To address the issues of high noise levels, low contrast, and insufficient clarity in pellet CT images—particularly given the demand for high-quality images during 3D reconstruction a pellet image resolution enhancement model based on MSEEGAN(Multi-Scale Edge Enhanced GAN) is proposed. Current image enhancement methods still face limitations in denoising, edge clarity improvement, and adaptability to industrial applications. Traditional approaches struggle to effectively remove complex noise, while deep learning-based techniques may result in the loss of texture information and involve high computational costs, making practical deployment challenging. This study adopts an end-to-end training approach to enhance the discriminability of material regions. During the generation process, edge enhancement loss and pixel attention are introduced to optimise boundary clarity, while multi-scale discrimination and edge-aware loss are incorporated to improve detail representation. Experimental results show that MSEEGAN significantly outperforms other methods in metrics such as AG (87.5), IE (7.01), AEC (7,103,909), and EPR (0.178), enhancing image edge clarity and contrast, and providing higher-quality data for 3D reconstruction. Moreover, the integration of the Industrial Internet of Things (IIoT) framework spans the entire process—from pellet production and computed tomography (CT) scanning to image enhancement and 3D reconstruction—facilitating end-to-end digital management and advancing the intelligent and efficient development of pellet production.

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.

Real-time object detection plays a critical role in advancing autonomous driving technologies. To meet the demands for real-time performance, a lightweight model is essential to reduce parameter size, simplify complexity, and enhance detection speed. This paper presents YOLO-FSE, a compact vehicle detection model built upon the YOLOv5 framework. In YOLO-FSE, the C3 module is substituted with the C3faster module from the FasterNet lightweight architecture. The backbone network is augmented with the Shuffle Attention module, which improves feature fusion by separating spatial and channel attention mechanisms. Additionally, the original loss function is replaced by EIoU loss, which directly penalizes width and height predictions, thereby improving the model’s generalization ability. During experimentation, it was assumed that the number of test images was sufficiently large and clear, with PyTorch serving as the primary framework for model development and training. Experimental results show that, on the UA-DETRAC and BIT-Vehicle datasets, the mean average precision (mAP) achieved 98.9% and 97.6%, respectively. Computational complexity (FLOPs) was reduced by 12.65%, while the average frame rate (Fps) increased by 46.13%. Overall, the enhanced model exhibits substantial improvements in both speed and performance, demonstrating its potential for deployment in autonomous driving applications.

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.

The current unreasonable deployment mechanism of shared bikes makes it difficult to meet public demand. Accurate prediction of shared bikes demand can alleviate this problem, but current prediction models are limited by small data size and poor robustness, making them unable to provide sufficiently accurate prediction to be applied in real-life situations. In this work, we propose a generative adversarial networks (GAN)-based ensemble model (GANEM) for predicting the demand of shared bikes in 5G networks to solve the above problem. With the support of 5G networks, real-time transmission and storage of traffic data of shared bikes have become reality. We then use these data to train the GANEM model to have better generalization performance. The GANEM model first uses GAN to learn the data features of existing shared bikes demand to generate new training samples. We borrow the idea of ensemble learning, three benchmark predictors are integrated to fully exploit the association between explicit features, which can improve the robustness of the model. Excellent prediction results are achieved on two real datasets. The experimental results of our proposed GANEM model on two datasets are as follows, the values of MAE are 0.120 and 0.144, the values of MSE are 0.027 and 0.032, the values of RMSE are 0.164 and 0.181.

Currently, the effective technologies used to protect the security of the Internet of Things (IoT) include blockchain and intrusion detection systems (IDSs). The traditional IoT IDSs based on supervised learning usually requires a large amount of data for training, with high costs, and most of them can only work in several specific types of attacks. Faced with the variability of current IoT attack methods and the complexity of the network environment, they are usually unable to play a role in a short time. Especially in dealing with new security problems such as Zero-day attacks, which have a small number of learnable samples. Therefore, this article proposed an IoT intrusion detection model to deal with the situation where learnable samples are insufficient. The model adopts the idea of meta-learning and divides the training process into two layers based on model-agnostic meta-learning. Its purpose is to train a relatively general model using the malicious network flow data of various known attack modes. To this end, a few-shot IoT intrusion detection data set, FSIDS-IoT, is constructed based on five data sets, namely, CIC-DDoS2019, CIC-IDS2017, CSE-CIC-IDS2018, NSL-KDD, and UNSW-NB15. Experiments show that our proposed approach, using only a few gradient steps and a small amount of training data from the new attack type, can perform well to protect cyber security. In the test of identifying unknown attacks, the optimal accuracy under the 5-way 1-shot setting reached 78.26%, 90.09% under the 5-way 5-shot setting, and 92.19% under the 5-way 10-shot setting.

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.

In recent years, pedestrian and vehicle detection at night has become an important subject of computer vision applications. Because the environment light is weak at night, the common traditional camera-input algorithms often performs poorly. Pedestrians and vehicles in infrared images are usually brighter than the surrounding environment and have salient features. In this paper, a fast saliency map of pedestrian and vehicle targets in infrared images at night is used to achieve rapid acquisition of areas of interest for pedestrians and vehicles. Based on this, we propose a method to refine and separate the target area to obtain accurate pedestrian and vehicle candidate bounding boxes. Specifically, this paper proposed a multi-feature fusion algorithm of pedestrian and vehicle feature extraction combined with support vector machine (SVM) to determine whether the extracted target area really includes pedestrians and vehicles. Our experimental results show that the proposed method can achieve the expected effect of the classification and detection for pedestrians and vehicles at night, and can meet the real-time requirements of actual road scenarios.

In recent years, deep learning has been widely used in the field of image visualization, and has attracted the attention of researchers. The main component of iron tailings is SiO2, In the process of quenching and tempering slag from iron tailings, melted SiO2particles will randomly walk in the crucible, therefore, how to intelligently identify and track targets (SiO2particles) in sequence image to promote the low consumption and efficient production of high value-added slag cotton has become an urgent problem. Aims at the temperature requirements of slag cotton preparation process, using intelligent algorithm with deep learning and hierarchical clustering, in-depth analysis of the visual information of the high temperature melting process of SiO2particles. Through centroid tracking and positioning technology, intelligent edge feature extraction technology and fitting method of experimental data through high temperature melting process of SiO2particles quantitative characterization functions of visual characteristics of SiO2particles melting process under high temperature environment were obtained in this article. Approximation of the melting process of iron tailings in high temperature environments and embed this function into the static mathematical model of process thermal compensation an accurate thermal dynamic intelligent compensation model for slag cotton preparation process is realized.

Secondary use of medical big data is becoming increasingly popular in healthcare services and clinical research in the medical industry. Cancer recurrence is a common phenomenon of cancer patients after treatment (recovery period). Studying the time and influencing factors of cancer recurrence can provide effective clinical intervention means, which is the gospel of cancer patients. In this article, a sample of 50 000 cases of seven cancer patients, including liver cancer, lung cancer, kidney cancer, breast cancer, uterine cancer, stomach cancer, and bowel cancer, was collected. A twin support regression vector machine (TSVR) algorithm based on dependent nearest neighbor (DNN) weighting is proposed, the eplion-TSVR model is improved by DNN-weighted algorithm with local information mining function, and the solution of the improved model is derived. It is proposed to use the cuckoo algorithm to determine the optimal parameters of DNN to determine the optimal dependency region domain. In this article, the improved TSVR algorithm is used to establish a cancer recurrence prediction model. The prediction accuracy of the model for various cancers can reach more than 91%, which is significantly higher than that of convolutional neural network and e-TSVR models.

In the future, pellet is gradually replacing sinter as the main charge structure of blast furnace ironmaking. In the process of pellet production, the linear regulate and control method is often used in the operation of proportioning scheme, roasting regime, and parameter setting. There are some problems such as low pelletizing rate and poor compressive strength. It is urgent to realize the intelligent pellet manufacturing. In order to realize an intelligent pellet material matching system, the general regression neural network is applied to construct the prediction model of mature pellets compressive strength under the technical framework of industrial Internet of Things (IoT), using beetle antennae search (BAS) algorithm to construct an intelligent recommendation model of pellets with optimal proportioning. The prediction model and the intelligent recommendation model are coupled within the technical framework of IoT. An IoT system of pellet material proportion is implemented, which is dominated by the compressive strength of mature pellet. The system can realize automatic detection of raw materials, automatic quantification processing of index data, automatic start of prediction model, visualization of proportioning results, and “one-click” operation of proportioning scheme. Recommended system simulation and experimental results show that the prediction model of the compressive strength of cooked balls has the strong interpolation ability and the excellent generalization performance; in the range where the changes of various pellet proportioning are no more than 20%, the intelligent recommended best proportioning scheme can increase the compressive strength of cooked pellets by over 16% on average, and the system runs stably and the simulation results are effective.

With the rapid development of the Internet of Things (IoT), security and privacy of smart home systems based on IoT are more and more popular. As the key component of IoT, wireless communication and sensor technology are prerequisites for the security and confidentiality of smart home systems. The smart home systems integrate electronic information technology and computer control. By designing and installing various sensors in the home for collecting data, and then using the IoT platform for data transmission, the remote control of the home running state can be realized. The home security is guaranteed. This article designs IoT architecture of smart home, and then hardware and software are designed according to the system architecture. The hardware part is mainly analyzed from the image recognition module and the speech recognition module. In addition, a stereo matching algorithm for smart video surveillance is proposed to optimize the accuracy of the surveillance system. Finally, the simulation results prove that the designed smart home systems have a low cost and high accuracy. It not only optimizes the performance of smart home systems but also improves the safety factor.