A Hierarchical Classification Method Used to Classify Livestock Behaviour from Sensor Data

  • Hari SuparwitoEmail author
  • Kok Wai Wong
  • Hong Xie
  • Shri Rai
  • Dean Thomas
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11909)


One of the fundamental tasks in the management of livestock is to understand their behaviour and use this information to increase livestock productivity and welfare. Developing new and improved methods to classify livestock behaviour based on their daily activities can greatly improve livestock management. In this paper, we propose the use of a hierarchical machine learning method to classify livestock behaviours. We first classify the livestock behaviours into two main behavioural categories. Each of the two categories is then broken down at the next level into more specific behavioural categories. We have tested the proposed methodology using two commonly used classifiers, Random Forest, Support Vector Machine and a newer approach involving Deep Belief Networks. Our results show that the proposed hierarchical classification technique works better than the conventional approach. The experimental studies also show that Deep Belief Networks perform better than the Random Forest and Support Vector Machine for most cases.


Machine learning Hierarchical classification Livestock behaviour Sensor data 



This research was supported by CSIRO Floreat, Western Australia. We are grateful for their cooperation and permission to use their data.


  1. 1.
    Manning, L.: What is Ag Big Data? (2015).
  2. 2.
    Carvalho, P.: Can grazing behavior support innovations in grassland management. Tropical Grasslands-Forrajes Tropicales 1, 137–155 (2013)CrossRefGoogle Scholar
  3. 3.
    Rushen, J., Chapinal, N., De Passille, A.: Automated monitoring of behavioural-based animal welfare indicators. Anim. Welfare UFAW J. 21, 339 (2012)CrossRefGoogle Scholar
  4. 4.
    Van Hertem, T., Lague. S., Rooijakkers, L., Vranken, E.: Towards a sustainable meat production with precision livestock farming. In: Proceedings in Food System Dynamics, pp. 357–362 (2016)Google Scholar
  5. 5.
    Manning, J.K., et al.: The effects of global navigation satellite system (GNSS) collars on cattle (Bos taurus) behaviour. Appl. Anim. Behav. Sci. 187, 54–59 (2017). Scholar
  6. 6.
    Williams, M., et al.: A novel behavioral model of the pasture-based dairy cow from GPS data using data mining and machine learning techniques. J. Dairy Sci. 99, 2063–2075 (2016). Scholar
  7. 7.
    González, L., Bishop-Hurley, G., Handcock, R., Crossman, C.: Behavioral classification of data from collars containing motion sensors in grazing cattle. Comput. Electron. Agric. 110, 91–102 (2015). Scholar
  8. 8.
    Alvarenga, F., et al.: Using a three-axis accelerometer to identify and classify sheep behaviour at pasture. Appl. Anim. Behav. Sci. (2016). Scholar
  9. 9.
    Hilario, M.C., Wrage-Mönnig, N., Isselstein, J.: Behavioral patterns of (co-) grazing cattle and sheep on swards differing in plant diversity. Appl. Anim. Behav. Sci. 191, 17–23 (2017). Scholar
  10. 10.
    Homburger, H., Schneider, M., Hilfiker, S., Luscher, A.: Inferring behavioral states of grazing livestock from high-frequency position data alone. PLoS ONE 9, e114522 (2014)CrossRefGoogle Scholar
  11. 11.
    Giovanetti, V., et al.: Automatic classification system for grazing, ruminating and resting behaviour of dairy sheep using a tri-axial accelerometer. Livestock Sci. 196, 42–48 (2017). Scholar
  12. 12.
    Manning, J., et al.: The behavioural responses of beef cattle (Bos taurus) to declining pasture availability and the use of GNSS technology to determine grazing preference. Agriculture 7, 45 (2017)CrossRefGoogle Scholar
  13. 13.
    de Weerd, N., et al.: Deriving animal behaviour from high-frequency GPS: tracking cows in open and forested habitat. PLoS ONE 10, e0129030 (2015)CrossRefGoogle Scholar
  14. 14.
    Diosdado, J.A.V., et al.: Classification of behaviour in housed dairy cows using an accelerometer-based activity monitoring system. Anim. Biotelemetry 3, 15 (2015). Scholar
  15. 15.
    Wang, G.: Machine learning for inferring animal behavior from location and movement data. Ecol. Inform. 49, 69–76 (2019). Scholar
  16. 16.
    Wainberg, M., Alipanahi, B., Frey, B.: Are random forests truly the best classifiers? J. Mach. Learn. Res. 17, 3837–3841 (2016)MathSciNetGoogle Scholar
  17. 17.
    Durgesh, K., Lekha, B.: Data classification using support vector machine. J. Theoret. Appl. Inf. Technol. 12, 1–7 (2010)Google Scholar
  18. 18.
    Hua, Y., Guo, J., Zhao, H.: Deep belief networks and deep learning. In: IEEE International Conference on Intelligent Computing and Internet of Things (ICIT) (2015)Google Scholar
  19. 19.
    Valletta, J., et al.: Applications of machine learning in animal behaviour studies. Anim. Behav. 124, 203–220 (2017). Scholar
  20. 20.
    Browning, E., et al.: Predicting animal behaviour using deep learning: GPS data alone accurately predict diving in seabirds. Methods Ecol. Evol. 9, 681–692 (2018). Scholar
  21. 21.
    Rayas-Amor, A.A., et al.: Triaxial accelerometers for recording grazing and ruminating time in dairy cows: an alternative to visual observations. J. Vet. Behav. Clin. Appl. Res. 20, 102–108 (2017). Scholar
  22. 22.
    Calenge, C., Dray, S., Royer-Carenzi, M.: The concept of animals’ trajectories from a data analysis perspective. Ecol. Inform. 4, 34–41 (2009)CrossRefGoogle Scholar
  23. 23.
    Chawla, N., Bowyer, K., Hall, L., Kegelmeyer, W.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Hari Suparwito
    • 1
    Email author
  • Kok Wai Wong
    • 1
  • Hong Xie
    • 1
  • Shri Rai
    • 1
  • Dean Thomas
    • 2
  1. 1.Murdoch UniversityPerthAustralia
  2. 2.CSIRO FloreatPerthAustralia

Personalised recommendations