An Innovative Concept for a Multivariate Plausibility Assessment of Simultaneously Recorded Data

Relationship between reticular pH parameters and potential on-farm indicators in the early lactation of dairy cows

Subacute ruminal acidosis (SARA) is an important nutritional disorder affecting animal welfare and economy of milk production. Definitions rely on ruminal pH but due to limitations of its measurement, indicators reflecting low pH are highly desirable. The aim of this study was to investigate the relationship between reticular pH and 18 on-farm indicators in milk, blood, faeces, urine and chewing behaviour in early lactating dairy cows. Ten farms were visited for 3 weeks and in total samples of 100 cows (10 per farm) were taken. The statistics and graphical visualization were performed using Pearson correlation and linear regression models on an animal individual level as well as with linear mixed models. Eight indicators (milk fat, fat-to-protein ratio, rumination time, feed intake time, rumination frequency, rumination boluses, lying time and faecal pH) were statistically significant associated with the daily animal individual reticular pH average. However, none of the models including the potential explanatory variables explained more than 5% of the pH variations. The study confirms the necessity of pH measurement to detect SARA risk animals in early lactation dairy cows.

Precision Detection of Real-Time Conditions of Dairy Cows Using an Advanced Artificial Intelligence Hub

One of the main challenges in the adoption of artificial intelligence-based tools, such as integrated decision support systems, is the complexities of their application. This study aimed to define the relevant parameters that can be used as indicators for real-time detection of heat stress and subclinical mastitis in dairy cows. Moreover, this study aimed to demonstrate the use of a developed data-mining hub as an artificial intelligence-based tool that integrates the defined relevant information (parameters or traits) in accurately identifying the condition of the cow. A comprehensive theoretical framework of the data-mining hub is demonstrated, the selection of the parameters that were used for the data-mining hub is listed, and the relevance of the traits is discussed. The practical application of the data-mining hub has shown that using 21 parameters instead of 13 and 8 parameters resulted in a high overall accuracy of detecting heat stress and subclinical mastitis in dairy cows with a high precision effect reflecting a low percentage of misclassifying the conditions of the dairy cows. This study has developed an innovative approach in which combined information from different independent data was used to accurately detect the health and wellness status of the dairy cows. It can also be implied that an artificial intelligence-based tool such as the proposed theoretical data-mining hub of dairy cows could maximize the use of continuously generated and underutilized data in farms, thus ultimately simplifying repetitive and difficult decision-making tasks in dairy farming.