An Adaptive Method for an Isolated Intersection Under Mixed Traffic Conditions in Hanoi Based on ANFIS Using VISSIM-MATLAB
Xuan Can Vuong, Ruifang Mou, Trong Thuat Vu, Hoang‐Vu Nguyen
Abstract
It is a new attempt to use an adaptive neuro-fuzzy inference system (ANFIS) as an adaptive traffic signal control method for an isolated intersection under mixed traffic conditions in Hanoi City, the capital of Vietnam. The proposed method using ANFIS can work more effectively as it gives full play to both an artificial neural network and a fuzzy logic system, hence can intelligently control the green time for each phase of the traffic signal lights according to the fluctuating traffic volume under mixed traffic conditions to improve the vehicular throughput and reduce delays. Taking a typical signalized intersection in Hanoi City as a case study is to evaluate the performance of the proposed method through a microscopic traffic simulator with an interface between VISSIM and MATLAB. Simulation results of the proposed method using ANFIS indicate better performances and adaptability compared with the fixed-time method and the fuzzy logic method.