A three-branch multimodal fusion network predicts path loss, delay spread, angular spreads, and angular power spectrum from vehicle camera images and GPS in urban V2I scenarios.
Artificial intelligence empowered channel prediction: A new paradigm for propagation channel modeling
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 2polarities
background 2representative citing papers
A dual-branch cross-attention neural network with recurrent tracking reconstructs complete channel impulse responses from satellite imagery by predicting TDL parameters, reaching over 0.96 PDP cosine similarity on unseen sites.
citing papers explorer
-
Environment-Aware Channel Prediction for Vehicular Communications: A Multimodal Visual Feature Fusion Framework
A three-branch multimodal fusion network predicts path loss, delay spread, angular spreads, and angular power spectrum from vehicle camera images and GPS in urban V2I scenarios.
-
Deep Learning-Based Site-Specific Channel Modeling and Inference
A dual-branch cross-attention neural network with recurrent tracking reconstructs complete channel impulse responses from satellite imagery by predicting TDL parameters, reaching over 0.96 PDP cosine similarity on unseen sites.