Tali Yollar için Kısa Vadeli Trafik Hacminin Yapay Sinir Ağlarıyla Belirlenmesi

Authors : Abdulgazi GEDİK

Pages : 1496-1508

Doi:10.31202/ecjse.773088

View : 12 | Download : 6

Publication Date : 2020-09-30

Article Type : Research Paper

Abstract :The forecasting of merging road traffic volume is one of the critical issues for the main networks of traffic-congestion suffering cities. Artificial neural network insert ignore into journalissuearticles values(ANN); – used in many disciplines varying from economy to different engineering applications such as sales forecasting, industrial process control, customer research, data validation, risk management, target marketing and civil engineering – could be a promising solution to this issue. Providing a higher forecasting accuracy based on past traffic data, ANN has become very popular in transportation engineering for the last 30 years. In this paper, the main goal was to predict the short-term traffic volume of a connection road leading to one of Istanbul’s Bosphorous Bridge in Turkey by the three different implementations of ANN. These were Feed Forward Back Propagation insert ignore into journalissuearticles values(FFBP);, Generalized Regression Neural Network insert ignore into journalissuearticles values(GRNN); and Radial Based Function insert ignore into journalissuearticles values(RBF);. Then, obtained results were compared with each other and the result of Multi Linear Regression insert ignore into journalissuearticles values(MLR); method.
Keywords : Artificial neural network, traffic volume, traffic flow, short term prediction