Advertisement

Automatic Recognition of a Weakly Identified Animal Activity State Based on Data Transformation of 3D Acceleration Sensor

  • Valentin Sturm
  • Julia Mayer
  • Dmitry EfrosininEmail author
  • Leonie Roland
  • Michael Iwersen
  • Marc Drillich
  • Wolfgang Auer
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 919)

Abstract

Smartbow ear-attached motion active sensor with a 3d accelerometer is used for animal activity tracking. Such technology is required to understand the welfare, nutrition scheme and management strategies for breeding cattle. The ear-tag with integrated sensor has no fixed location and orientation that leads to necessity to use the orientation independent features by solving a time series classification problem. In this paper we propose an accelerometer data transformation techniques based on Euler angle rotation and signal projection and show their equivalence relative to a reference coordinate system. The main aim is to increase a recognition accuracy for the weakly-identified states or actions. The previous research for the fitting of the calves has demonstrated certain difficulties by recognition of some rare states and actions, e.g. milk intake. The results show that an average area under the ROC-curve of 0.740 is achieved with improvement of 0.252 over classifications without data transformation.

Keywords

Activity recognition Accelerometer Data transformation Machine learning 

Notes

Acknowledgements

This work has been supported by the COMET-K2 “Center for Symbiotic Mechatronics” of the Linz Center of Mechatronics (LCM) funded by the Austrian federal government and the federal state of Upper Austria.

References

  1. 1.
    Aminev, D.A., Kozyrev, D.V., Zhurkov, A.P., Romanov, A.Y., Romanova, I.I.: Method of automated control of distributed radio direction finding system. In: Dynamics of Systems, Mechanisms and Machines (Dynamics), Omsk, Russia, pp. 1–9 (2017)Google Scholar
  2. 2.
    Ann, O.C., Theng, L.B.: Human activity recognition: a review. In: 2014 IEEE International Conference on Control System, Computing and Engineering (ICCSCE 2014), Batu Ferringhi, pp. 389–393 (2014)Google Scholar
  3. 3.
    Cohen, J.: A coefficient of agreement for nominal scales. Educ. Psychol. Meas. 20, 37–46 (1960)CrossRefGoogle Scholar
  4. 4.
    Fawcett, T.: An introduction to ROC analysis. Pattern Recognit. Lett. 27(8), 861–874 (2006)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Hill, T.M., Suarez-Mena, F.X., Hu, W., Dennis, T.S., Schlotterbeck, R.L., Timms, L.L.: Technical note: evaluation of an ear-attached movement sensor to record rumination, eating, and activity behaviors in 1-month-old calves. Prof. Anim. Sci. 33, 743–747 (2017)Google Scholar
  6. 6.
    Hodson, M., Timms, L.: Use of an Ear Tag Based Behavioral and Temperature Monitor (Cow ManageR) on Dairy Calves (Preliminary Report). Animal Industry Report: AS 663, ASL R3164 (2017). https://lib.dr.iastate.edu/ans_air/vol663/iss1/37
  7. 7.
    Krieger, S., Sattlecker, G., Kickinger, F., Auer, W., Drillich, M., Iwersen, M.: Prediction of calving in dairy cows using a tail-mounted tri-axial accelerometer: a pilot study. Biosyst. Eng. (2017). https://doi.org/10.1016/j.biosystemseng.2017.11.010
  8. 8.
    Lu, H., Yang, J., Liu, Z., Lane, N.D., Choudhury, T., Campbell, A.T.: The jigsaw continuous sensing engine for mobile phone applications. In: SenSys, pp. 71–84 (2010)Google Scholar
  9. 9.
    Sturm, V., et al.: A chaos theoretic approach to animal activity recognition. J. Math. Sci. (2017, to appear). XXXIV International Seminar on Stability Problems for Stochastic Models, Debrecen, HungaryGoogle Scholar
  10. 10.
    Wolfger, B., Timsit, E., Pajor, E.A., Cook, N., Barkema, H.W., Orsel, K.: Technical note: accuracy of an ear tag-attached accelerometer to monitor rumination and feeding behavior in feedlot cattle. J. Anim. Sci. 93(6), 3164–3168 (2015)CrossRefGoogle Scholar
  11. 11.
    Vishnevsky, V., Kozyrev, D., Rykov, V.: New generation of safety systems for automobile traffic control using RFID technology and broadband wireless communication. In: Vishnevsky, V., Kozyrev, D., Larionov, A. (eds.) DCCN 2013. CCIS, vol. 279, pp. 145–153. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-05209-0_13CrossRefzbMATHGoogle Scholar
  12. 12.
    Yan, Z., Chakraborty, D., Misra, A., Jeung, H., Aberer, K.: Semantic Acitivity Classification Using Locomotive Signatures from Mobile Phones (2012). https://infoscience.epfl.ch/record/174016/files/2012_semActi.pdf
  13. 13.
    Youden, J.W.: Index for rating diagnostic tests. Cancer 3, 32–35 (1950)CrossRefGoogle Scholar
  14. 14.
    Zhu, W., Zeng, N., Wang, N.: Sensitivity, Specificity, Accuracy, Associated Confidence Interval and ROC Analysis with Practical SAS\(^{\textregistered }\) Implementations (2010). https://www.lexjansen.com/nesug/nesug10/hl/hl07.pdf

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Valentin Sturm
    • 1
  • Julia Mayer
    • 1
  • Dmitry Efrosinin
    • 2
    • 3
    Email author
  • Leonie Roland
    • 4
  • Michael Iwersen
    • 4
  • Marc Drillich
    • 4
  • Wolfgang Auer
    • 5
  1. 1.Linz Center of Mechatronics GmbhLinzAustria
  2. 2.Johannes Kepler UniversityLinzAustria
  3. 3.Institute of Control Sciences, RASMoscowRussia
  4. 4.University of Veterinary Medicine ViennaViennaAustria
  5. 5.Smartbow GmbHWeibernAustria

Personalised recommendations