SUMMARY
In this study, a real-world isolated signalized intersection with a fixed-time signal control system is considered. The signal timing plans are arranged regardless of the traffic density, and these plans cause delays in vehicle queues. However, the construction of a traffic signal control system that considers the needs of the intersection will help to decrease the traffic density and increase the economic contribution by reducing waiting times and accidents. In order to increase the efficiency of the intersection, an adaptive traffic signal control system that applies signal timing plans according to changes in the traffic flow is proposed to manage the intersection. To find the appropriate adaptive green times for each lane, simulations are performed by traffic simulation software using vehicle arrivals and other information about vehicle movements gathered from the real-world intersection. Then, a hybrid radial basis function neural network is developed to forecast the adaptive green times, which is trained and tested with historical arrivals and simulation results. The performance of the proposed network is compared with well-known data mining classification methods, such as support vector regression, k-nearest neighbors, decision tree, random forest, and multilayer perceptron methods, by different evaluation parameters. The comparison results provide that the developed radial basis function neural network outperforms the other classification methods, and can be successfully used for forecasting adaptive green times as an alternative to complex unsupervised classification methods.