Hybrid Solution Combining Kalman Filtering with Takagi-Sugeno Fuzzy Inference System for Online Car-Following Model...

Area of Science:

• Intelligent Transportation Systems
• Traffic Flow Modeling
• Control Systems Engineering

Background:

• Intelligent transportation systems (ITS) are crucial for optimizing mobility and reducing travel times.
• Validating advanced traffic models necessitates robust calibration processes to ensure real-world accuracy.
• Current traffic models require enhanced calibration techniques for improved performance.

Purpose of the Study:

• To propose a novel multidisciplinary approach for traffic model calibration.
• To integrate microscopic traffic modeling with intelligent control systems, specifically fuzzy inference.
• To enhance the accuracy and adaptability of traffic models using real-time data.

Main Methods:

• A Takagi-Sugeno fuzzy inference system was employed for its adaptive capabilities in real-time systems.
• The fuzzy inference system was applied to calibrate specific parameters of a microscopic car-following model.
• A Kalman filter was integrated with the fuzzy inference system to refine parameter adaptation.

Main Results:

• The proposed method demonstrated the adaptive capacity of microscopic traffic model parameters.
• Calibration results showed improved model validity through adaptation to real data.
• The integration of fuzzy logic and Kalman filters effectively enhanced traffic model calibration.

Conclusions:

• The multidisciplinary approach offers a significant advancement in traffic model calibration.
• Fuzzy inference systems, combined with Kalman filters, provide an effective solution for real-time traffic model adaptation.
• This research contributes to the development of more accurate and reliable intelligent transportation systems.