<![CDATA[Environmental concerns have led to a growing focus on sustainability in computing systems, from small devices to big data centers. At the same time, technologies like resource-intensive encryption and sophisticated intrusion detection systems are necessary to provide cybersecurity in these linked networks. Artificial intelligence (AI) is changing how the world works, and innovative products are the end consequence. AI and the Internet of Things (IoTs) enable several brilliant advances that make up a smart city. The concept highlights a smart city's simplicity and comfort, but its growth is hampered by several security issues that are being brought up. An intrusion detection system (IDS) monitors network traffic and notifies users of abnormalities. A method based on machine learning, IDS makes decisions regarding the legibility of data packets, detects network threats intelligently, and notifies the user. Researchers have used a variety of machine-learning techniques to increase the detection accuracy of IDS. A comparison of several machine learning algorithms trained over the NSL-KDD dataset. XG Boost, Random forest K-Nearest Neighbors KNN and Logistic Regression are simulated, which generates excellent performance accuracies (99.92%, 99.86%, 99.57%, and 88.05%). It has been observed that the LR model has the lowest accuracy among the different models, while the XGB model has the highest accuracy]]>
Copyrights © 2025
