Developing Algorithms and a Mathematical Model for Monitoring the Physiological State of Cattle
Abstract
This study involved theoretical and experimental research at farms with existing hardware and software. Measurements were conducted with non-invasive methods using special bolus transmitters (smaXtec animal care GmbH, Graz, Austria) developed for cow health monitoring. The boluses were introduced orally into the rumen of the studied cows. Algorithms and mathematical models were constructed for identifying estrus, calving and illnesses, and for monitoring feed and water consumption. Initial data were imported from a standard file, compatible with other applications (CSV table). Additionally, correlations were analyzed between temperature indicators, the rumen pH and the motor activity of the cattle. Illustrations include plots of the main vital factors and the correlated functions, and a screenshot of the software working console. Also included are tables with the results for each cow, the average values and the RMS deviation. The mathematical model developed is a set of algorithms and calculation results. Code for its implementation was written in Matlab R2019b and is attached to this report. This mathematical model may be used to process and interpret data obtained by boluses put into the rumen of animals.
Keywords: cattle, rumen acidity, temperature, motor activity, estrus, calving
References
[1] Krieter, J., Cavero, D. and Henze, C. (2007). Mastitis Detection in Dairy Cows using Neural Networks. GIL Jahrestagung, vol. 101, pp. 123-126.
[2] Ducrot, C., Bed’Hom, B. and Béringue, V. (2011). Issues and Special Features of Animal Health Research. Veterinary Research, vol. 42, p. 1.
[3] Poliantsev, N. I. (2015). Veterinary Obstetrics, Gynecology and Animal Husbandry Biotechnics. Saint Petersburg: Lan.
[4] Jensen, M. B. (2012). Behaviour around the Time of Calving in Dairy Cows. Applied Animal Behaviour Science, vol. 139, pp. 195–202.
[5] Maltz, E. and Antler, A. (2007). A Practical Way to Detect Approaching Calving of the Dairy Cow by a Behaviour Sensor. Precision Livestock Farming, vol. 7, pp. 141-146.
[6] Schirmann, K., et al. (2013). Short Communication: Rumination and Feeding Behavior Before and after Calving in Dairy Cows. Journal of Dairy Science, vol. 96, pp. 7088–7092.
[7] Borchers, M. R., et al. (2017). Machine-Learning-Based Calving Prediction from Activity, Lying, and Ruminating Behaviors in Dairy Cattle. Journal of Dairy Science, vol. 100, pp. 5664–5674.
[8] Dolecheck, K. A., et al. (2015). Behavioral and Physiological Changes around Estrus Events Identified using Multiple Automated Monitoring Technologies. Journal of Dairy Science, vol. 98, pp. 8723-8731.
[9] Saint-Dizier, M. and Chastant-Maillard, S. (2018). Potential of Connected Devices to Optimize Cattle Reproduction. Theriogenology, vol. 112, pp. 53–62.
[10] Schweinzer, V., et al. (2019). Evaluation of an Ear-Attached Accelerometer for Detecting Estrus Events in Indoor Housed Dairy Cows. Theriogenology, vol. 130, pp. 19-25.
[11] Reith, S., Brandt, H. and Hoy, S. (2014). Simultaneous Analysis of Activity and Rumination Time, Based on Collar-Mounted Sensor Technology, of Dairy Cows over the Peri-Estrus Period. Livestock Science, vol. 170, pp. 219–227.
[12] Reith, S. and Hoy, S. (2018). Review: Behavioral Signs of Estrus and the Potential of Fully Automated Systems for Detection of Estrus in Dairy Cattle. Animal, vol. 12, issue 2, pp. 398-407.
[13] Poliantsev, N. I. (2014). Reproductive Technology of Pedigree Cattle. A Study Guide. Saint Petersburg: Lan.
[14] Kocharian, V. D., Chizhov, G. S. and Shabasheva, I. G. (2015). Diagnostic and Treatment Methodologies for Agricultural Animals: A Study Guide. Volgograd: Volgograd State Agrarian University.