Digital Twin and Graph Neural Network Advance Substation Fault Early Warning
Researchers have engineered a hybrid early warning system that couples graph neural networks with digital twin physics to detect emerging ...
Tag: graph neural networks
Authorship AI Framework Uncovers Hidden Coordination in Social Media Astroturfing Campaigns
Researchers have developed AstroAuth-ID, an artificial intelligence framework that combines stylometric, neural semantic, behavioral, and graph-based representations to identify the ...
Physics-Guided Graph Transformer Demonstrates Accurate Multimodal Brain Tumor Classification
Researchers have introduced a physics-guided graph transformer framework that combines convolutional features, transformer attention, and graph topology for automated multimodal ...
Deep Learning Models Transform Urban Traffic Volume Forecasting Across Global Road Networks
A systematic survey evaluates modern deep learning architectures and benchmark datasets for traffic volume prediction across recent transport studies.
New Model Detects Anomalies in Complex Network Data
A new framework called AMG improves unsupervised anomaly detection in complex attributed multiplex heterogeneous networks by integrating multi-channel graph convolutional ...
Compact AI Model Predicts Protein Stability With Fewer Parameters
A compact energy-based neural network called LEEN predicts protein stability changes from single amino acid substitutions using roughly 2 to ...
Graph Diffusion Convolution Enhances Inductive Link Prediction Across Complex Networks
A hybrid framework combining graph diffusion convolution with GraphSAGE improves inductive link prediction across diverse benchmark networks by capturing long-range ...
Undersea Cable Threat Detection Model Fuses Acoustic Sensors and Trajectory Data
Researchers have developed an adaptive spatio-temporal graph attention network that couples ship trajectory tracking with seabed acoustic sensing to reliably ...
Adaptive Multimodal Brain Network Model Improves Cross-Site Autism Classification Accuracy
A cross-attention-guided graph neural network fusing structural and functional MRI achieves high diagnostic accuracy and cross-site generalization in autism spectrum ...
Geometric Deep Learning Unifies Vertical and Horizontal Integration for Spatial Multi-Omics
Researchers have developed DIRAC, a geometric deep learning model that aligns distinct molecular modalities and transfers cell annotations across diverse ...
Physics-Informed Graph Network Improves Fatigue Life Prediction for Robotic Arms
A physics-informed graph neural network achieved 92.48% overall accuracy in predicting industrial robotic arm fatigue life across variable-load conditions.
AI learns to steer EV charging, traffic and power grids as one system
A deep multi-agent reinforcement learning framework that jointly coordinates electric vehicle charging, traffic routing and grid dispatch cut total system ...
Graph Neural Network Predicts Job Wait Times Across Huge Computing Grids
A graph neural network trained on about 2.1 million PanDA job records predicts job turnaround time with an R-squared of ...
Graph neural networks meet the edge in new fraud detection survey
A systematic survey of 22 studies finds that no published fraud-detection system simultaneously combines graph learning, edge deployment, federated training, ...
Graph neural networks reshape electrocatalyst design for green hydrogen
A new review details how graph neural networks are accelerating the discovery of electrocatalysts for green hydrogen production by learning ...
AI and Omics Converge to Decode the Gene Regulatory Logic of the Brain
A new Brain Informatics review traces how AI methods, from co-expression statistics to causal graph neural networks and foundation models, ...
Attention and dynamic pruning sharpen link prediction on static knowledge graphs
A new graph neural network method called MADPGraph combines relation-aware multi-head attention with adaptive dynamic pruning to improve link prediction ...
New Graph Learning Framework Balances Consistency and Diversity to Outperform Rivals
Researchers report a graph contrastive learning framework called COIN that combines continuous orthogonal augmentation with an information-balancing training principle and ...
Graph neural network model learns design element links for sharper style transfer
A new study proposes a graph neural network tuned by a modified zebra optimization algorithm that models relationships among visual ...
New AI model reads text, images and social networks to spot cyberbullying
A new multimodal AI system called HMTF-Net combines text, conversation context, user interaction graphs, images and metadata to detect cyberbullying, ...
