article · Big Data Mining and Analytics
Industrial Internet of Things systems embed connected technologies into manufacturing operations, but they face severe security vulnerabilities. Intrusion detection systems help monitor these environments in real time to prevent damaging attacks. To improve detection performance and lower computational costs, an intrusion detection framework combines feature engineering with machine learning. The approach couples Isolation Forest for outlier detection and removal with Pearson's Correlation Coefficient for feature selection, testing both sequencing combinations. A Random Forest classifier then identifies threats. Evaluated on the Bot-IoT and NF-UNSW-NB15-v2 benchmark datasets, the configurations achieve high detection accuracy alongside rapid prediction times. Testing demonstrates over 99.9 percent accuracy on Bot-IoT and above 99.1 percent accuracy on NF-UNSW-NB15-v2, completing predictions in under seven seconds. These results show measurable performance advantages over related detection models.
Industrial networks control vital manufacturing infrastructure, making cyber intrusions exceptionally dangerous. Automated detection systems that accurately spot malicious behaviour in real time without causing heavy computational delays are essential. By refining data inputs before classification, security tools can process network traffic rapidly and reliably, protecting connected industrial machinery from disruptive attacks without overburdening computational resources.
The model is aimed at safeguarding industrial networks and manufacturing environments using embedded Internet of Things devices. Potential users include industrial facility operators and cybersecurity teams managing automated manufacturing plants. Because validation is currently limited to benchmark network datasets such as Bot-IoT and NF-UNSW-NB15-v2, the technology represents applied and tested research that requires further evaluation in live operational environments before reaching commercial deployment.
AI-generated from the published abstract. Always read the original work before citing.
Industrial Internet of Things (IIoT) represents the expansion of the Internet of Things (IoT) in industrial sectors. It is designed to implicate embedded technologies in manufacturing fields to enhance their operations. However, IIoT involves some security vulnerabilities that are more damaging than those of IoT. Accordingly, Intrusion Detection Systems (IDSs) have been developed to forestall inevitable harmful intrusions. IDSs survey the environment to identify intrusions in real time. This study designs an intrusion detection model exploiting feature engineering and machine learning for IIoT security. We combine Isolation Forest (IF) with Pearson's Correlation Coefficient (PCC) to reduce computational cost and prediction time. IF is exploited to detect and remove outliers from datasets. We apply PCC to choose the most appropriate features. PCC and IF are applied exchangeably (PCCIF and IFPCC). The Random Forest (RF) classifier is implemented to enhance IDS performances. For evaluation, we use the Bot-IoT and NF-UNSW-NB15-v2 datasets. RF-PCCIF and RF-IFPCC show noteworthy results with 99.98% and 99.99% Accuracy (ACC) and 6.18s and 6.25s prediction time on Bot-IoT, respectively. The two models also score 99.30% and 99.18% ACC and 6.71 s and 6.87s prediction time on NF-UNSW-NB15-v2, respectively. Results prove that our designed model has several advantages and higher performance than related models.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.26599/bdma.2022.9020032
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
