The use of a rule-based module as a decision support system for dystocia detection in dairy cows

DOI: 10.18805/ijar.B-841    | Article Id: B-841 | Page : 128-130
Citation :- The use of a rule-based module as a decision support system for dystocia detection in dairy cows.Indian Journal Of Animal Research.2020.(54):128-130
D. Zaborski, W. Grzesiak and J. Wojcik daniel.zaborski@zut.edu.pl
Address : Department of Ruminants Science, West Pomeranian University of Technology, Szczecin -71270, Poland.
Submitted Date : 19-10-2017
Accepted Date : 8-03-2018

Abstract

The aim of the present study was to construct a rule-based module (RBM) for dystocia detection in dairy cattle and to verify its predictive performance. A total of 3041 calving records of Polish Holstein-Friesian Black-and-White heifers and cows were used. Three continuous and seven categorical predictors of dystocia were included in the three decision tree models, from which the rules for RBM were extracted. The system was equipped with a user-friendly text interface. The percentage of correctly detected easy, moderate and difficult calvings in heifers on the independent test set was 26.13%, 76.52% and 77.27%, respectively. The overall accuracy was 60.12%. The respective values for cows were: 59.18%, 69.01%, 0% and 62.03%. The predictive performance of the constructed system was satisfactory, except for the difficult category in cows.

Keywords

Dairy cattle Decision support system Diagnosis Dystocia Prediction Rule-based module.

References

  1. Allore, H.G. and Jones, L.R. (1995). An approach to summarize somatic cell score trends for a data-driven, decision support system. Journal of Dairy Science, 78:1377–1381. DOI: 10.3168/jds.S0022-0302(95)76760-1.
  2. Balasundaram, B., Gupta, A.K., Dongre, V.B., Mohanty, T.K., Sharma, P.C., Khat, K., Singh, R.K. (2011a). Influence of genetic and non-genetic factors on incidence of calving abnormalities in Karan Fries cows. Indian Journal of Animal Research, 45:26–31.    Balasundaram, B., Gupta, A.K., Dongre, V.B., Mohanty, T.K., Sharma, P.C., Khate, K., Singh, R.K. (2011b). Influence of genetic and non-genetic factors on incidence of post partum utero-vaginal complications in Karan Fries cows. Indian Journal of Animal Research, 45:192–197.
  3. Domecq, J.J., Nebel, R.L., McGilliard, M.L., Pasquino, A.T. (1991). Expert system for evaluation of reproductive performance and management. Journal of Dairy Science, 74:3446–3453. DOI: 10.3168/jds.S0022-0302(91)78534-2.
  4. Ercan, N., Yokuº, B., Gûn, M., Koçhan, A. (2017). Paraoxonase activity an indicator of complications at early stage of complicated pregnant cows. Indian Journal of Animal Research, 51:927–931. DOI: 10.18805/ijar.v0iOF.8459.
  5. Giarratano, J. and Riley, G. (2005). Expert systems: Principles and programming. Thomson Publications, Boston, MA. pp. 288.
  6. Mane, P.M. and Bhangre, R.D. (2015). Outcome of different regimes of treatment for uterine torsion in bovine at field level – A clinical study. Indian Journal of Animal Research, 49:819–822. DOI: 10.18805/ijar.7045.
  7. McHugh, N., Kearney, J.F., Berry, D.P. (2011). The effect of dystocia on subsequent performance in dairy cows. Moorepark Research Report, 2011:15. 
  8. Mee, J. F. (2008). Prevalence and risk factors for dystocia in dairy cattle: A review. The Veterinary Journal, 176:93–101. DOI: 10.1016/j.tvjl.2007.12.032.
  9. Pellerin, D., Levallois, R., St-Laurent, G., Perrier, J.-P. (1994). LAIT-XPERT VACHES: an expert system for dairy herd management. Journal of Dairy Science, 77:2308–2317. DOI: 10.3168/jds.S0022-0302(94)77174-5.
  10. Pogorzelska, P. and Nogalski, Z. (2010). Calving difficulty in cows and heifers of the Polish dairy cattle population in 2007-2008. Scientific Annals of Polish Society of Animal Production, 6:103–110.
  11. Rutkowski, L. (2012). Methods and techniques of artificial intelligence. PWN, Warsaw. pp. 434.
  12. Zaborski, D., Grzesiak, W., Kotarska, K., Szatkowska, I., Jedrzejczak, M. (2014). Detection of difficult calvings in dairy cows using boosted classification trees. Indian Journal of Animal Research, 48:452-458. DOI: 10.5958/0976-0555.2014.00010.7.
  13. Zaborski, D., Proskura, W.S., Grzesiak, W. (2016). Classification of calving difficulty scores using different types of decision trees. Acta Scientiarum Polonorum Zootechnica, 15:55–70. DOI: 10.21005/asp.2016.15.4.05.
  14. Zaborski, D., Proskura, W.S., Grzesiak, W. (2017). Comparison between data mining methods to assess calving difficulty in cattle. Revista Colombiana de Ciencias Pecuarias, 30:196–208. DOI: 10.17533/udea.rccp.v30n3a03.

Global Footprints