Transportation mode identification using road-network subgraph representation

Ying Zhang; Xuefeng Guan; Huayi Wu

doi:10.1117/12.3034923

7 August 2024 Transportation mode identification using road-network subgraph representation

Ying Zhang, Xuefeng Guan, Huayi Wu

Proceedings Volume 13224, 4th International Conference on Internet of Things and Smart City (IoTSC 2024); 132241S (2024) https://doi.org/10.1117/12.3034923
Event: 4th International Conference on Internet of Things and Smart City, 2024, Hangzhou, China

Abstract

Transportation mode identification (TMI) is an essential component of intelligent transportation systems, which provides guidance for understanding travel behavior preferences. Existing studies primarily focus on motion attributes of trajectories, neglecting the auxiliary function of urban road-network information in TMI. Inspired by subgraph representation, we propose a novel TMI framework using road-network subgraph representation (TRSS) to tackle this issue. The framework consists of a graph attention network with labeling trick to capture the topology relationship between road segments, and a Bi-LSTM network to encode the motion characteristics. Finally, we combine road-network semantics and motion semantics to jointly train the model. Experiments on two trajectory datasets show that TRSS significantly outperforms existing TMI methods. And ablation analysis demonstrates that road-network subgraph representation can effectively enhance the performance of identifying model.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Ying Zhang, Xuefeng Guan, and Huayi Wu "Transportation mode identification using road-network subgraph representation", Proc. SPIE 13224, 4th International Conference on Internet of Things and Smart City (IoTSC 2024), 132241S (7 August 2024); https://doi.org/10.1117/12.3034923

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available