The increasing numbers of vehicles and drivers resulting from rapid economic development has led to a greater requirement for road traffic congestion planning. With the emergence of intelligent transportation, measures to solve traffic congestion have gradually shifted to the guidance and intelligent management of traffic flows. The research described here was based on the use of a combination of Dempster–Shafer evidence theory and fuzzy control to propose a fusion model for intelligent signal-light timing and an intelligent transportation system to relieve traffic congestion. The findings revealed that the model’s average recognition accuracy for the congestion level was 98.87%, and it also had the lowest root mean square error and average absolute error values and the biggest value of the coefficient of determination for the training and test sets. In simulation experiments, the intelligent signal timing proposed by the study increased the speed of the vehicles by 1.65%, 4.8%, and 15.4%, and reduced the average delay time by 11.6%, 24%, and 24.1% compared with when fixed timing was used for small, medium, and high traffic flows, respectively. The average number of stops under these three traffic volumes was 0.46 stops/vehicle, 0.59 stops/vehicle, and 0.78 stops/vehicle, respectively. It can be concluded that the model is able to achieve congestion relief and a traffic load reduction through automatic control of the green light delay after the accurate identification of the traffic congestion conditions.
Intelligent Transportation System for Traffic Congestion Based on Dempster–Shafer Evidence Theory and Fuzzy Logic Control
Transportation Research Record: Journal of the Transportation Research Board
2025-03-03
Article (Journal)
Electronic Resource
English
Iris Image Classification Approach Based on Dempster-Shafer Theory of Evidence
British Library Online Contents | 2005
|Human Face Recognition using Dempster-Shafer Theory
British Library Conference Proceedings | 1994
|Human face recognition using Dempster-Shafer theory
IEEE | 1994
|