Full
Outline
To address multi-factor subway line passenger volume forecasting needs, 12 influential features are selected (time, weather, network scale, urban development, holidays, and events) via feature mining and correlation analysis, and—targeting the difficulty of XGBoost hyperparameter tuning—a hyperparameter optimization approach based on the Zebra Optimization Algorithm (ZOA) is proposed. An XGBoost-ZOA integrated forecasting model is developed, a cross-validation scheme tailored for time-series prediction is designed, and a case study is conducted using Xi'an Metro data. The ZOA-optimized model achieves a MAPE of 3.85% on the Line 1 test set; compared with representative intelligent optimization algorithms, it yields the best performance, confirming the algorithm's superiority. Across nine lines, the XGBoost-ZOA model attains an average MAPE of 5.18%, with the maximum error below 7%, and the predicted and actual curves show a high degree of agreement. Compared with SARIMA and LSTM, the MAPE decreases by 17.8% and 21.9%, and the RMSE decreases by 10.8% and 13.6%, respectively. Finally, using feature importance, the nine lines were grouped into three categories: trend-driven, holiday/activity-driven, and multi-factor balanced passenger flows. Lines dominated by holidays/activities exhibit larger prediction errors, whereas those governed by periodic trends show smaller errors, confirming the model's interpretability and practical utility.
70
14
| 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
