Relating different Artificial Intelligence approaches for Animals disease outbreak detection

Abstract

The past two years have witnessed a worrying surge in animal disease outbreaks, with African swine fever, foot-and-mouth disease, and bird flu wreaking havoc on animal populations and human livelihoods. Millions of animals have succumbed to these highly contagious diseases, causing severe economic losses, disrupting livestock industries, and threatening global food security. Data reveals the alarming occurrence, distribution, and impact of these outbreaks, while highlighting the challenges in controlling them and the potential public health risks. Innovative approaches like AI-powered disease models and international cooperation are crucial to tackle this crisis and mitigate future threats. The abstract is about finding disease outbreak of different natures, so we can predict it before it is going to hit in future. By integrating existing information with the potential of cutting-edge solutions of Artificial Intelligence and Machine learning, our models of SVM with accuracy and precision of 0.9041%, recall 1.0 and ROC AUC of 0.05. The confusion matrix indicates 0 true positive predictions and 0 false negative predictions. These are the models used and results are mentioned respectfully. KNN with accuracy of 99%, precision of 1.0, Recall 0.99% and ROC AUC of 0.99%. The confusion matrix indicates 489 true positive predictions and 4 false negative predictions Naive Bayes with accuracy of 0.99, precision of 1.0, recall and ROC AUC 0.99. The confusion matrix indicates 489 true positive predictions and 37 false negative predictions.