Hybrid XGBoost-CNN Model for Anomaly Detection: A New Approach for IoT Wireless Sensor Networks

The Internet of Things (IoT) continues to expand rapidly, resulting in increasingly heterogeneous and complex wireless sensor networks (WSNs). Traditional anomaly detection approaches cannot cope with dynamic traffic patterns, high data volumes, and strict resource constraints. This study presents a hybrid XGBoost-CNN model that integrates XGBoost-based feature selection with a lightweight Convolutional Neural Network optimized for IoT environments. The proposed model was evaluated using real-world IoT traffic data and benchmarked against XGBoost, KNN, and SVM. Experimental results show that the hybrid approach improves detection accuracy by up to 2.29%, increases throughput by 8-48%, and reduces computational cost by 3%-8% compared with the baseline models. The model also demonstrated higher energy efficiency under varying attack scenarios. These results indicate that combining the feature selection capabilities of XGBoost with the pattern extraction strength of CNN yields a scalable, accurate, and resource-efficient anomaly detection solution suitable for IoT-WSN devices.