Machine Learning Approaches to Intrusion Detection in Cloud Computing for Healthcare Cybersecurity

Background: Utilizing cloud technology in the healthcare sector has completely changed how patient data is stored, retrieved, and shared while improving scalability and costefficiency. In this environment, however, it is crucial to ensure network security. Objective: Intrusion Detection Systems (IDS) continuously monitor network traffic and system activities to detect and neutralize possible threats. This helps preserve patient privacy and the reliability of healthcare delivery systems. We proposed Machine learning classifiers. Methods: The machine learning classifiers used four feature selection techniques: Logistic Regression, naive Baye, Decision Tree, and K-nearest neighbors with the Adam optimization method. Finally, we used the Django framework to deploy the trained model. Results: In experimental work, the NSL-KDD dataset and CICIDS-2017 dataset are used. The models were trained and tested using the same datasets to ensure consistency in data preparation. Conclusion: When the classification accuracy of the four distinct classifiers is compared, the suggested optimized Decision Tree classifier performs better.