Mobile Sensor Data Classification Using GM-SOM

  • Petr Gajdoš
  • Pavel Moravec
  • Pavel Dohnálek
  • Tomáš Peterek
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 210)

Abstract

The paper uses a previously-introduced modification of standard Kohonen network (SOM), called GM-SOM. This approach uses partitioning the problem in case of insufficient resources (memory, disc space, etc.) and parallel processing of input data set to process all input vectors at once, with the use of modern multi-core GPUs to achieve massive parallelism. The algorithm pre-selects potential centroids of data clusters in the first step and uses them as weight vectors in the final calculation. In this paper, the algorithm has been demonstrated on a new UCI HAR dataset, representing activities recorded by smartphone sensors, which are prone to random noise due to the sensor behavior. Moreover the separation of classes is not linear, which introduces additional complexity and makes it hard to process the data by linear algebra methods.

Keywords

accelerometer activity recognition gyroscope KohonenNetwork parallel calculation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Anguita, D., Ghio, A., Oneto, L., Parra, X., Reyes-Ortiz, J.L.: Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine. In: Bravo, J., Hervás, R., Rodríguez, M. (eds.) IWAAL 2012. LNCS, vol. 7657, pp. 216–223. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  2. 2.
    Gajdos, P., Moravec, P.: Two-step modified SOM for parallel calculation. In: Pokorný, J., Snásel, V., Richta, K. (eds.) DATESO, CEUR Workshop Proceedings, vol. 567, pp. 13–21 (2010), CEUR-WS.org
  3. 3.
    Gajdoš, P., Moravec, P.: Intruder data classification using GM-SOM. In: Cortesi, A., Chaki, N., Saeed, K., Wierzchoń, S. (eds.) CISIM 2012. LNCS, vol. 7564, pp. 92–100. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  4. 4.
    Khan, A., Lee, Y., Lee, S.: Accelerometer’s position free human activity recognition using a hierarchical recognition model. In: 2010 12th IEEE International Conference on e-Health Networking Applications and Services (Healthcom), pp. 296–301 (2010), doi:10.1109/HEALTH.2010.5556553Google Scholar
  5. 5.
    Khan, A., Lee, Y.K., Lee, S., Kim, T.S.: Human activity recognition via an accelerometer-enabled-smartphone using kernel discriminant analysis. In: 5th International Conference on Future Information Technology (FutureTech), pp. 1–6 (2010), doi:10.1109/FUTURETECH.2010.5482729Google Scholar
  6. 6.
    Kohonen, T.: Self-Organizing Maps, 2nd edn. Springer, Berlin (1997)MATHCrossRefGoogle Scholar
  7. 7.
    Mirarmandehi, N., Rabiee, H.: An asynchronous dynamic bayesian network for activity recognition in an ambient intelligent environment. In: 5th International Conference on Pervasive Computing and Applications (ICPCA), pp. 20–25 (2010), doi:10.1109/ICPCA.2010.5704069Google Scholar
  8. 8.
    Parkka, J., Cluitmans, L., Ermes, M.: Personalization algorithm for real-time activity recognition using pda, wireless motion bands, and binary decision tree. IEEE Transactions on Information Technology in Biomedicine 14(5), 1211–1215 (2010), doi:10.1109/TITB.2010.2055060CrossRefGoogle Scholar
  9. 9.
    Yang, X., Dinh, A., Chen, L.: Implementation of a wearerable real-time system for physical activity recognition based on naive bayes classifier. In: 2010 International Conference on Bioinformatics and Biomedical Technology (ICBBT), pp. 101–105 (2010), doi:10.1109/ICBBT.2010.5479000Google Scholar
  10. 10.
    Zhang, H., Yoshie, O.: Improving human activity recognition using subspace clustering. In: 2012 International Conference on Machine Learning and Cybernetics (ICMLC), vol. 3, pp. 1058–1063 (2012), doi:10.1109/ICMLC.2012.6359501Google Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Petr Gajdoš
    • 1
    • 2
  • Pavel Moravec
    • 1
    • 2
  • Pavel Dohnálek
    • 1
  • Tomáš Peterek
    • 2
  1. 1.Department of Computer Science, FEECSVŠB - Technical University of OstravaOstrava-PorubaCzech Republic
  2. 2.IT4 Innovations, Centre of ExcellenceVŠB - Technical University of OstravaOstrava-PorubaCzech Republic

Personalised recommendations