, J. (eds.) AI 2015. LNCS, vol. 9457, pp. 505–516. Springer, Cham (2015). doi: 10.1007/978-3-319-26350-2_45 CrossRefGoogle Scholar
  16. 16.
    Sobhani, P., Viktor, H., Matwin, S.: Learning from imbalanced data using ensemble methods and cluster-based undersampling. In: Appice, A., Ceci, M., Loglisci, C., Manco, G., Masciari, E., Ras, Z.W. (eds.) NFMCP 2014. LNCS, vol. 8983, pp. 69–83. Springer, Cham (2015). doi: 10.1007/978-3-319-17876-9_5 Google Scholar
  17. 17.
    Van Kasteren, T., Noulas, A., Englebienne, G., Kröse, B.: Accurate activity recognition in a home setting. In: Proceedings of the 10th International Conference on Ubiquitous Computing, pp. 1–9. ACM (2008)Google Scholar
  18. 18.
    Wan, J., O’Grady, M.J., O’Hare, G.M.: Dynamic sensor event segmentation for real-time activity recognition in a smart home context. Personal Ubiquitous Comput. 19(2), 287–301 (2015)CrossRefGoogle Scholar
  19. 19.
    Wiss, S., Kulikowsk, C.: Computer systems that learn: classification and prediction methods from statistics. In: Neural Networks, Machine Learning and Expert Systems. Morgan Kaufmann, San Mateo (1991)Google Scholar
  20. 20.
    Yala, N., Fergani, B., Fleury, A.: Feature extraction for human activity recognition on streaming data. In: 2015 International Symposium on Innovations in Intelligent SysTems and Applications (INISTA), pp. 1–6. IEEE (2015)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Department of Information ScienceUniversity of OtagoDunedinNew Zealand
  2. 2.Department of Computer and Information ScienceUniversity of KonstanzKonstanzGermany

Personalised recommendations