App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 10

Multi-scale spatio-temporal-frequency fused self-supervised learning framework for traffic flow prediction

Ding Yuanming1,2
Wang Rongmin1,2
Song Lin1,2
Wang Kaixin1,2
1. Liaoning Key Laboratory of Communication and Signal Processing, Dalian 116622, China
2. College of Information Engineering, Dalian University, Dalian 116622, China
DOI: 10.19734/j.issn.1001-3695.2026.03.0049

Abstract

Addressing the inadequate mining of coupled multi-scale spatio-temporal dependencies and periodic patterns in traffic flow data, this paper developed a Multi-scale Spatio-Temporal-Frequency Fused Self-supervised Framework (MSTF-SSL) . This paper designed a multi-scale spatio-temporal-frequency encoder at the architectural level to construct a fused feature extraction mechanism. In the spatio-temporal dimension, a channel-wise adaptive gating mechanism fused dilated convolution and Transformer to capture local and global temporal dependencies, and multi-scale graph convolution aggregated spatial features. In the frequency dimension, the framework embedded an adaptive spectral residual filter at the feature level for signal purification. Furthermore, this paper introduced a frequency consistency loss into self-supervised contrastive learning to constrain the model to learn robust periodic representations. Experiments on four public datasets demonstrate that the model can effectively fuse multi-scale spatio-temporal information and frequency-domain features. Compared with the baseline model ST-SSL, MSTF-SSL reduces outflow MAE, MAPE and RMSE by 3.24%, 5.85% and 4.42% respectively on the NYCBike1 dataset, and by 3.81%, 3.39% and 7.46% respectively on the NYCTaxi dataset. The proposed model effectively improves the accuracy and robustness of traffic flow prediction.

Foundation Support

国家自然科学基金项目(61901079)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.03.0049
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 10

Publish History

[2026-07-29] Accepted Paper

Cite This Article

丁元明, 王荣敏, 宋琳, 等. 基于多尺度时空频融合的自监督交通流预测模型 [J]. 计算机应用研究, 2026, 43 (10). (2026-07-30). https://doi.org/10.19734/j.issn.1001-3695.2026.03.0049. (Ding Yuanming, Wang Rongmin, Song Lin, et al. Multi-scale spatio-temporal-frequency fused self-supervised learning framework for traffic flow prediction [J]. Application Research of Computers, 2026, 43 (10). (2026-07-30). https://doi.org/10.19734/j.issn.1001-3695.2026.03.0049. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)