A parallel genetic algorithm-based TSK-Fuzzy system for dynamic car-following modeling

• Main Authors: Purnomo, Muhammad Ridwan Andi, Abdul Wahab, Dzuraidah, Hassan, Azmi, Rahmat, Riza Atiq
• Format: Article
• Language: English
• Published: EuroJournals Publishing, Inc. 2009
• Subjects: QA75 Electronic computers. Computer science; T175 Industrial research. Research and development
• Online Access: http://irep.iium.edu.my/37310/1/a_parallel_genetic_algorithm.pdf; http://irep.iium.edu.my/37310/
• Institution: Universiti Islam Antarabangsa Malaysia

This paper presents the application of Parallel Genetic Algorithm (PGA)-based Takagi Sugeno Kang (TSK)-Fuzzy approach for dynamic car-following modeling in the traffic simulation software. It differs from the usual car-following model significantly as the proposed model provides a more dynamic car movement and realistic headway by considering the driver progressive level factor. These two advantages could make further traffic analysis become more accurate. The proposed model is used for the tire-road slippage index determination which influences the car's speed. Since the car interact with each other on the road and the driver progressive level is different, three interaction variables, that are current car speed, distance to the car ahead and driver progressive level, are defined and an indication of their influence on the tire-road slippage index is analysed. PGA is included in the TSK-Fuzzy system to determine the optimum parameters in the Fuzzy sets and Fuzzy rules so as to improve the accuracy of the tire-road slippage index estimation. A set of data in a size of 38 × 4 and 22 × 4 were used for training and testing the performance of the model. The study shows that TSK-Fuzzy system combined with PGA is effective and accurate in estimating the tire-road slippage index