Affiliation:
1. The Pennsylvania State University, University Park, PA, USA
Abstract
In this article, we propose a novel representation learning framework, namely
TRajectory EMBedding via Road networks (Trembr)
, to learn
trajectory embeddings
(low-dimensional feature vectors) for use in a variety of trajectory applications. The novelty of Trembr lies in (1) the design of a recurrent neural network--(RNN) based encoder--decoder model, namely
Traj2Vec
, that encodes spatial and temporal properties inherent in trajectories into trajectory embeddings by exploiting the underlying road networks to constrain the learning process in accordance with the matched road segments obtained using road network matching techniques (e.g., Barefoot [24, 27]), and (2) the design of a neural network--based model, namely
Road2Vec
, to learn
road segment embeddings
in road networks that captures various relationships amongst road segments in preparation for trajectory representation learning. In addition to model design, several unique technical issues raising in Trembr, including data preparation in Road2Vec, the road segment relevance-aware loss, and the network topology constraint in Traj2Vec, are examined. To validate our ideas, we learn trajectory embeddings using multiple large-scale real-world trajectory datasets and use them in three tasks, including trajectory similarity measure, travel time prediction, and destination prediction. Empirical results show that Trembr soundly outperforms the state-of-the-art trajectory representation learning models,
trajectory2vec
and
t2vec
, by at least one order of magnitude in terms of mean rank in trajectory similarity measure, 23.3% to 41.7% in terms of mean absolute error (MAE) in travel time prediction, and 39.6% to 52.4% in terms of MAE in destination prediction.
Funder
National Science Foundation
Publisher
Association for Computing Machinery (ACM)
Subject
Artificial Intelligence,Theoretical Computer Science
Reference45 articles.
1. Matching planar maps
2. Representation Learning: A Review and New Perspectives
3. Taxi Service Trajectory (TST) Prediction Challenge. 2015. Taxi Trajectory Prediction. Retrieved from http://www.geolink.pt/ecmlpkdd2015-challenge/. Taxi Service Trajectory (TST) Prediction Challenge. 2015. Taxi Trajectory Prediction. Retrieved from http://www.geolink.pt/ecmlpkdd2015-challenge/.
4. Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cited by
27 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Explainable Trajectory Representation through Dictionary Learning;Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems;2023-11-13
2. A Critical Perceptual Pre-trained Model for Complex Trajectory Recovery;Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Searching and Mining Large Collections of Geospatial Data;2023-11-13
3. Discovering urban mobility structure: a spatio-temporal representational learning approach;International Journal of Digital Earth;2023-10-02
4. Contrastive Learning for Graph-Based Vessel Trajectory Similarity Computation;Journal of Marine Science and Engineering;2023-09-21
5. Trajectory-User Linking using Higher-order Mobility Flow Representations;2023 24th IEEE International Conference on Mobile Data Management (MDM);2023-07