Machine-Learning Techniques Can Enhance Dairy Cow Estrus Detection Using Location and Acceleration Data.

Wang, J., Bell, M., Liu, X., & Liu, G. (2020). Machine-Learning Techniques Can Enhance Dairy Cow Estrus Detection Using Location and Acceleration Data. Animals, 10(7), 1160. https://doi.org/10.3390/ani10071160

This study evaluated the use of location and acceleration data combined with machine learning techniques to improve estrus detection in dairy cows. Data were collected from 12 cows over 12 days using neck-mounted devices, with 25,684 records analyzed for behavioral metrics through principal component analysis (PCA). Four machine learning models—K-nearest neighbor (KNN), back-propagation neural network (BPNN), linear discriminant analysis (LDA), and classification and regression tree (CART)—were compared across different time windows for estrus prediction. The BPNN model with a 0.5-hour time window provided the best results, demonstrating that integrating these technologies enhances estrus detection accuracy.