TY - GEN
T1 - Learning embeddings of intersections on road networks
AU - Wang, Meng Xiang
AU - Lee, Wang Chien
AU - Fu, Tao Yang
AU - Yu, Ge
N1 - Funding Information:
This research is supported in part by the National Science Foundation under Grant No. IIS-1717084. Meng-xiang Wang and Ge Yu are supported by the State Scholarship Fund of the China Scholarship Council (201806080042) and the National Natural Science Foundation of China (U1811261, 61872070).
Publisher Copyright:
© 2019 Copyright held by the owner/author(s).
PY - 2019/11/5
Y1 - 2019/11/5
N2 - Road network is a basic component of intelligent transportation systems (ITS) in smart city. Informative representation of road networks is important as it is essential to a wide variety of ITS applications. In this paper, we propose a neural network representation learning model, namely Intersection of Road Network to Vector (IRN2Vec), to learn embeddings of road intersections that encode rich information in a road network by exploring geo-locality and intrinsic properties of intersections and moving behaviors of road users. In addition to model design, several issues unique to IRN2Vec, including data preparation for model training and various relationships among intersections, are examined. We evaluate the learned embeddings via extensive experiments on three real-world datasets using three downstream test cases, including prediction of traffic signals and crossings on intersections and travel time estimation. Experimental results show that the proposed IRN2Vec outperforms three existing methods, DeepWalk, LINE and Node2vec, in terms of F1-score in predicting traffic signals (22.21% to 23.84%) and crossings (8.65% to 11.65%), and mean absolute error (MAE) in travel time estimation (9.87% to 19.28%).
AB - Road network is a basic component of intelligent transportation systems (ITS) in smart city. Informative representation of road networks is important as it is essential to a wide variety of ITS applications. In this paper, we propose a neural network representation learning model, namely Intersection of Road Network to Vector (IRN2Vec), to learn embeddings of road intersections that encode rich information in a road network by exploring geo-locality and intrinsic properties of intersections and moving behaviors of road users. In addition to model design, several issues unique to IRN2Vec, including data preparation for model training and various relationships among intersections, are examined. We evaluate the learned embeddings via extensive experiments on three real-world datasets using three downstream test cases, including prediction of traffic signals and crossings on intersections and travel time estimation. Experimental results show that the proposed IRN2Vec outperforms three existing methods, DeepWalk, LINE and Node2vec, in terms of F1-score in predicting traffic signals (22.21% to 23.84%) and crossings (8.65% to 11.65%), and mean absolute error (MAE) in travel time estimation (9.87% to 19.28%).
UR - http://www.scopus.com/inward/record.url?scp=85076968892&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85076968892&partnerID=8YFLogxK
U2 - 10.1145/3347146.3359075
DO - 10.1145/3347146.3359075
M3 - Conference contribution
AN - SCOPUS:85076968892
T3 - GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems
SP - 309
EP - 318
BT - 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2019
A2 - Banaei-Kashani, Farnoush
A2 - Trajcevski, Goce
A2 - Guting, Ralf Hartmut
A2 - Kulik, Lars
A2 - Newsam, Shawn
PB - Association for Computing Machinery
T2 - 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2019
Y2 - 5 November 2019 through 8 November 2019
ER -
