Search

Simple Summary: Rumination behavior is a crucial indicator of cattle health and welfare. The timely monitoring and analysis of this behavior can provide valuable insights into the physiological status of the animals. Distinguishing from manual observation and wearable devices, this study proposes a method using video technology for monitoring cattle rumination behavior. This method aims to track physiological indicators during rumination, including chewing count, rumination duration, and chewing frequency. This approach can help livestock managers promptly understand the health status of cattle. Furthermore, this research method offers a new perspective for the construction of smart farming, providing technical support for the intelligent transformation of the livestock industry. Cattle rumination behavior is strongly correlated with its health. Current methods often rely on manual observation or wearable devices to monitor ruminating behavior. However, the manual monitoring of cattle rumination is labor-intensive, and wearable devices often harm animals. Therefore, this study proposes a non-contact method for monitoring cattle rumination behavior, utilizing an improved YOLOv8-pose keypoint detection algorithm combined with multi-condition threshold peak detection to automatically identify chewing counts. First, we tracked and recorded the cattle's rumination behavior to build a dataset. Next, we used the improved model to capture keypoint information on the cattle. By constructing the rumination motion curve from the keypoint information and applying multi-condition threshold peak detection, we counted the chewing instances. Finally, we designed a comprehensive cattle rumination detection framework to track various rumination indicators, including chewing counts, rumination duration, and chewing frequency. In keypoint detection, our modified YOLOv8-pose achieved a 96% mAP, an improvement of 2.8%, with precision and recall increasing by 4.5% and 4.2%, enabling the more accurate capture of keypoint information. For rumination analysis, we tested ten video clips and compared the results with actual data. The experimental results showed an average chewing count error of 5.6% and a standard error of 2.23%, verifying the feasibility and effectiveness of using keypoint detection technology to analyze cattle rumination behavior. These physiological indicators of rumination behavior allow for the quicker detection of abnormalities in cattle's rumination activities, helping managers make informed decisions. Ultimately, the proposed method not only accurately monitors cattle rumination behavior but also provides technical support for precision management in animal husbandry, promoting the development of modern livestock farming. [ABSTRACT FROM AUTHOR]

Simple Summary: Discovering estrus biomarkers is of utmost importance to develop an easy, reliable, and accurate estrus detection method in dairy cows. The proteomics approach is an attractive and powerful tool and recently has been used to explore proteomic alterations in a variety of bodily fluids to identify the relative biomarkers. Milk produced by dairy cows is a complex biofluid consisting of hundreds of different components that may be a good source for biomarker discovery. In this study, the proteomics approach was performed on milk sampled from estrus and non-estrus dairy cows to identify potential biomarkers of estrus, which may be helpful for further development of an easy and reliable estrus detection method in dairy cows. Efficient reproductive management of dairy cows depends primarily upon accurate estrus identification. However, the currently available estrus detection methods, such as visual observation, are poor. Hence, there is an urgent need to discover novel biomarkers in non-invasive bodily fluids such as milk to reliably detect estrus status. Proteomics is an emerging and promising tool to identify biomarkers. In this study, the proteomics approach was performed on milk sampled from estrus and non-estrus dairy cows to identify potential biomarkers of estrus. Dairy cows were synchronized and timed for artificial insemination, and the cows with insemination leading to conception were considered to be in estrus at the day of insemination (day 0). Milk samples of day 0 (estrus group) and day −3 (non-estrus group) from dairy cows confirming to be pregnant were collected for proteomic analysis using the tandem mass tags (TMT) proteomics approach. A total of 89 differentially expressed proteins were identified, of which 33 were upregulated and 56 were downregulated in the estrus milk compared with the non-estrus milk. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis showed that acetyl coenzyme A carboxylase α (ACACA), apolipoprotein B (APOB), NAD(P)H steroid dehydrogenase-like (NSDHL), perilipin 2 (PLIN2), and paraoxonase 1 (PON1) participated in lipid binding, lipid storage, lipid localization, and lipid metabolic process, as well as fatty acid binding, fatty acid biosynthesis, and fatty acid metabolism, and these processes are well documented to be related to estrus regulation. These milk proteins are proposed as possible biomarkers of estrus in dairy cows. Further validation studies are required in a large population to determine their potential as estrus biomarkers. [ABSTRACT FROM AUTHOR]