This study integrates three data mining techniques, K-means clustering, decision trees, and neural networks, to predict the travel time of freeway with non-recurrent congestion. By creating dummy variables and identifying important variables, not only is the prediction performance increased without increasing investment in equipment, but also important variables are obtained concerning the important locations of equipment in order to effectively assist public transit agencies with system maintenance. The experimental results for a segment of 36.1. km of National Freeway No. 1, Taiwan, with non-recurrent congestion show that, whether or not the data generated by the Electronic Toll Collection (etc) system is used as input variables, the travel time prediction method developed in this study is able to improve the prediction performance. Meanwhile, the proposed approach also reduces the percentage of samples with mean absolute percentage error (MAPE)>20%. Furthermore, in this study, important variables are extracted from the decision tree in order to predict the travel time. Finally, the prediction models constructed in accordance with six scenarios are highly accurate due to the low MAPE values, which are from 6% to 9%.
- Classification and regression tree
- Neural networks
- Non-recurrent congestion
- Travel time prediction