Scatter-GNN: A Scatter Graph Neural Network for Prediction of High-Speed Railway Station—A Case Study of Yinchuan–Chongqing HSR
Source abstract
Abstract
The Yinchuan–Chongqing high-speed railway (HSR) is one of the “ten vertical and ten horizontal” comprehensive transportation channels in the National 13th Five-Year Plan for Mid- and Long-Term Railway Network. However, the choice of node stations on this line is controversial. In this paper, the problem of high-speed railway station selection is transformed into a classification problem under the edge graph structure in complex networks, and a Scatter-GNN model is proposed to predict stations. The article first uses the Node2vec algorithm to perform a biased random walk on the railway network to generate the vector representation of each station. Secondly, an adaptive method is proposed, which derives the critical value of edge stations through the pinching rule, and then effectively identifies the edge stations in the high-speed railway network. Next, the calculation method of Hadamard product is used to represent the potential neighbors of edge sites, and then the attention mechanism is used to predict the link between all potential neighbors and their corresponding edge sites. After the link prediction, the final high-speed railway network is obtained, and it is input into the GNN classifier together with the line label to complete the station prediction. Experiments show that: Baoji and Hanzhong are more likely to become node stations in this north–south railway trunk line. The Scatter-GNN classifier optimizes the site selection strategy by calculating the connection probabilities between two or more candidate routes and comparing their results. This may reduce manual selection costs and ease geographic evaluation burdens. The model proposed in this paper can be used as an auxiliary strategy for the traditional route planning scheme, which may become a new way of thinking to study such problems in the future.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Traffic Prediction and Management Techniques · Transportation Planning and Optimization · Human Mobility and Location-Based Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China
Funding
National Natural Science Foundation of China · The Major Scientific Research Projects of Northwest Normal University
References (52)
Show source-provided references
1. Internet of Things for sustainable railway transportation: Past, present, and future10.1016/j.clscn.2022.100065 ↗
2. Estimating the demand for rail freight transport in Pakistan: A time series analysis
3. Freight transportation demand elasticities: A geographic multimodal transportation network analysis10.1016/S1366-5545(00)00022-3 ↗
4. The impact of access to rail transportation on agricultural improvement: The American Midwest as a test case, 1850–186010.5198/jtlu.v4i2.188 ↗
5. Recent applications of big data analytics in railway transportation systems: A survey10.1016/j.trc.2018.03.010 ↗
6. Dynamic modeling and experimental investigation of self-powered sensor nodes for freight rail transport10.1016/j.apenergy.2019.113969 ↗
7. Effectiveness of high-speed railway on regional economic growth for less developed areas10.1016/j.jtrangeo.2019.102621 ↗
8. The effects of the high-speed railway on urban development: International experience and potential implications for China10.1016/j.progress.2013.11.001 ↗
9. Resilience in railway transport systems: A literature review and research agenda10.1080/01441647.2020.1728419 ↗
10. Deployment of autonomous trains in rail transportation: Current trends and existing challenges10.1109/ACCESS.2021.3091550 ↗
11. Singh, P., Pasha, J., Khorram-Manesh, A., Goniewicz, K., Roshani, A., and Dulebenets, M. (2021). A Holistic Analysis of Train-Vehicle Accidents at Highway-Rail Grade Crossings in Florida. Sustainability, 13.10.3390/su13168842 ↗
12. The importance of punctuality in rail transport service: An empirical investigation on the delay determinants
13. Research on Route Planning of Xi’an to Hancheng Intercity Railway
14. Modelling of rail networks: Toward a routing/makeup model10.1016/0191-2615(80)90036-3 ↗
15. Strategic environment assessment and biological diversity conservation in the Korean high-speed railway project10.1142/S1464333205002018 ↗
16. Public protests against the Beijing–Shenyang high-speed railway in China10.1016/j.trd.2015.11.009 ↗
17. A geographic information system-based model for economical and eco-friendly high-speed railway route determination using analytic hierarchy process and least-cost-path analysis10.1111/exsy.12376 ↗
18. Inductive representation learning on large graphs
19. Thomas, N., and Welling, M. (2017, January 24–26). Semi-supervised classification with graph convolutional networks. Proceedings of the ICLR, Toulon, France.
20. Petar, V., Guillem, C., Arantxa, C., Adriana, R., Pietro, L., and Yoshua, B. (30–May, January 30). Graph attention networks. Proceedings of the ICLR, Vancouver, BC, Canada.
21. Xu, K., Hu, W.H., Jure, L., and Stefanie, J. How powerful are graph neural networks? In Proceedings of the ICLR, New Orleans, LA, USA, 6–9 May 2019.
22. Liu, Z.M., Fang, Y., Liu, C.H., and Steven, C.H. (2021, January 19–27). Node-wise localization of graph neural networks. Proceedings of the IJCAI, Montreal, QC, Canada.10.24963/ijcai.2021/210 ↗
23. Pei, H.B., Wei, B.Z., Kevin, C., Chang, C., Lei, Y., and Yang, B. (2020, January 30). Geom-GCN: Geometric graph convolutional networks. Proceedings of the ICLR, Ababa, Ethiopia.
24. A multi objective model for passenger train services planning: Application to Taiwan’s high-speed rail line10.1016/S0191-2615(99)00013-2 ↗
25. Multi objective bilevel optimization for transportation planning and management problems10.1002/atr.5670360106 ↗
26. The transit network design problem with elastic demand and internalization of external costs: An application to rail frequency optimization10.1016/j.trc.2011.02.008 ↗
27. A Matheuristic Iterative Approach for Profit-Oriented Line Planning Applied to the Chinese High-Speed Railway Network
28. Scholl, S. (2005). Customer-Oriented Line Planning, University of Kaiserslautern.
29. Schöbel, B., and Scholl, S. (2005, January 1). Line planning with minimal transfers. Proceedings of the 5th Workshop on Algorithmic Methods and Models for Optimization of Railways, Dagstuhl, Germany.
30. Schöbel, A., and Scholl, S. (2006). Line Planning with Minimal Traveling Time, Schloss Dagstuhl-Leibniz-Zentrum für Informatik. 5th Workshop on Algorithmic Methods and Models for Optimization of Railways (ATMOS’05).
31. Fu, H.L. (2010). Research on Theory and Methods of Line Planning for High-Speed Railways, Beijing Jiaotong University. (In Chinese).
32. A line planning approach for high-speed railway network with time-varying demand10.1016/j.cie.2021.107547 ↗
33. A two-layer optimization model for high-speed railway line planning10.1631/jzus.A11GT016 ↗
34. T-gcn: A temporal graph convolutional network for traffic prediction10.1109/TITS.2019.2935152 ↗
35. Deep architecture for traffic flow prediction: Deep belief networks with multitask learning10.1109/TITS.2014.2311123 ↗
36. Shi, M., Tang, Y.F., Zhu, X.Q., Wilson, D.A., and Liu, J.X. (2020, January 19–26). Multi-Class Imbalanced Graph Convolutional Network Learning. Proceedings of the 29th International Joint Conference on Artificial Intelligence, IJCAI, Virtual.10.24963/ijcai.2020/398 ↗
37. Ghorbani, M., Kazi, A., Baghshah, M.S., Rabiee, H.R., and Navab, N. (2021). RA-GCN: Graph Convolutional Network for Disease Prediction Problems with Imbalanced Data. arXiv.10.1016/j.media.2021.102272 ↗
38. A review on classification of imbalanced data for wireless sensor networks10.1177/1550147720916404 ↗
39. Yang, Y.Z., and Xu, Z. (2020, January 6–12). Rethinking the value of labels for improving class-imbalanced learning. Proceedings of the Advances in Neural Information Processing Systems 33, Annual Conference on Neural Information Processing Systems, Virtual.
40. Chen, D.L., Lin, Y.K., Zhao, G.X., Ren, X.C., Li, P., Zhou, J., and Sun, X. (2021, January 6–14). Topology-Imbalance Learning for Semi-Supervised Node Classification. Proceedings of the NeurIPS, Virtual.
41. Huang, C., Li, Y.N., Loy, C.C., and Tang, X. (2016, January 27–30). Learning Deep Representation for Imbalanced Classification. Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, Las Vegas, NV, USA.10.1109/CVPR.2016.580 ↗
42. Ren, M.Y., Zeng, W.Y., Yang, B., and Urtasun, B. (2018, January 10–15). Learning to Reweight Examples for Robust Deep Learning. Proceedings of the International Conference on Machine Learning, PMLR, Stockholm, Sweden.
43. Cui, Y., Li, M., Jia, T., Lin, Y., Song, Y., and Belongie, S.J. (2019, January 16–20). Class-Balanced Loss Based on Effective Number of Samples. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, Long Beach, CA, USA.10.1109/CVPR.2019.00949 ↗
44. Cao, K.D., Wei, C., Gaidon, A., Aréchiga, N., and Ma, T.Y. (2019, January 8–14). Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss. Proceedings of the Advances in Neural Information Processing Systems 32, Annual Conference on Neural Information Processing Systems 2019, NeurIPS, Vancouver, BC, Canada.
45. Liu, Z.M., Nguyen, T.K., and Fang, Y. (2021, January 14–18). Tail-GNN: Tail-Node Graph Neural Networks. Proceedings of the KDD, Virtual.10.1145/3447548.3467276 ↗
46. Leroy, V., Cambazoglu, B.B., and Bonchi, F. (2010, January 24–28). Cold start link prediction. Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington, DC, USA.10.1145/1835804.1835855 ↗
47. An approach to cold-start link prediction: Establishing connections between non-topological and topological information10.1109/TKDE.2016.2597823 ↗
48. Wang, H., Zhang, F., Hou, M., and Qi, Y. (2018, January 2). Shine: Signed heterogeneous information network embedding for sentiment link prediction. Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, Angeles, CA, USA.10.1145/3159652.3159666 ↗
49. Ge, L., and Zhang, A. (2012, January 26–28). Pseudo cold start link prediction with multiple sources in social networks. Proceedings of the 2012 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics 2012, Anaheim, CA, USA.10.1137/1.9781611972825.66 ↗
50. Cold-start link prediction integrating community information via multi-nonnegative matrix factorization10.1016/j.chaos.2022.112421 ↗
51. Bryan, P., Rami, A., and Steven, S. (2014, January 24–27). DeepWalk: Online learning of social representations. Proceedings of the KDD, New York, NY, USA.
52. Grover, A., and Leskovec, J. (2016, January 13–17). node2vec: Scalable Feature Learning for Networks. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, San Francisco, CA, USA.10.1145/2939672.2939754 ↗