Investigation of Bovine Disease and Events through Machine Learning Models
Investigation of Bovine Disease and Events through Machine Learning Models
Ghalib Nadeem* and Muhammad Irfan Anis
ABSTRACT
Bovine disease identification utilizing multiple information sources and methods is widely applicate in the field of bovine disease prevention and health monitoring. Bovine disease detection is an emerging subject today to accomplish the farms demands of individuals across the globe. This research delves into the realm of bovine disease and event detection using advanced Machine Learning (ML) techniques. Focusing on the critical events of estrus, acidosis, mastitis, lameness, and calving, our study aims to revolutionize disease identification and timely intervention within the dairy industry. By leveraging four distinct ML models—Random Forest, XGBoost, Logistic Regression, and Single Perceptron we meticulously analyze four diverse data-sets to uncover intricate patterns and unveil hidden insights. The efficiency of random sampling in resolving the class imbalance issue is tested along with the validity and adaptability of these models utilizing GridSearchCV optimum parameter modification. The performance evaluation is based on accuracy, precision, recall, F1 score, and Area Under the Curve (AUC) metrics. With a resounding highest accuracy metric, the Random Forest model achieves a notable accuracy of up to 98.25%, while the recall score of 100, and Precision up to 97% affirming its supremacy in classifying bovine events. This achievement underscores the efficacy of employing ML algorithms for accurate and timely disease identification. This ground-breaking fusion of ML techniques with bovine disease detection holds trans-formative potential, promising to elevate animal welfare standards, optimize dairy productivity, and usher in a new era of data-driven dairy management.
To share on other social networks, click on any share button. What are these?
