Date of Award
Doctor of Philosophy
School of Engineering
Faculty of Computing, Health and Science
Dr David McDougall
Dr James Cross
This study aims at calculating the traffic signal timing that suits traffic intensity at intersections studied in the inner city of Ubon Rachathani Provice, Thailand. The mixed models between maximum likelihood estimation and Bayesian inference are presented to estimate traffic intensity. A queuing system is used to generate the performance of traffic flow. A fuzzy logic system is applied to calculate the optimal length of each phase of the cycle. The fortran language is used to produce the computer program for computation. The algorithm of the computer programming is based on EM algorithm, Markov Chain Monte Carlo algorithm, queuing generation and fuzzy logic. The output of traffic signal timing from the fuzzy controller are longer than the traffic signal timing from the conventional controller. Cost function is used to evaluate the efficiency of the traffic controller. The result of the evaluation shows that fuzzy controller is more efficient than a conventional controller.
Vonglao, P. (2007). The solution of traffic signal timing by using traffic intensity estimation and fuzzy logic. https://ro.ecu.edu.au/theses/50