On-Body Smartphone Position Detection with Position Transition Correction Based on the Hand State

  • Anja ExlerEmail author
  • Christoph Michel
  • Michael Beigl
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 240)


Smartphone users tend to store their devices at manifold on-body positions: in their trouser pocket, in their backpack, on the table, or simply in their hands. Depending on the position, it might be required to adapt the ringtone and notification type to enhance their perception. To do so, the smartphone needs to be able to automatically detect the device’s position.

In this paper, we present an approach to detect the on-body position of the smartphone based on the smartphone features such as accelerometer data. In addition, we propose a position transition correction (PTC) algorithm to improve the position detection. The PTC assumes that each position transition involves the position “hand” as the user has to hold the phone into their hands to take them out of one position and place them another.

We gathered data from 20 participants and ran different classification methods. The KStar classifier achieved an accuracy of 81.97%. By applying the PTC we were able to correct about 50% of the errors on a simulated transition sequence, leading to an accuracy of almost 90%.


  1. 1.
    Alanezi, K., Mishra, S.: Design, implementation and evaluation of a smartphone position discovery service for accurate context sensing. Comput. Electr. Eng. 44, 307–323 (2015)CrossRefGoogle Scholar
  2. 2.
    Antos, S.A., Albert, M.V., Kording, K.P.: Hand, belt, pocket or bag: Practical activity tracking with mobile phones. J. Neurosci. Methods 231, 22–30 (2014). Motion Capture in Animal Models and HumansCrossRefGoogle Scholar
  3. 3.
    Exler, A., Dinse, C., Günes, Z., Hammoud, N., Mattes, S., Beigl, M.: Investigating the perceptibility different notification types on smartphones depending on the smartphone position. In: Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers, pp. 970–976. ACM (2017)Google Scholar
  4. 4.
    Fujinami, K.: On-body smartphone localization with an accelerometer. Information 7(2), 21 (2016)CrossRefGoogle Scholar
  5. 5.
    Kunze, K., Lukowicz, P.: Using acceleration signatures from everyday activities for on-body device location. In: 2007 11th IEEE International Symposium on Wearable Computers, pp. 115–116, October 2007Google Scholar
  6. 6.
    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). Scholar
  7. 7.
    Shi, Y., Shi, Y., Liu, J.: A rotation based method for detecting on-body positions of mobile devices. In: Proceedings of the 13th International Conference on Ubiquitous Computing, UbiComp 2011, pp. 559–560. ACM, New York (2011)Google Scholar
  8. 8.
    Vahdatpour, A., Amini, N., Sarrafzadeh, M.: On-body device localization for health and medical monitoring applications. In: 2011 IEEE International Conference on Pervasive Computing and Communications (PerCom), pp. 37–44, March 2011Google Scholar
  9. 9.
    Wiese, J., Saponas, T.S., Brush, A.B.: Phoneprioception: enabling mobile phones to infer where they are kept. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, CHI 2013, pp. 2157–2166. ACM, New York (2013)Google Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018

Authors and Affiliations

  1. 1.Karlsruhe Institute of Technology (KIT), TECOKarlsruheGermany

Personalised recommendations