A Framework for Classifying Threats in Nigeria’s Healthcare System Leveraging on NSL-KDD dataset
The Random Forest (RF) classifier proved highly effective in classifying threats within Nigeria’s healthcare system, achieving an outstanding accuracy of 99.93% and an AUC score of 1.0, indicating excellent discrimination between threat classes. In contrast, the Naive Bayes classifier struggled with the dataset's complexity, with a significantly lower accuracy of 39.62% and an AUC of 0.7419. The RF model's superior performance suggests it is well-suited for accurately identifying and categorizing potential threats in the healthcare system.