Ensuring the reliability of power transmission networks depends heavily on the early detection of faults in key components such as insulators,which serve both mechanical and electrical functions.Even a single defectiv...Ensuring the reliability of power transmission networks depends heavily on the early detection of faults in key components such as insulators,which serve both mechanical and electrical functions.Even a single defective insulator can lead to equipment breakdown,costly service interruptions,and increased maintenance demands.While unmanned aerial vehicles(UAVs)enable rapid and cost-effective collection of high-resolution imagery,accurate defect identification remains challenging due to cluttered backgrounds,variable lighting,and the diverse appearance of faults.To address these issues,we introduce a real-time inspection framework that integrates an enhanced YOLOv10 detector with a Hybrid Quantum-Enhanced Graph Neural Network(HQGNN).The YOLOv10 module,fine-tuned on domainspecific UAV datasets,improves detection precision,while the HQGNN ensures multi-object tracking and temporal consistency across video frames.This synergy enables reliable and efficient identification of faulty insulators under complex environmental conditions.Experimental results show that the proposed YOLOv10-HQGNN model surpasses existing methods across all metrics,achieving Recall of 0.85 and Average Precision(AP)of 0.83,with clear gains in both accuracy and throughput.These advancements support automated,proactive maintenance strategies that minimize downtime and contribute to a safer,smarter energy infrastructure.展开更多
Optimizing routing and resource allocation in decentralized unmanned aerial vehicle(UAV)networks remains challenging due to interference and rapidly changing topologies.The authors introduce a novel framework combinin...Optimizing routing and resource allocation in decentralized unmanned aerial vehicle(UAV)networks remains challenging due to interference and rapidly changing topologies.The authors introduce a novel framework combining double deep Q-networks(DDQNs)and graph neural networks(GNNs)for joint routing and resource allocation.The framework uses GNNs to model the network topology and DDQNs to adaptively control routing and resource allocation,addressing interference and improving network performance.Simulation results show that the proposed approach outperforms traditional methods such as Closest-to-Destination(c2Dst),Max-SINR(mSINR),and Multi-Layer Perceptron(MLP)-based models,achieving approximately 23.5% improvement in throughput,50% increase in connection probability,and 17.6% reduction in number of hops,demonstrating its effectiveness in dynamic UAV networks.展开更多
Graph Neural Networks(GNNs),as a deep learning framework specifically designed for graph-structured data,have achieved deep representation learning of graph data through message passing mechanisms and have become a co...Graph Neural Networks(GNNs),as a deep learning framework specifically designed for graph-structured data,have achieved deep representation learning of graph data through message passing mechanisms and have become a core technology in the field of graph analysis.However,current reviews on GNN models are mainly focused on smaller domains,and there is a lack of systematic reviews on the classification and applications of GNN models.This review systematically synthesizes the three canonical branches of GNN,Graph Convolutional Network(GCN),Graph Attention Network(GAT),and Graph Sampling Aggregation Network(GraphSAGE),and analyzes their integration pathways from both structural and feature perspectives.Drawing on representative studies,we identify three major integration patterns:cascaded fusion,where heterogeneous modules such as Convolutional Neural Network(CNN),Long Short-Term Memory(LSTM),and GraphSAGE are sequentially combined for hierarchical feature learning;parallel fusion,where multi-branch architectures jointly encode complementary graph features;and feature-level fusion,which employs concatenation,weighted summation,or attention-based gating to adaptively merge multi-source embeddings.Through these patterns,integrated GNNs achieve enhanced expressiveness,robustness,and scalability across domains including transportation,biomedicine,and cybersecurity.展开更多
We introduce a pioneering anomaly detection framework within spatial crowdsourcing Internet of Drone Things(IoDT),specifically designed to improve bushfire management in Australia’s expanding urban areas.This framewo...We introduce a pioneering anomaly detection framework within spatial crowdsourcing Internet of Drone Things(IoDT),specifically designed to improve bushfire management in Australia’s expanding urban areas.This framework innovatively combines Graph Neural Networks(GNN)and advanced data fusion techniques to enhance IoDT capabilities.Through spatial crowdsourcing,drones collectively gather diverse,real-time data across multiple locations,creating a rich dataset for analysis.This method integrates spatial,temporal,and various data modalities,facilitating early bushfire detection by identifying subtle environmental and operational changes.Utilizing a complex GNN architecture,our model effectively processes the intricacies of spatially crowdsourced data,significantly increasing anomaly detection accuracy.It incorporates modules for temporal pattern recognition and spatial analysis of environmental impacts,leveraging multimodal data to detect a wide range of anomalies,from temperature shifts to humidity variations.Our approach has been empirically validated,achieving an F1 score of 0.885,highlighting its superior anomaly detection performance.This integration of spatial crowdsourcing with IoDT not only establishes a new standard for environmental monitoring but also contributes significantly to disaster management and urban sustainability.展开更多
These days,social media has grown to be an integral part of people’s lives.However,it involves the possibility of exposure to“fake news”,which may contain information that is intentionally or inaccurately false to ...These days,social media has grown to be an integral part of people’s lives.However,it involves the possibility of exposure to“fake news”,which may contain information that is intentionally or inaccurately false to promote particular political or economic interests.The main objective of this work is to use the co-attention mechanism in a Combined Graph neural network model(CMCG)to capture the relationship between user profile features and user preferences in order to detect fake news and examine the influence of various social media features on fake news detection.The proposed approach includes three modules.The first one creates a Graph Neural Network(GNN)based model to learn user profile properties,while the second module encodes news content,user historical posts,and news sharing cascading on social media as user preferences GNN-based model.The inter-dependencies between user profiles and user preferences are handled through the third module using a co-attention mechanism for capturing the relationship between the two GNN-based models.We conducted several experiments on two commonly used fake news datasets,Politifact and Gossipcop,where our approach achieved 98.53%accuracy on the Gossipcop dataset and 96.77%accuracy on the Politifact dataset.These results illustrate the effectiveness of the CMCG approach for fake news detection,as it combines various information from different modalities to achieve relatively high performances.展开更多
Federated Graph Neural Networks (FedGNNs) have achieved significant success in representation learning for graph data, enabling collaborative training among multiple parties without sharing their raw graph data and so...Federated Graph Neural Networks (FedGNNs) have achieved significant success in representation learning for graph data, enabling collaborative training among multiple parties without sharing their raw graph data and solving the data isolation problem faced by centralized GNNs in data-sensitive scenarios. Despite the plethora of prior work on inference attacks against centralized GNNs, the vulnerability of FedGNNs to inference attacks has not yet been widely explored. It is still unclear whether the privacy leakage risks of centralized GNNs will also be introduced in FedGNNs. To bridge this gap, we present PIAFGNN, the first property inference attack (PIA) against FedGNNs. Compared with prior works on centralized GNNs, in PIAFGNN, the attacker can only obtain the global embedding gradient distributed by the central server. The attacker converts the task of stealing the target user’s local embeddings into a regression problem, using a regression model to generate the target graph node embeddings. By training shadow models and property classifiers, the attacker can infer the basic property information within the target graph that is of interest. Experiments on three benchmark graph datasets demonstrate that PIAFGNN achieves attack accuracy of over 70% in most cases, even approaching the attack accuracy of inference attacks against centralized GNNs in some instances, which is much higher than the attack accuracy of the random guessing method. Furthermore, we observe that common defense mechanisms cannot mitigate our attack without affecting the model’s performance on mainly classification tasks.展开更多
Turmeric Leaf diseases pose a major threat to turmeric cultivation,causing significant yield loss and economic impact.Early and accurate identification of these diseases is essential for effective crop management and ...Turmeric Leaf diseases pose a major threat to turmeric cultivation,causing significant yield loss and economic impact.Early and accurate identification of these diseases is essential for effective crop management and timely intervention.This study proposes DenseSwinGNNNet,a hybrid deep learning framework that integrates DenseNet-121,the Swin Transformer,and a Graph Neural Network(GNN)to enhance the classification of turmeric leaf conditions.DenseNet121 extracts discriminative low-level features,the Swin Transformer captures long-range contextual relationships through hierarchical self-attention,and the GNN models inter-feature dependencies to refine the final representation.A total of 4361 images from the Mendeley turmeric leaf dataset were used,categorized into four classes:Aphids Disease,Blotch,Leaf Spot,and Healthy Leaf.The dataset underwent extensive preprocessing,including augmentation,normalization,and resizing,to improve generalization.An 80:10:10 split was applied for training,validation,and testing respectively.Model performance was evaluated using accuracy,precision,recall,F1-score,confusion matrices,and ROC curves.Optimized with the Adam optimizer at the learning rate of 0.0001,DenseSwinGNNNet achieved an overall accuracy of 99.7%,with precision,recall,and F1-scores exceeding 99%across all classes.The ROC curves reported AUC values near 1.0,indicating excellent class separability,while the confusion matrix showed minimal misclassification.Beyond high predictive performance,the framework incorporates considerations for cybersecurity and privacy in data-driven agriculture,supporting secure data handling and robust model deployment.This work contributes a reliable and scalable approach for turmeric leaf disease detection and advances the application of AI-driven precision agriculture.展开更多
The rapid evolution of AI-driven cybersecurity solutions has led to increasingly complex network infrastructures,which in turn increases their exposure to sophisticated threats.This study proposes a Graph Neural Netwo...The rapid evolution of AI-driven cybersecurity solutions has led to increasingly complex network infrastructures,which in turn increases their exposure to sophisticated threats.This study proposes a Graph Neural Network(GNN)-based feature selection strategy specifically tailored forNetwork Intrusion Detection Systems(NIDS).By modeling feature correlations and leveraging their topological relationships,this method addresses challenges such as feature redundancy and class imbalance.Experimental analysis using the KDDTest+dataset demonstrates that the proposed model achieves 98.5% detection accuracy,showing notable gains in both computational efficiency and minority class detection.Compared to conventional machine learning methods,the GNN-based approach exhibits a superior capability to adapt to the dynamics of evolving cyber threats.The findings support the feasibility of deploying GNNs for scalable,real-time anomaly detection in modern networks.Furthermore,key predictive features,notably f35 and f23,are identified and validated through correlation analysis,thereby enhancing the model’s interpretability and effectiveness.展开更多
基金supported by Ho Chi Minh City Open University,Vietnam and Suan Sunandha Rajabhat Univeristy,Thailand.
文摘Ensuring the reliability of power transmission networks depends heavily on the early detection of faults in key components such as insulators,which serve both mechanical and electrical functions.Even a single defective insulator can lead to equipment breakdown,costly service interruptions,and increased maintenance demands.While unmanned aerial vehicles(UAVs)enable rapid and cost-effective collection of high-resolution imagery,accurate defect identification remains challenging due to cluttered backgrounds,variable lighting,and the diverse appearance of faults.To address these issues,we introduce a real-time inspection framework that integrates an enhanced YOLOv10 detector with a Hybrid Quantum-Enhanced Graph Neural Network(HQGNN).The YOLOv10 module,fine-tuned on domainspecific UAV datasets,improves detection precision,while the HQGNN ensures multi-object tracking and temporal consistency across video frames.This synergy enables reliable and efficient identification of faulty insulators under complex environmental conditions.Experimental results show that the proposed YOLOv10-HQGNN model surpasses existing methods across all metrics,achieving Recall of 0.85 and Average Precision(AP)of 0.83,with clear gains in both accuracy and throughput.These advancements support automated,proactive maintenance strategies that minimize downtime and contribute to a safer,smarter energy infrastructure.
文摘Optimizing routing and resource allocation in decentralized unmanned aerial vehicle(UAV)networks remains challenging due to interference and rapidly changing topologies.The authors introduce a novel framework combining double deep Q-networks(DDQNs)and graph neural networks(GNNs)for joint routing and resource allocation.The framework uses GNNs to model the network topology and DDQNs to adaptively control routing and resource allocation,addressing interference and improving network performance.Simulation results show that the proposed approach outperforms traditional methods such as Closest-to-Destination(c2Dst),Max-SINR(mSINR),and Multi-Layer Perceptron(MLP)-based models,achieving approximately 23.5% improvement in throughput,50% increase in connection probability,and 17.6% reduction in number of hops,demonstrating its effectiveness in dynamic UAV networks.
基金funded by Guangzhou Huashang University(2024HSZD01,HS2023JYSZH01).
文摘Graph Neural Networks(GNNs),as a deep learning framework specifically designed for graph-structured data,have achieved deep representation learning of graph data through message passing mechanisms and have become a core technology in the field of graph analysis.However,current reviews on GNN models are mainly focused on smaller domains,and there is a lack of systematic reviews on the classification and applications of GNN models.This review systematically synthesizes the three canonical branches of GNN,Graph Convolutional Network(GCN),Graph Attention Network(GAT),and Graph Sampling Aggregation Network(GraphSAGE),and analyzes their integration pathways from both structural and feature perspectives.Drawing on representative studies,we identify three major integration patterns:cascaded fusion,where heterogeneous modules such as Convolutional Neural Network(CNN),Long Short-Term Memory(LSTM),and GraphSAGE are sequentially combined for hierarchical feature learning;parallel fusion,where multi-branch architectures jointly encode complementary graph features;and feature-level fusion,which employs concatenation,weighted summation,or attention-based gating to adaptively merge multi-source embeddings.Through these patterns,integrated GNNs achieve enhanced expressiveness,robustness,and scalability across domains including transportation,biomedicine,and cybersecurity.
文摘We introduce a pioneering anomaly detection framework within spatial crowdsourcing Internet of Drone Things(IoDT),specifically designed to improve bushfire management in Australia’s expanding urban areas.This framework innovatively combines Graph Neural Networks(GNN)and advanced data fusion techniques to enhance IoDT capabilities.Through spatial crowdsourcing,drones collectively gather diverse,real-time data across multiple locations,creating a rich dataset for analysis.This method integrates spatial,temporal,and various data modalities,facilitating early bushfire detection by identifying subtle environmental and operational changes.Utilizing a complex GNN architecture,our model effectively processes the intricacies of spatially crowdsourced data,significantly increasing anomaly detection accuracy.It incorporates modules for temporal pattern recognition and spatial analysis of environmental impacts,leveraging multimodal data to detect a wide range of anomalies,from temperature shifts to humidity variations.Our approach has been empirically validated,achieving an F1 score of 0.885,highlighting its superior anomaly detection performance.This integration of spatial crowdsourcing with IoDT not only establishes a new standard for environmental monitoring but also contributes significantly to disaster management and urban sustainability.
基金funded by Umm Al-Qura University,Saudi Arabia under grant number:25UQU4300346GSSR05.
文摘These days,social media has grown to be an integral part of people’s lives.However,it involves the possibility of exposure to“fake news”,which may contain information that is intentionally or inaccurately false to promote particular political or economic interests.The main objective of this work is to use the co-attention mechanism in a Combined Graph neural network model(CMCG)to capture the relationship between user profile features and user preferences in order to detect fake news and examine the influence of various social media features on fake news detection.The proposed approach includes three modules.The first one creates a Graph Neural Network(GNN)based model to learn user profile properties,while the second module encodes news content,user historical posts,and news sharing cascading on social media as user preferences GNN-based model.The inter-dependencies between user profiles and user preferences are handled through the third module using a co-attention mechanism for capturing the relationship between the two GNN-based models.We conducted several experiments on two commonly used fake news datasets,Politifact and Gossipcop,where our approach achieved 98.53%accuracy on the Gossipcop dataset and 96.77%accuracy on the Politifact dataset.These results illustrate the effectiveness of the CMCG approach for fake news detection,as it combines various information from different modalities to achieve relatively high performances.
基金supported by the National Natural Science Foundation of China(Nos.62176122 and 62061146002).
文摘Federated Graph Neural Networks (FedGNNs) have achieved significant success in representation learning for graph data, enabling collaborative training among multiple parties without sharing their raw graph data and solving the data isolation problem faced by centralized GNNs in data-sensitive scenarios. Despite the plethora of prior work on inference attacks against centralized GNNs, the vulnerability of FedGNNs to inference attacks has not yet been widely explored. It is still unclear whether the privacy leakage risks of centralized GNNs will also be introduced in FedGNNs. To bridge this gap, we present PIAFGNN, the first property inference attack (PIA) against FedGNNs. Compared with prior works on centralized GNNs, in PIAFGNN, the attacker can only obtain the global embedding gradient distributed by the central server. The attacker converts the task of stealing the target user’s local embeddings into a regression problem, using a regression model to generate the target graph node embeddings. By training shadow models and property classifiers, the attacker can infer the basic property information within the target graph that is of interest. Experiments on three benchmark graph datasets demonstrate that PIAFGNN achieves attack accuracy of over 70% in most cases, even approaching the attack accuracy of inference attacks against centralized GNNs in some instances, which is much higher than the attack accuracy of the random guessing method. Furthermore, we observe that common defense mechanisms cannot mitigate our attack without affecting the model’s performance on mainly classification tasks.
基金supported through the Ongoing Research Funding Program(ORF-2025-498)King Saud University,Riyadh,Saudi Arabia。
文摘Turmeric Leaf diseases pose a major threat to turmeric cultivation,causing significant yield loss and economic impact.Early and accurate identification of these diseases is essential for effective crop management and timely intervention.This study proposes DenseSwinGNNNet,a hybrid deep learning framework that integrates DenseNet-121,the Swin Transformer,and a Graph Neural Network(GNN)to enhance the classification of turmeric leaf conditions.DenseNet121 extracts discriminative low-level features,the Swin Transformer captures long-range contextual relationships through hierarchical self-attention,and the GNN models inter-feature dependencies to refine the final representation.A total of 4361 images from the Mendeley turmeric leaf dataset were used,categorized into four classes:Aphids Disease,Blotch,Leaf Spot,and Healthy Leaf.The dataset underwent extensive preprocessing,including augmentation,normalization,and resizing,to improve generalization.An 80:10:10 split was applied for training,validation,and testing respectively.Model performance was evaluated using accuracy,precision,recall,F1-score,confusion matrices,and ROC curves.Optimized with the Adam optimizer at the learning rate of 0.0001,DenseSwinGNNNet achieved an overall accuracy of 99.7%,with precision,recall,and F1-scores exceeding 99%across all classes.The ROC curves reported AUC values near 1.0,indicating excellent class separability,while the confusion matrix showed minimal misclassification.Beyond high predictive performance,the framework incorporates considerations for cybersecurity and privacy in data-driven agriculture,supporting secure data handling and robust model deployment.This work contributes a reliable and scalable approach for turmeric leaf disease detection and advances the application of AI-driven precision agriculture.
文摘The rapid evolution of AI-driven cybersecurity solutions has led to increasingly complex network infrastructures,which in turn increases their exposure to sophisticated threats.This study proposes a Graph Neural Network(GNN)-based feature selection strategy specifically tailored forNetwork Intrusion Detection Systems(NIDS).By modeling feature correlations and leveraging their topological relationships,this method addresses challenges such as feature redundancy and class imbalance.Experimental analysis using the KDDTest+dataset demonstrates that the proposed model achieves 98.5% detection accuracy,showing notable gains in both computational efficiency and minority class detection.Compared to conventional machine learning methods,the GNN-based approach exhibits a superior capability to adapt to the dynamics of evolving cyber threats.The findings support the feasibility of deploying GNNs for scalable,real-time anomaly detection in modern networks.Furthermore,key predictive features,notably f35 and f23,are identified and validated through correlation analysis,thereby enhancing the model’s interpretability and effectiveness.
