Machine Learning in Cyber-Physical Systems in Industry 4.0

Ahmed, Rania; Ali, Elmustafa Sayed; Saeed, Rashid A.

doi:10.4018/978-1-7998-5101-1.ch002

Cited by 18 publications

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 2 presents the training and testing dataset, and Figure 3 presents the visual representation of the training and testing dataset. The UNB dataset contains normal, back-door, worms, reconnaissance, fuzzers, DoS, shell code, exploits, and generic data attributes [23]. The dataset includes 38,500 normal records, 950 back-doors, 174 worms, 978 reconnaissance, 7500 fuzzers, 4800 DoS, 978 shellcode, 12,440 exploits, and 18,554 generic.…”

Section: Unw-nb15mentioning

confidence: 99%

HIDM: Hybrid Intrusion Detection Model for Industry 4.0 Networks Using an Optimized CNN-LSTM with Transfer Learning

Lilhore,

Manoharan,

Simaiya

et al. 2023

Sensors

View full text Add to dashboard Cite

Industrial automation systems are undergoing a revolutionary change with the use of Internet-connected operating equipment and the adoption of cutting-edge advanced technology such as AI, IoT, cloud computing, and deep learning within business organizations. These innovative and additional solutions are facilitating Industry 4.0. However, the emergence of these technological advances and the quality solutions that they enable will also introduce unique security challenges whose consequence needs to be identified. This research presents a hybrid intrusion detection model (HIDM) that uses OCNN-LSTM and transfer learning (TL) for Industry 4.0. The proposed model utilizes an optimized CNN by using enhanced parameters of the CNN via the grey wolf optimizer (GWO) method, which fine-tunes the CNN parameters and helps to improve the model’s prediction accuracy. The transfer learning model helps to train the model, and it transfers the knowledge to the OCNN-LSTM model. The TL method enhances the training process, acquiring the necessary knowledge from the OCNN-LSTM model and utilizing it in each next cycle, which helps to improve detection accuracy. To measure the performance of the proposed model, we conducted a multi-class classification analysis on various online industrial IDS datasets, i.e., ToN-IoT and UNW-NB15. We have conducted two experiments for these two datasets, and various performance-measuring parameters, i.e., precision, F-measure, recall, accuracy, and detection rate, were calculated for the OCNN-LSTM model with and without TL and also for the CNN and LSTM models. For the ToN-IoT dataset, the OCNN-LSTM with TL model achieved a precision of 92.7%; for the UNW-NB15 dataset, the precision was 94.25%, which is higher than OCNN-LSTM without TL.

show abstract

Section: Unw-nb15mentioning

confidence: 99%