Full
Outline
To address the critical issue of predicting the time-series passenger flow at subway stations, a novel hybrid deep learning method, AFT-K-GRU+, is proposed to provide more accurate decision support for subway operation and management. Leveraging the multi-scale temporal dependencies inherent in subway passenger flow data, the model innovatively integrates three core components: the attention-free transformer (AFT), the gated recurrent unit (GRU), and the KAN network. Specifically, the AFT module captures long-term periodic patterns in passenger flow data, the GRU module focuses on extracting short-term fluctuation characteristics, and the KAN network enhances the model's expressive capacity. To enhance the robustness of the model's predictions, this study innovatively designs a knowledge-driven correction controller based on residual feedback, which enables online self-correction of the output. Experimental validation using real-world card swipe data from Beijing subway stations demonstrates that the AFT-K-GRU+ model effectively predicts station passenger flow, achieving mean error reductions of 25.3% and 18.7% compared to Transformer and LSTM methods, respectively. This model offers effective methodological support for subway operators, assisting management departments in passenger flow control and daily planning, thereby enhancing the operational efficiency and service quality of subway lines.
150
31
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
