A Deep Learning Framework for Improving Lameness Identification in Dairy Cattle

Authors

  • Yasmine Karoui University of Stuttgart Université du Québec à Montréal
  • Amanda A. Boatswain Jacques Université du Québec à Montréal
  • Abdoulaye Baniré Diallo Université du Québec à Montréal
  • Elise Shepley Mcgill University
  • Elsa Vasseur McGill University

Keywords:

Classification, Data Augmentation, Dairy Cattle, Lamness

Abstract

Lameness, characterized by an anomalous gait in cows due to a dysfunction in their locomotive system, is a serious welfare issue for cows and farmers. Prompt lameness detection methods can prevent the development of acute lameness in cattle. In this study, we propose a deep learning framework to help identify lameness based on motion curves of different leg joints on the cow. The framework combines data augmentation and a convolutional neural network using an LeNet architecture. Performance assessed using cross validation showed promising prediction accuracies above 99% and 91% for validation and test sets, respectively. This also demonstrates the usefulness of data generation in cases where the data set is originally small in size and difficult to generate.

Downloads

Published

2021-05-18

How to Cite

Karoui, Y., Boatswain Jacques, A. A., Diallo, A. B., Shepley, E., & Vasseur, E. (2021). A Deep Learning Framework for Improving Lameness Identification in Dairy Cattle. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15811-15812. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17902

Issue

Section

AAAI Student Abstract and Poster Program