Freeway travel time prediction is a key technology of Intelligent Transportation Systems (ITS). Many scholars have found that periodic function plays a positive role in improving the prediction accuracy of travel time prediction models. However, very few studies have comprehensively evaluated the impacts of different periodic functions on statistical and machine learning models. In this paper, our primary objective is to evaluate the performance of the six commonly used multistep ahead travel time prediction models (three statistical models and three machine learning models). In addition, we compared the impacts of three periodic functions on multistep ahead travel time prediction for different temporal scales (5-minute, 10-minute, and 15-minute). The results indicate that the periodic functions can improve the prediction performance of machine learning models for more than 60 minutes ahead prediction and improve the over 30 minutes ahead prediction accuracy for statistical models. Three periodic functions show a slight difference in improving the prediction accuracy of the six prediction models. For the same prediction step, the effect of the periodic function is more obvious at a higher level of aggregation.

As a new type of short distance commuting, the station-free sharing bike effectively alleviates urban traffic congestion. Thus, they are deployed in a large scale in many cities. However, various complex factors, including spatial, temporal, and other external information, result in serious imbalance of supply and demand between regions, which makes accurate prediction a challenging issue. In this study, our primary objective is to accurately forecast supply and demand by leveraging multi-source datasets. Based on the visual analysis about spatial-temporal characteristics of GPS data in Shanghai, we presented the innovative methods of Area of Interest grading and Traffic Analysis Zone division of bike-sharing, and revealed the distribution characteristics of sharing bike trips. A multi-block hybrid model where three blocks were separately modeled according to different data types was proposed. Moreover, eight state-of-theart models and two variant models were developed as benchmarks to compare and evaluate the proposed model. The results suggested that MBH outperforms ten baselines with the highest accuracy. In addition, we conducted practical application of prediction results to validate that the proposed model could provide effective information for scheduling and rebalancing of bike-sharing system.

No abstract

Travel time prediction is playing an increasingly important part in advanced traveler information system (ATIS), which is of great significance to alleviate urban traffic congestion. Although graph convolutional networks have been widely used in road network traffic prediction, spatiotemporal dynamic modeling of urban traffic is still an intractable task. In this study, we propose an improved graph convolutional network (IGC-Net) for travel time prediction. Specifically, we design a modified adjacency matrix by fusing distance and correlation matrix with original adjacency matrix to capture spatial dynamic feature. We then establish three components based on temporal property to capture recent, daily-periodic, and weekly periodic correlations. The comparison experiments with baseline models and variants on a real-world dataset in Beijing are conducted. The results show that the IGC-Net outperforms baseline models in different prediction horizons and has stronger robustness for dynamic traffic prediction.