Monitoring dairy calves using precision dairy science (PDS), which is the use of technology to measure physiological and behavioral indicators of individual farm animals, if based on the “internet of things” (IoT) and machine learning (ML) can lead to early detection of calf-killing bovine respiratory disease, according to a study conducted by researchers from Penn State, University of Kentucky, and the University of Vermont. This innovative approach has the potential to improve economic outcomes for dairy producers. The study’s lead researcher, an assistant professor of PDS at Penn State, explained that advancements in technology have made it more affordable for farmers to detect animal health problems early, saving calves and lowering costs.
The IoT refers to embedded devices equipped with sensors, processing, and communication abilities, which enables them to connect and exchange data with other devices online. In this study, wearable sensors and automatic feeders were employed as IoT technologies to closely monitor and analyze the condition of dairy calves. These devices generated large amounts of data by observing the cows’ behaviors. To make this data more accessible and provide insights into calf health issues, the researchers incorporated ML, a branch of artificial intelligence that identifies hidden patterns in data. By using input from IoT devices, ML algorithms distinguished between sick and healthy calves.
The study’s lead researcher said, “We attached leg bands to the calves, which recorded their activity behavior data, such as the number of steps and lying time. We also utilized automatic feeders, which dispense milk and grain while recording feeding behaviors, including the number of visits and liters of consumed milk. Information from these sources alerted us when a calf’s condition was deteriorating.”
Bovine respiratory disease is a common infection in the respiratory tract and is the leading cause of antimicrobial use in dairy calves. Additionally, it is responsible for 22% of calf mortalities. The financial and practical implications of this ailment are significant for dairy farms, as raising calves is a major investment. Until now, diagnosing bovine respiratory disease requires skilled and specialized labor that is difficult to find. IoT devices, such as automatic feeders, scales, and accelerometers, can help detect behavioral changes in calves before the disease displays traditional outward clinical signs.
The study involved 159 dairy calves, and data was collected using PDS livestock technologies and daily physical health exams performed by the researchers at the University of Kentucky. Both automatic data collection and manual data collection were utilized, and their results were compared. The researchers reported their findings in IEEE Access, a peer-reviewed scientific journal, that this approach successfully identified calves that developed bovine respiratory disease earlier. The system accurately labeled sick and healthy calves with an 88% accuracy rate. Most notably, they were able to predict 70% of sick calves four days before diagnosis and detected 80% of calves that developed a chronic form of the disease within the first five days of sickness.
Earlier studies revealed that behavioral changes in sick and recovering calves differed significantly. This prompted the idea that IoT technologies empowered with machine learning could identify these changes sooner than can be observed by the naked eye. Such advancements offer producers additional options to address calf health issues.
The institutions participating in this research consisted of the Department of Animal and Dairy Science at the University of Wisconsin-Madison, the Department of Animal Science at Penn State University, the Department of Animal and Food Sciences at the University of Kentucky, the Department of Computer Science at the University of Kentucky, and the Department of Animal and Veterinary Sciences at the University of Vermont. Support for this work was provided by the U.S. Department of Agriculture and the National Science Foundation.
The whytry.ai article you just read is a brief synopsis; the original article can be found here: Read the Full Article…
