基于时空图卷积的城市流迁移预测

刘斌琨; 康宇; 曹洋; 赵云波; 许镇义

doi:10.1631/FITEE.2300571

Your Location：

Home >

Browse articles >

基于时空图卷积的城市流迁移预测

常规文章 | Updated：2025-03-13

- 基于时空图卷积的城市流迁移预测
  Enhanced Publication
- Transfer learning with a spatiotemporal graph convolution network for city flow prediction
- “在智慧城市发展领域，引入了一种新的迁移学习方法来解决数据稀缺地区城市流量预测的可扩展性问题。该方法利用时空图卷积，构建一个共现空间来对齐源域和目标域之间的数据映射，从而促进城市流量预测模型的传输。该技术捕获了并发的时空特征，并采用马氏距离损失进行特征对齐，通过2015年对芝加哥、纽约和华盛顿的公共自行车流量数据集的评估，该技术已被证明优于现有方法。”
- 信息与电子工程前沿（英文） 2025年26卷第1期页码：79-92
- Affiliations：
  
  1.Department of Automation, University of Science and Technology of China, Hefei 230026, China
  2.Key Laboratory of System Control and Information Processing, Ministry of Education, Shanghai 200240, China
  3.Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei 230088, China
  4.Institute of Advanced Technology, University of Science and Technology of China, Hefei 230088, China
- Author bio：
  
  ‡Corresponding authors
- Funds：
  
  National Natural Science Foundation of China(62103124;62033012);Major Special Science and Technology Project of Anhui Province, China(202003a07020009);Open Project Program of Key Laboratory of Ministry of Education of System Control and Information Processing, China(SCIP20230109)
- DOI：10.1631/FITEE.2300571
  中图分类号： TP311;U495
- 收稿：2023-08-23，
  
  修回：2023-12-11，
  
  网络出版：2024-12-27，
  
  纸质出版：2025-01
- Accepted：
Scan QR Code
刘斌琨, 康宇, 曹洋, 等. 基于时空图卷积的城市流迁移预测[J]. 信息与电子工程前沿（英文）, 2025,26(1):79-92.

Binkun LIU, Yu KANG, Yang CAO, et al. Transfer learning with a spatiotemporal graph convolution network for city flow prediction[J]. Frontiers of Information Technology & Electronic Engineering, 2025, 26(1): 79-92.
刘斌琨, 康宇, 曹洋, 等. 基于时空图卷积的城市流迁移预测[J]. 信息与电子工程前沿（英文）, 2025,26(1):79-92. DOI： 10.1631/FITEE.2300571.

Binkun LIU, Yu KANG, Yang CAO, et al. Transfer learning with a spatiotemporal graph convolution network for city flow prediction[J]. Frontiers of Information Technology & Electronic Engineering, 2025, 26(1): 79-92. DOI： 10.1631/FITEE.2300571.

浏览量

190

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Frequency-learning adversarial networks based on transfer learning for cross-scenario signal modulation classification

A software defect prediction method with metric compensation based on feature selection and transfer learning

Texture branch network for chronic kidney disease screening based on ultrasound images

Two-level hierarchical feature learning for image classification

基于时空图卷积的城市流迁移预测

Transfer learning with a spatiotemporal graph convolution network for city flow prediction

DOI：10.1631/FITEE.2300571