New PEHT model enhances urban network traffic prediction

Researchers have developed a Parameter-Efficient Hybrid Transformer (PEHT) model designed for more accurate network traffic prediction in urban cellular networks. This model integrates urban mobility and congestion data by separating communication features from mobility features and using Low-Rank Adaptation (LoRA) to reduce trainable parameters. A multimodal fusion strategy then combines these features to enhance traffic forecasting, showing improved performance over existing methods on the Telecom Italia Milan dataset. AI

IMPACT This research could lead to more efficient resource allocation in urban cellular networks by improving traffic prediction accuracy.

RANK_REASON The cluster contains an academic paper detailing a new model and its evaluation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Abdolazim Rezaei
• arXiv
• GitHub
• Hugging Face
• Lora
• Milan
• Pehtred
• TIM Group
• transformer

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →