A novel lightweight hybrid deep learning system for real-time network traffic anomaly detection

This study proposes a network traffic monitoring and anomaly detection system implemented on a Raspberry Pi platform, integrating advanced deep learning techniques. To effectively detect anomalous behaviors and enable rapid response, the system employs a hybrid deep learning model that combines convolutional neural networks with long short-term memory networks. Beyond fulfilling the requirements for low-cost and portable deployment, the Raspberry Pi platform demonstrates that computationally intensive, artificial intelligence (AI)-based security tasks can be executed in resource-constrained environments. Experimental results indicate that the proposed AI-driven detection system achieves superior overall performance: it significantly outperforms traditional approaches in terms of detection accuracy and response speed, while the robustness of the deep learning model ensures a very low false positive rate.