Predictive modelling for rabbit health monitory system using machine learning techniques

The early detection and continuous monitoring of rabbit health are vital for improving animal welfare, reducing mortality, and enhancing farm productivity. This research presents a predictive modelling framework for rabbit health monitoring using machine learning techniques, specifically Logistic Regression, Random Forest, and K-Nearest Neighbors (KNN). The proposed system integrates a structured data pipeline encompassing data preprocessing, feature engineering, vector representation, model training, and evaluation. A dataset comprising physiological and behavioral features was collected and used to train and test the models. Evaluation metrics such as accuracy, precision, recall, F1 score, and ROC-AUC were employed to assess model performance. Among the three models, Random Forest achieved the highest performance with an accuracy of 99%, F1 score of 99.16%, and ROC-AUC of 99.96%, demonstrating exceptional capability in detecting unhealthy rabbits. KNN and Logistic Regression also performed reasonably well but showed limitations in sensitivity and overall predictive power. The findings suggest that Random Forest is the most reliable model for real-time health monitoring in rabbits, offering a promising tool for smart farming and veterinary applications.