The Potentialities of Machine Learning for Cow-Specific Milking: Automatically Setting Variables in Milking Machines

SIMPLE SUMMARY: In dairy farms, milking-related operations and procedures are often demanding, time-consuming, and directly affect farm economics. Therefore, milking operations need to be performed efficiently and effectively, with the proper pre-dipping and post-dipping operations, and with the avoidance of overmilking. Several studies have been carried out on milking operations and the parameters for shortening milking time without harming cows. The most important prerequisites for ensuring high-level milking conditions are the appropriate pulsation ratio and detachment flow rate. Both parameters were investigated in this study, where milking operations and parameters were recorded for three months on a dairy cattle farm in Northern Italy. A comparison was made between cows milked with a pulsation ratio of 60:40 vs. 65:35 and between cows milked with a detachment flow rate of 600 g/min vs. 800 g/min. Machine learning was used to achieve automatic adjustment of pulsation ratios and detachment flows for individual cows. The least-squares support vector machine (LSSVM) classification model based on the sparrow search algorithm (SSA) applied in this study outperformed other common machine learning models. Therefore, if implemented on milking machines, this could help to automatically vary the machine’s settings based on cows’ specific characteristics, for the benefit of cows’ welfare. ABSTRACT: In dairy farming, milking-related operations are time-consuming and expensive, but are also directly linked to the farm’s economic profit. Therefore, reducing the duration of milking operations without harming the cows is paramount. This study aimed to test the variation in different parameters of milking operations on non-automatic milking machines to evaluate their effect on a herd and finally reduce the milking time. Two trials were set up on a dairy farm in Northern Italy to explore the influence of the pulsation ratio (60:40 vs. 65:35 pulsation ratio) and that of the detachment flow rate (600 g/min vs. 800 g/min) on milking performance, somatic cell counts, clinical mastitis, and teats score. Moreover, the innovative aspect of this study relates to the development of an optimized least-squares support vector machine (LSSVM) classification model based on the sparrow search algorithm (SSA) to predict the proper pulsation ratio and detachment flow rate for individual cows within the first two minutes of milking. The accuracy and precision of this model were 92% and 97% for shortening milking time at different pulsation ratios, and 78% and 79% for different detachment rates. The implementation of this algorithm in non-automatic milking machines could make milking operations cow-specific.