Identifying important variables for predicting travel time of freeway with non-recurrent congestion with neural networks

Abstract

The provision of long-distance travel time information has been a major factor facilitating the intelligent transportation system to become more successful. Previous studies have pointed out that non-recurrent congestion is the major cause of freeway delay. The long travel distance complicates the characteristics of traffic flow. Hence, how to improve the prediction capability of long-distance travel time in the case of non-recurrent congestion is an important issue that must be overcome in the field of travel time prediction. This study constructs the travel time prediction model for a segment of 36.1 kms (including eight interchanges) in the National Freeway No. 1, Taiwan, by using the multilayer perceptron. To improve the prediction capability of the model in the case of non-recurrent congestion, this study collects data of average spot speed and heavy vehicle volume gathered by dual-loop vehicle detectors, in addition to rainfall and temporal feature. Furthermore, the historical travel time inferred from the original data of electronic toll collection (ETC) system is also used as the input variable, and the actual travel time inferred from ETC is used as the training target to establish a robust prediction model. As suggested by the results of 168 experimental combinations, the most appropriate prediction model established in this study is a highly accurate forecasting model with MAPE of 6.47 %.