Lameness detection challenges in automated milking systems addressed with partial least squares discriminant analysis

Emanuel Garcia, Ilka Christine Klaas, Jose Manuel Amigo Rubio, Rasmus Bro, Carsten Enevoldsen

Research output: Contribution to journalJournal articleResearchpeer-review

29 Citations (Scopus)
288 Downloads (Pure)

Abstract

Lameness is prevalent in dairy herds. It causes decreased animal welfare and leads to higher production costs. This study explored data from an automatic milking system (AMS) to model on-farm gait scoring from a commercial farm. A total of 88 cows were gait scored once per week, for 2 5-wk periods. Eighty variables retrieved from AMS were summarized week-wise and used to predict 2 defined classes: nonlame and clinically lame cows. Variables were represented with 2 transformations of the week summarized variables, using 2-wk data blocks before gait scoring, totaling 320 variables (2 × 2 × 80). The reference gait scoring error was estimated in the first week of the study and was, on average, 15%. Two partial least squares discriminant analysis models were fitted to parity 1 and parity 2 groups, respectively, to assign the lameness class according to the predicted probability of being lame (score 3 or 4/4) or not lame (score 1/4). Both models achieved sensitivity and specificity values around 80%, both in calibration and cross-validation. At the optimum values in the receiver operating characteristic curve, the false-positive rate was 28% in the parity 1 model, whereas in the parity 2 model it was about half (16%), which makes it more suitable for practical application; the model error rates were, 23 and 19%, respectively. Based on data registered automatically from one AMS farm, we were able to discriminate nonlame and lame cows, where partial least squares discriminant analysis achieved similar performance to the reference method.
Original languageEnglish
JournalJournal of Dairy Science
Volume97
Issue number12
Pages (from-to)7476-7486
Number of pages11
ISSN0022-0302
DOIs
Publication statusPublished - 2014

Keywords

  • Cattle
  • lameness detection in AMS
  • animal welfare
  • pattern recognition
  • Partial Least Squares Discriminant Analysis

Cite this