|
AUTHOR(S): Amjad Jumaah Frhan, Ali L. A. Al-Zaidi
|
TITLE |
 PDF |
ABSTRACT The Industrial Internet of Things (IIoT) presented up new safety obstacles especially how to keep safe networks as well as edge endpoints. The ever-changing nature and complexity of IIoT communications makes traditional Intrusion Detection Systems (IDS) inadequate. Using Artificial Neural Networks (ANNs) and Machine Learning (ML) on the Edge-IIoTset dataset, this study presents an IDS hybrid model in this study. Improving detection performance and reducing false alarms are achieved through the employment of ML-DL algorithms. Investigations show that a combined approach may reach high levels of accuracy, recall, and precision when compared with solo methods. Statistics and information tables show the model's competence and validation in specific IIoT scenarios. |
KEYWORDS Artificial Neural Networks, Cybersecurity, Internet of Things, Machine Learning, SVM and XGBoost |
|
Cite this paper Amjad Jumaah Frhan, Ali L. A. Al-Zaidi. (2026) A Robust Hybrid Intrusion Detection Approach for Industrial IoT Networks Based on the Edge-IIoTset Dataset. International Journal of Internet of Things and Web Services, 11, 11-16 |
|
