Date Available
7-18-2017
Year of Publication
2017
Document Type
Doctoral Dissertation
Degree Name
Doctor of Philosophy (PhD)
College
Agriculture, Food and Environment
Department/School/Program
Animal and Food Sciences
Advisor
Dr. Jeffrey M. Bewley
Abstract
Lameness is a painful disorder that decreases performance and is highly recognized as one of the most important health and welfare concerns for dairy cattle. Visual gait scoring is the most common way to detect gait change in dairy cattle. However, this is not only subjective, but is also time consuming and costly. A need to remove the subjective assessment of human observation exists. Therefore, automatic gait change detection for continuous monitoring by precision dairy monitoring technologies may be beneficial. The first objective of this research was to characterize behavior and production variables as cow gait changed to evaluate potential usefulness in gait change detection across two different studies. Weighted gait score was a significant (P < 0.05) predictor of rumination time for study 1. Rumination time decreased as weighted gait score increased. However, for study 2, numbers of steps and feeding time were significant predictors (P < 0.05). Number of steps increased as weighted gait score increased. Time at the feedbunk and feedbunk visits decreased as cows weighted gait score increased. The second objective was to compare behavior and production variables for each individual gait aspect in increasing gait scores to evaluate potential usefulness in gait change detection across two different studies. For study 1, milk yield, rumination, and neck activity decreased as cows as tracking score increased. For study 2, lying time decreased as cow’s general symmetry score increased. Feedbunk visits decreased as cows tracking score increased. Number of steps increased as cow’s spine curvature score increased. Time active increased as cows head bobbing score increased. Activity increased as cows speed score increased. Lying time decreased as cow’s abduction/adduction score increased. The third objective was to detect gait change utilizing multiple precision dairy monitoring technologies in two different studies. For study 1, 56% of predicted gait scores were within 0.25 points of the actual weighted gait score and for study 2, 41% of predicted gait scores were within 0.25 points of the actual weighted gait score. Pearson Correlation for study 1 and 2 was 0.43 and 0.46, respectively. For both studies, the Pearson Correlation yielded results in the low category, when evaluating goodness of fit.
Digital Object Identifier (DOI)
https://doi.org/10.13023/ETD.2017.264
Recommended Citation
Jones, Barbara Wadsworth, "BEHAVIORAL GAIT CHANGE CHARACTERIZATION AND DETECTION USING PRECISION DAIRY MONITORING TECHNOLOGIES" (2017). Theses and Dissertations--Animal and Food Sciences. 75.
https://uknowledge.uky.edu/animalsci_etds/75