Path Travel Time Estimation using Attribute-related Hybrid Trajectories Network

The architecture of AS-Capsules


Estimation of path travel time provides great value to applications like bus line designs and route plannings. Existing approaches are mainly based on single-source trajectory datasets that are usually large in size to ensure a satisfactory performance. This leads to two limitations:1) Large-scale data may not always be attainable, e.g. city-scale public bus data is usually small compared to taxi data due to relative fewer bus trips in a day. 2) Considering only single-source trajectory data neglects the potential estimation-improving insights of external data, e.g. trajectory dataset of other vehicle sources obtained from the same geographical region. A challenge is how to effectively utilize such other trajectory sources. Moreover, existing work does not attend the important attributes of a trajectory including vehicle ID, day of week, rainfall level etc., which are important for estimating the path travel time. Motivated by these and the recent successes of neural network models, we propose Attribute-related Hybrid Trajectories Network~(AtHy-TNet), a neural model that effectively utilizes the attribute correlations, as well as the spatial and temporal relationships across hybrid trajectory data. We apply this to a novel problem of estimating path travel time of a type of vehicles using a hybrid trajectory dataset that includes trajectories from other vehicle types. We demonstrate in our experiments the benefits of considering hybrid data for travel time estimation, and show that AtHy-TNet significantly outperforms state-of-the-art methods on real-world trajectory datasets.

In Proceedings of the 28th ACM International Conference on Information and Knowledge Management
Yequan Wang
Yequan Wang
Researcher of Artificial Intelligence

My research interests include pre-trained language model, dialog model and sentiment analysis.