Estimating risk probabilities for sickness from behavioural patterns to identify health challenges in dairy cows with multivariate cumulative sum control charts

Health Status Classification for Cows Using Machine Learning and Data Management on AWS Cloud

The health and welfare of livestock are significant for ensuring the sustainability and profitability of the agricultural industry. Addressing efficient ways to monitor and report the health status of individual cows is critical to prevent outbreaks and maintain herd productivity. The purpose of the study is to develop a machine learning (ML) model to classify the health status of milk cows into three categories. In this research, data are collected from existing non-invasive IoT devices and tools in a dairy farm, monitoring the micro- and macroenvironment of the cow in combination with particular information on age, days in milk, lactation, and more. A workflow of various data-processing methods is systematized and presented to create a complete, efficient, and reusable roadmap for data processing, modeling, and real-world integration. Following the proposed workflow, the data were treated, and five different ML algorithms were trained and tested to select the most descriptive one to monitor the health status of individual cows. The highest result for health status assessment is obtained by random forest classifier (RFC) with an accuracy of 0.959, recall of 0.954, and precision of 0.97. To increase the security, speed, and reliability of the work process, a cloud architecture of services is presented to integrate the trained model as an additional functionality in the Amazon Web Services (AWS) environment. The classification results of the ML model are visualized in a newly created interface in the client application.

Technological Tools for the Early Detection of Bovine Respiratory Disease in Farms

Simple Summary

The inclusion of remote automatic systems that use continuous learning technology are of great interest in precision livestock cattle farming, since the average size of farms is increasing while time for individual observation is decreasing. Bovine respiratory disease is a main concern in both fattening and heifer rearing farms due to its impact on antibiotic use, loss of performance, mortality, and animal welfare. Much scientific literature has been published regarding technologies for continuous learning and monitoring of cattle’s behavior and accurate correlation with health status, including early detection of bovine respiratory disease. This review summarizes the up-to-date technologies for early diagnosis of bovine respiratory disease and discusses their advantages and disadvantages under practical conditions.

Abstract

Classically, the diagnosis of respiratory disease in cattle has been based on observation of clinical signs and the behavior of the animals, but this technique can be subjective, time-consuming and labor intensive. It also requires proper training of staff and lacks sensitivity (Se) and specificity (Sp). Furthermore, respiratory disease is diagnosed too late, when the animal already has severe lesions. A total of 104 papers were included in this review. The use of new advanced technologies that allow early diagnosis of diseases using real-time data analysis may be the future of cattle farms. These technologies allow continuous, remote, and objective assessment of animal behavior and diagnosis of bovine respiratory disease with improved Se and Sp. The most commonly used behavioral variables are eating behavior and physical activity. Diagnosis of bovine respiratory disease may experience a significant change with the help of big data combined with machine learning, and may even integrate metabolomics as disease markers. Advanced technologies should not be a substitute for practitioners, farmers or technicians, but could help achieve a much more accurate and earlier diagnosis of respiratory disease and, therefore, reduce the use of antibiotics, increase animal welfare and sustainability of livestock farms. This review aims to familiarize practitioners and farmers with the advantages and disadvantages of the advanced technological diagnostic tools for bovine respiratory disease and introduce recent clinical applications.