Using machine-learning technique for estrus onset detection in dairy cows from acceleration and location data acquired by a neck-tag

Abstract

To promote reproductive performance in dairy cows, the timely and accurate detection of estrus onset associated with ovulation time is necessary. However, poor heat detection by manual inspection and incompetent monitoring ability via the current automated estrus discrimination methods, lead to an unsatisfactory pregnancy rate. The aim of this study was to evaluate the potential of machine learning technique based on acceleration and location data to identify the onset of estrus in dairy cows. Measurements were obtained from 296 lactating cows housed in a free-stall barn for 8 months. A total of 325 estrus events were used for modelling and testing, consisting of 2768 1-h estrus time windows and 20,632 1-h non-estrus time windows. The backpropagation neural network (BPNN) algorithm with optimized parameter combination of the number of hidden layer neurons and learning rate were investigated to automatically detect estrus onset from seven behavioral metrics, which were: duration of standing, duration of lying, duration of walking, steps, displacement, switching times between standing and walking, and number of standing mounts. The study showed that the accuracy, precision, sensitivity, specificity and F1 score of the BPNN algorithm were up to 95.46%, 72.80%, 98.29%, 95.08%, 83.65%, respectively, enabling automated estrus identification. Compared to the support vector machine (SVM) and logistic regression (LR) algorithms, the perception capability of the proposed method of estrus onset was comparable in performance to manual inspection as assessed by mean, standard deviation, absolute value of the difference, and consistency, making it an excellent alternative to replace laborious visual observation.