An Optimized Ensemble Approach with Feature Selection for Network Intrusion Detection in the Internet of Vehicles

In the modern digital age, technological advancements have led to unprecedented connectivity, notably with the rise of connected networks that integrate vehicles into the Internet of Vehicles (IoV), thereby heightening the risk of cyber threats. Network Intrusion Detection Systems (NIDS) are crucial for protecting these systems by identifying and mitigating unauthorized access. Traditional machine learning techniques, though effective, often struggle with sophisticated and evolving threats. This study introduces an Optimized Ensemble approach for enhanced intrusion detection in the IoV. Our approach, the Optimized Random Forest (Opt-Forest), combines Decision Forest approaches with Genetic Algorithms (GAs) to improve detection accuracy. Feature selection methods, including Best-First Search, Particle Swarm Optimization, Evolutionary Search, and Genetic Search, are employed to boost the model’s adaptability and resilience against modern threats. We evaluated our approach against established machine learning models like K-Nearest Neighbor (KNN), J48-Decision Tree (J48), and Multilayer Perceptron (MLP). The results demonstrate the superior performance of our approach across various metrics, highlighting its potential to significantly enhance network intrusion detection in the IoV environment.