Related Experiment Video
Updated: Jul 15, 2026
16:14
Trajectory Data Analyses for Pedestrian Space-time Activity Study
Published on: February 25, 2013
Real time urban traffic prediction using RFID and a hybrid LSTM random forest model
Omar Khattab1, B Saravana Balaji2, Fatmah Alghadhoori1
1Department of Computer Science and Engineering, Kuwait College of Science and Technology, Doha, Kuwait.
Scientific Reports
|December 12, 2025
Summary
This study introduces a new system for real-time urban traffic management using Radio-Frequency Identification and a hybrid machine learning model. The Traffic Pattern Classification using LSTM-Random Forest (TPC-LSTM-RF) system accurately predicts congestion, enhancing urban mobility.
Area of Science:
- Computer Science
- Artificial Intelligence
- Urban Planning
Background:
- Traffic congestion significantly impacts urban efficiency, safety, and quality of life.
- Existing traffic management solutions often address symptoms rather than root causes.
- Increased vehicle use exacerbates urban mobility challenges.
Purpose of the Study:
- To propose a novel prototype for real-time urban traffic management.
- To enhance traffic flow, reduce violations, and improve urban mobility.
- To develop a privacy-preserving system for vehicle tracking and traffic regulation.
Main Methods:
- Utilized Radio-Frequency Identification (RFID) for non-visual vehicle tracking with privacy-by-design features.
- Developed a hybrid machine learning algorithm, Traffic Pattern Classification using LSTM-Random Forest (TPC-LSTM-RF).
- Integrated temporal and spatial traffic data for congestion prediction and management recommendations.
Main Results:
- Achieved a prediction accuracy of 93.5% for traffic congestion patterns.
- Demonstrated a Mean Absolute Error (MAE) of 2.43.
- Exhibited a processing time of 198 ms, outperforming existing models.
Conclusions:
- The TPC-LSTM-RF system offers a promising solution for proactive urban traffic management.
- The system effectively predicts congestion and enforces traffic regulations, improving urban mobility.
- Future work includes real-world validation and integration with existing traffic infrastructure.