Detection of difficult conceptions in dairy cows using selected data mining methods

Journal Title: Animal Science Papers and Reports - Year 2011, Vol 29, Issue 4

Abstract

In the present study, the detection of difficult conceptions in dairy cows using selected data mining methods – na ve Bayes classifier (NBC) and regression and classifications trees (CART) is presented. The set of 11 diagnostic variables was used, which included, among others, number of lactation, artificial insemination (AI) season, age of inseminated cow, proportion of HF-genes in cow genotype, sex of calf from preceding calving, length of pregnancy, milk, protein and fat yield. Two conception classes were distinguished: the GOOD class, if a cow conceived after one or two AIs and the “POOR” class, if more than two AIs per conception were required. The models were characterized by capability of predicting the membership of conceptions to either class. Correctness of predictions was 83%. CART proved to be more precise in detecting conceptions of the POOR class (sensitivity) compared with predictions by NBC (P≤0.01). Specificity was similar for both classifiers (90% and 93%). Among the variables determining conception class, calving-to-conception interval, calving interval and the difference between the mean body condition and condition at AI were the most significant variables for CART. Utilization of these classifiers, particularly of CART, may help a breeder to appropriately prepare cows for AI, thus contributing to the improved financial results of a herd.

Authors and Affiliations

Wilhelm Grzesiak, Daniel Zaborski, Piotr Sablik, Renata Pilarczyk

Keywords

Related Articles

Correlation between the proteins and protein profile(s) of different regions of epididymis and their contents in goat buck

Total proteins and their profile(s) in three regions of epididymis, its fluid and sperm membrane extract (SME) were analysed with an objective to determine the changes in spermatozoa during epididymal maturation in goat...

Effect of calpastatin gene (CAST) polymorphism on pork quality

The aim of the study was to assess the effect of calpastatin gene (CAST/RsaI) polymorphism on technological and sensory quality of pork, the range of glycolytic and proteolytic post mortem changes and slaughter value. Th...

The effect of dietary protein level on selected degradative enzymes activity of hepatocyte cellular subfractions in experimental mice

Studied was the activity of selected degradative enzymes of lysosomal, microsomal and cytoplasmic fraction of hepatocytes as affected by different protein levels in the diet of experimental mice. The control animals were...

Impact of LEP and LEPR gene polymorphisms on functional traits in Polish Holstein-Friesian cattle

Five single nucleotide polymorphisms in leptin and leptin receptor genes were analysed for their possible impact on estimating breeding values for somatic cell count score (SCS) in milk, longevity and reproductive traits...

Alternative supplemental mixture for organic dairy herds to maintain desirable milk fatty acid profile throughout the indoor feeding period

The aim of the study was to evaluate the effect of diet containing a supplemental mixture with alternative components suitable for organic herds on the yield and composition of milk and the fatty acid profile. The on-far...

Download PDF file
  • EP ID EP71328
  • DOI -
  • Views 141
  • Downloads 0

How To Cite

Wilhelm Grzesiak, Daniel Zaborski, Piotr Sablik, Renata Pilarczyk (2011). Detection of difficult conceptions in dairy cows using selected data mining methods. Animal Science Papers and Reports, 29(4), 293-302. https://europub.co.uk/articles/-A-71328