Clinical mastitis detection by on-line measurements of milk yield, electrical conductivity and deep Learn

Abstract

Abstract Mastitis is the most common and costly disease in dairy cows since it can reduce milk yield, degrade milk quality, and increase healthcare costs. Detection of mastitis is an important part of udder-health management on dairy farms. Thus, the objective of this study is to develop a novel method for automatic on-line detection of clinical mastitis in an automatic milking system using the measurement of electrical parameters, data of milk production efficiency, and deep learning. The measurements were inputted into a neural network to calculate the mastitis detection index. The network was trained with 44 healthy and 6 clinical mastitic cows. 42 out of 44 healthy and 5 out of 6 mastitic cows were classified correctly after training. The trained neural network can predicted 164 out of 176 healthy quarters correctly in different evaluation data sets. These results were better than the results obtained with the model usually used on the farm.