August 11, 2025Applied SciencesOpen Access

xLSTM-Based Urban Traffic Flow Prediction for Intelligent Transportation Governance

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Observational analysis enhanced congestion prediction in urban settings, indicating better public safety responses.

The xLSTM model achieves an accuracy of 87.3% in predicting urban traffic congestion, and its F1-score is 0.882.
Congestion prediction accuracy, combined with a 41.2 ms average inference latency, outperforms traditional models like LSTM and GRU.
Methodologically, the study integrates spatio-temporal learning using vehicle data collected from over 300 sensors.
The findings highlight the model's potential for real-time deployment in police control centers, improving urban mobility responsiveness.

Huang et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark