Handling Displacement Effects in On-Body Sensor-Based Activity Recognition

  • Oresti Baños
  • Miguel Damas
  • Héctor Pomares
  • Ignacio Rojas
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8277)


So far little attention has been paid to activity recognition systems limitations during out-of-lab daily usage. Sensor displacement is one of these major issues, particularly deleterious for inertial on-body sensing. The effect of the displacement normally translates into a drift on the signal space that further propagates to the feature level, thus modifying the expected behavior of the predefined recognition systems. On the use of several sensors and diverse motion-sensing modalities, in this paper we compare two fusion methods to evaluate the importance of decoupling the combination process at feature and classification levels under realistic sensor configurations. In particular a ’feature fusion’ and a ’multi-sensor hierarchical-classifier’ are considered. The results reveal that the aggregation of sensor-based decisions may overcome the difficulties introduced by the displacement and confirm the gyroscope as possibly the most displacement-robust sensor modality.


Sensor displacement Sensor network Sensor fusion Activity recognition Human Behavior Motion sensors 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Albert, M.V., Toledo, S., Shapiro, M., Kording, K.: Using mobile phones for activity recognition in parkinsons patients. Frontiers in Neurology 3(158) (2012)Google Scholar
  2. 2.
    Banos, O., Damas, M., Pomares, H., Rojas, F., Delgado-Marquez, B., Valenzuela, O.: Human activity recognition based on a sensor weighting hierarchical classifier. Soft. Computing 17, 333–343 (2013)CrossRefGoogle Scholar
  3. 3.
    Banos, O., Damas, M., Pomares, H., Rojas, I.: On the use of sensor fusion to reduce the impact of rotational and additive noise in human activity recognition. Sensors 12(6), 8039–8054 (2012)CrossRefGoogle Scholar
  4. 4.
    Banos, O., Damas, M., Pomares, H., Rojas, I., Attila Toth, M., Amft, O.: A benchmark dataset to evaluate sensor displacement in activity recognition. In: Proceedings of the 2012 ACM Conference on Ubiquitous Computing, UbiComp 2012, pp. 1026–1035. ACM, New York (2012)CrossRefGoogle Scholar
  5. 5.
    Chavarriaga, R., Bayati, H., del R. Millán, J.: Unsupervised adaptation for acceleration-based activity recognition: robustness to sensor displacement and rotation. Pers. Ubiquit. Comput., 1–12 (2012)Google Scholar
  6. 6.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley-Interscience (2000)Google Scholar
  7. 7.
    Förster, K., Roggen, D., Tröster, G.: Unsupervised classifier self-calibration through repeated context occurences: Is there robustness against sensor displacement to gain? In: Proc. 13th IEEE Int. Symposium on Wearable Computers (ISWC), Linz, Austria, pp. 77–84. IEEE Press (September 2009)Google Scholar
  8. 8.
    Kunze, K., Lukowicz, P.: Dealing with sensor displacement in motion-based onbody activity recognition systems. In: 10th International Conference on Ubiquitous Computing, Seoul, South Korea, pp. 20–29. ACM Press (September 2008)Google Scholar
  9. 9.
    Kunze, K., Lukowicz, P., Junker, H., Tröster, G.: Where am I: Recognizing on-body positions of wearable sensors. In: Strang, T., Linnhoff-Popien, C. (eds.) LoCA 2005. LNCS, vol. 3479, pp. 264–275. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  10. 10.
    Kunze, K., Lukowicz, P., Partridge, K., Begole, B.: Which way am i facing: Inferring horizontal device orientation from an accelerometer signal. In: 13th IEEE Int. Symposium on Wearable Computers (ISWC), Linz, Austria, pp. 149–150. IEEE Press (September 2009)Google Scholar
  11. 11.
    Kusserow, M., Amft, O., Gubelmann, H., Troester, G.: Arousal pattern analysis of an olympic champion in ski jumping. Sports Technology 3(3), 192–203 (2010)Google Scholar
  12. 12.
    Lara, O., Labrador, M.: A survey on human activity recognition using wearable sensors. IEEE Communications Surveys Tutorials PP(99), 1–18 (2012)Google Scholar
  13. 13.
    Sagha, H., del R. Millan, J., Chavarriaga, R.: Detecting and rectifying anomalies in opportunistic sensor networks. In: 8th Int. Conf. on Networked Sensing Systems, Penghu, Taiwan, pp. 162–167. IEEE Press (June 2011)Google Scholar
  14. 14.
    Stiefmeier, T., Roggen, D., Ogris, G., Lukowicz, P., Tröster, G.: Wearable activity tracking in car manufacturing. IEEE Pervasive Computing 7(2), 42–50 (2008)CrossRefGoogle Scholar
  15. 15.
    Zappi, P., Stiefmeier, T., Farella, E., Roggen, D., Benini, L., Troster, G.: Activity recognition from on-body sensors by classifier fusion: sensor scalability and robustness. In: 3rd International Conference on Intelligent Sensors, Sensor Networks and Information, Melbourne, Australia, pp. 281–286. IEEE Press (December 2007)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Oresti Baños
    • 1
  • Miguel Damas
    • 1
  • Héctor Pomares
    • 1
  • Ignacio Rojas
    • 1
  1. 1.Department of Computer Architecture and Computer Technology, Research Center for Information and Communications TechnologiesUniversity of Granada (CITIC-UGR)GranadaSpain

Personalised recommendations