Integrating Future Exogenous Information into Multi-mode Travel Demand Forecasting at Gateway Hubs

Chenhui Zhang, Jinguo Cheng, Jing Yang, Huachun Tan, Yuankai Wu*

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Forecasting the demand for different modes of transportation at gateway hubs, such as high-speed train stations and airports, plays a crucial role in urban transit ecosystems. One important characteristic of this problem is that some future exogenous information, such as passenger inflow and weather conditions influencing future demand, can be obtained in advance. Traditional time series forecasting approaches have not fully utilized this characteristic. To address this issue, we propose a novel Transformer architecture called FXFormer that utilizes future exogenous information. We first decompose the input into historical information containing demand time series and covariate time series, as well as future information containing future covariates, and apply different attention mechanisms to each part. To fully exploit the relationships between variables, we treat each variate as a token. After processing through different attention mechanisms, we design a gate mechanism to fuse historical and future information to enhance the model’s performance. Extensive experiments conducted using multi-mode demand datasets from a high-speed railway station and an airport in Chengdu City demonstrate that the proposed FXFormer outperforms state-of-the-art multivariate time series forecasting approaches.

源语言英语
主期刊名Neural Information Processing - 31st International Conference, ICONIP 2024, Proceedings
编辑Mufti Mahmud, Maryam Doborjeh, Zohreh Doborjeh, Kevin Wong, Andrew Chi Sing Leung, M. Tanveer
出版商Springer Science and Business Media Deutschland GmbH
394-408
页数15
ISBN(印刷版)9789819669530
DOI
出版状态已出版 - 2025
活动31st International Conference on Neural Information Processing, ICONIP 2024 - Auckland, 新西兰
期限: 2 12月 20246 12月 2024

出版系列

姓名Communications in Computer and Information Science
2284 CCIS
ISSN(印刷版)1865-0929
ISSN(电子版)1865-0937

会议

会议31st International Conference on Neural Information Processing, ICONIP 2024
国家/地区新西兰
Auckland
时期2/12/246/12/24

指纹

探究 'Integrating Future Exogenous Information into Multi-mode Travel Demand Forecasting at Gateway Hubs' 的科研主题。它们共同构成独一无二的指纹。

引用此