The purpose of this research was to study the influence of various factors on the results of theshort-time prediction of the traffic situation on motorways. The models were made to predictthe speed and flow 15 minutes ahead of the observation period in five-minute periods. Multilayerperceptron networks were used as prediction models. According to this study, it wasbetter to increase the number of hidden neurons by reducing the input parameters bydecreasing the number of cross-sections rather than by shortening the time-series. The modelsthat were divided into two sub-models – one for the mean speed forecasts and the other for thetraffic flow forecasts – gave better results than one single model predicting both variablessimultaneously. For 90 percent of the predicted flows the relative error was 20 percent atmost, and for 90 percent of the predicted speeds it was four percent at most.
展开▼
