Voting Classifier and Metaheuristic Optimization for Network Intrusion燚etection

Managing physical objects in the network’s periphery is made possible by Internet of Things (IoT), revolutionizing human life. Open attacks and unauthorized access are with these IoT devices, which exchange data to enable remote access. These often detected using intrusion detection methodologies, although systems’ effectiveness accuracy subpar. This paper proposes a new voting classifier composed an ensemble machine learning models trained optimized metaheuristic optimization. The employed optimizer version whale optimization algorithm (WOA), guided dipper throated (DTO) improve exploration process ofthe traditional WOA optimizer. proposed categorizes network intrusions robustly efficiently. To assess approach, dataset created from devices record efficiency for binary attack categorization. records balanced locality-sensitive hashing (LSH) Synthetic Minority Oversampling Technique (SMOTE). evaluation achieved results performed terms statistical analysis visual plots prove approach’s effectiveness, stability, significance. confirmed superiority task detection.