In Industrial Internet of Things (IIoT), while improving the quality of products, the growth of smart devices also generates a huge quantity of network traffic data, which is mixed with part of the unknown attack traffic, which will pose a certain threat to industrial products and user privacy. To ensure the security of IIoT (Industrial Internet of Things) network, this paper proposes a Whale Optimization Algorithm-eXtreme Gradient Boosting (WOA-XGBoost) intelligent network traffic anomaly detection algorithm combined with the Extremely Randomized Trees Classifier (ExtraTreesClassifier) and Synthetic Minority Over-sampling Technique-Edited Nearest Neighbors (SMOTE-ENN) Resampling Technique for feature selection and dealing with data imbalance. Meanwhile, SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) methods are introduced to conduct an in-depth study of the network traffic anomaly detection model to analyze the impact of key features and the operation principle. To validate the credibility and extensiveness of the model, the model is validated on RT-IoT2022 dataset and UCI public dataset, and in RT-IoT2022 dataset, the model performances Accuracy, Recall, Precision, F1 Score, and G-mean are 0.9985, 0.9997, 0.9974, 0.9985 and 0.9985, and the values of each index on the five UCI datasets are all above 0.85. Meanwhile, this paper compares the model with the common mathematical detection models, and the model performance indexes of this paper are all the highest, the model in this paper can more accurately detect anomalous network traffic, and it can be proposed as an effective artificial intelligence numerical model for network traffic anomaly detection to realize the IIoT in the Intelligent management of network traffic security.

In the production process of hot rolled strip steel plate, the Industrial Internet of Things (IIoT) improves the quality and efficiency of production and manufacturing products, but also because of the large amount of data generated by its equipment, resulting in a significant decline in plate crown fault diagnosis and decision-making ability. To improve the yield and quality of hot strip steel plate, in this paper, an intelligent algorithm based on the Hippopotamus optimization algorithm-Kernel Extreme Learning Machine (HOA-KELM) is proposed. Adaptive synthetic sampling technology (ADASYN) resampling technique is used to deal with multi-class unbalance of data. At the same time, InterpretML and SHapley additive stripping (SHAP) methods based on game theory were introduced to analyze the crown diagnosis model of hot strip, and the influencing factors of the strip in hot rolling were studied. To verify the applicability of the model, the model was tested on the hot rolling production data set and UCI data set. In the hot rolling data set, the model performance Kappa Coefficient, F1 Score, and Accuracy were 0.988, 0.993, and 0.992, respectively, indicating a good effect. It is compared with the common mathematical model. The findings indicate that this model significantly outperforms the conventional approach in solving the problem of strip convexity diagnosis in the hot rolling process, and can be proposed as an effective mathematical model for plate convexity diagnosis to realize the intelligent management of industrial production.

Deep neural networks (DNNs) are critical for obstacle recognition in autonomous driving, commonly used to classify objects like vehicles and animals. However, DNNs are vulnerable to adversarial attacks that can cause misclassifications and compromise system safety. To address this, we propose the Adaptive Multi-Scale Positional Encoding Parallel Attention Network (APANet), a model designed to enhance adversarial robustness. APANet includes four main components: multi-scale feature map generation, Adaptive Multi-Scale Positional Encoding (AMSPE), Parallel Attention (PA), and multi-scale feature fusion. AMSPE embeds adaptive positional information and captures long-range dependencies to boost resistance to adversarial perturbations. PA independently processes multi-scale features, enhancing feature utilization and isolating adversarial noise. These components work synergistically to improve the model’s robustness. Experiments show APANet significantly outperforms several state-of-the-art models in Top-1 accuracy under various adversarial attacks and on clean samples. Specifically, AMSPE contributes a 4.13-point improvement in adversarial accuracy and narrows the clean-adversarial performance gap by 4.73 points, while PA improves recognition accuracy by 6.11 points. To validate real-world robustness, we tested APANet on the German Traffic Sign Recognition Benchmark (GTSRB), where adversarial interference can critically affect autonomous driving. APANet demonstrates high accuracy and robustness under adversarial scenarios on GTSRB, confirming its effectiveness in enhancing the safety and reliability of autonomous driving systems.

A rational approach to predict passenger car sales and analyze the current state of the passenger car sales market can contribute to the healthy development of the automotive industry. The number of features used to describe passenger car sales in real life is too redundant. The features of human empirical filtering and combination cause loss of time. In addition, explicit features are too homogeneous, which need to be complemented by implicit features. The fixed-parameter weights in the trained model cannot provide some estimates for unknown uncertainties. Therefore, in this work, we propose a DeepFM-based nonparametric model (DFMNP) for predicting passenger car sales in sustainable way. We use a big data platform to provide data for the DFMNP model. The DFMNP model uses feature engineering to expand the number of explicit features, a multilayer neural network to extract implicit features, and a Bayesian neural network to replace the neural network with fixed weights for inferring predictive values. In addition, a factorization machine is used in the prediction function to take into account the cross information of implicit features. The combination of the above improvement points can be used to improve the model’s expressive and predictive power for unknown data. Its prediction performance on two real passenger car sales datasets is as follows, RMSE values of 0.0825 and 0.116, and MAE values of 0.0482 and 0.0595. The above experimental results verify the superiority of the method proposed in this work.