Application of Fuzzy Mamdani Model for Effective Prediction of Traffic Flow of Vehicles at Signalized Road Intersections

Over the last decade, the increase in urban population due to continuous migration from rural to urban parts of a country has led to the availability of more vehicles on the road, causing severe traffic bottlenecks, which is a big challenge in our society today. This study aims to develop an algorithm based on the signalized traffic control system to address the constant repetitive traffic congestion problem in South Africa. The Fuzzy Mamdani model (FMM) was implemented using MATLAB R2020. Within the investigation period, the number of connecting vehicles, the time taken for vehicles to navigate at road intersections, and the distance covered by the vehicles before the intersection were noted as input and output variables. Membership functions for input, output variables were defined, rules were developed based on available parameters, and traffic datasets were obtained. The result obtained from the FMM showed a significant improvement in the system. The model is capable of reducing the problem of traffic congestion significantly at signalized road intersections. However, further research can be conducted at different traffic conditions to prove the FMM Model's trustworthiness further.