An Ensemble Tree-Based Model for Intrusion Detection in Industrial Internet of Things Networks

Abstract

With less human involvement, the Industrial Internet of Things (IIoT) connects billions of heterogeneous and self-organized smart sensors and devices. Recently, IIoT-based technologies are now widely employed to enhance the user experience across numerous application domains. However, heterogeneity in the node source poses security concerns affecting the IIoT system, and due to device vulnerabilities, IIoT has encountered several attacks. Therefore, security features, such as encryption, authorization control, and verification, have been applied in IIoT networks to secure network nodes and devices. However, the requisite machine learning models require some time to detect assaults because of the diverse IIoT network traffic properties. Therefore, this study proposes ensemble models enabled with a feature selection classifier for Intrusion Detection in the IIoT network. The Chi-Square Statistical method was used for feature selection, and various ensemble classifiers, such as eXtreme gradient boosting (XGBoost), Bagging, extra trees (ET), random forest (RF), and AdaBoost can be used for the detection of intrusion applied to the Telemetry data of the TON_IoT datasets. The performance of these models is appraised based on accuracy, recall, precision, F1-score, and confusion matrix. The results indicate that the XGBoost ensemble showed superior performance with the highest accuracy over other models across the datasets in detecting and classifying IIoT attacks.

Enhancing Retail Transactions: A Data-Driven Recommendation Using Modified RFM Analysis and Association Rules Mining

“…Association rule mining (ARM) is widely utilized in a multitude of industries, such as market basket research [8,23], stock market analysis [24], recommendation systems [7,19,22,[25][26][27], healthcare [28,29], and more [30]. This powerful technique plays a pivotal role in aiding organizations in making informed decisions [8,22,25,26], improving customer experience [7,19], and implementing preventive strategies [28,29].…”

“…Both methods aim to enhance predictive accuracy and robustness by combining the predictions of multiple base models [18]. Bagging trains multiple instances of the same base model on different subsets of the training data [24,25], while AdaBoost focuses on misclassified samples and assigns higher weights to them during training [24,26]. Doing so allows weaker models to adapt and improve over time.…”

“…Bagging reduces model variance while maintaining or improving bias, making it effective for small datasets or models prone to overfitting [25]. On the other hand, Ad-aBoost reduces model bias while maintaining or improving variance, making it suitable for more complex models [24].…”

“…Such a process is repeated for a predefined number of iterations or until the desired level of accuracy is achieved. The final prediction is obtained by averaging or voting on the predictions of each model, creating a weighted mixture of the weak learners' forecasts [24,26].…”

Explaining Xgboost Predictions With Shap Value: A Comprehensive Guide to Interpreting Decision Tree-Based Models

“…Feature Importance using Tree-Based Models: This method involves using decision treebased models such as Random Forest, XGBoost, or Gradient Boosting, to determine the importance of each feature in the model. The importance of features is measured based on their contribution to reducing impurity or error in the model (Liu & Aldrich, 2023;Kim et al, 2023;Awotunde et al, 2023).…”