Exploration of Travel Patterns of Intercity Metro Passengers—A Case Study in Changsha–Zhuzhou–Xiangtan Metropolitan Area, China
Abstract
:1. Introduction
2. Materials
2.1. Study Area and Data
2.2. Ridership Characteristics
3. Methods
3.1. GMM
3.2. Parameter Estimation
- (1)
- E-step: Obtain the probability :
- (2)
- M-step: Re-estimate the model parameters with the maximum likelihood estimation based on the probability of each Gaussian distribution calculated in step E.
4. Results and Discussion
4.1. GMM Clustering Based on Travel Time
4.1.1. Clustering Results Based on Travel Time
4.1.2. Analysis of Travel-Time Cluster
4.2. GMM Clustering Based on Stay Time
4.2.1. Clustering Results Based on Stay Time
4.2.2. Analysis of Weekday and Weekend Ridership
5. Conclusions
- (1)
- The intercity ridership shows clear commuting patterns with AM and PM peaks on weekdays for both directions. However, on weekends, the ridership from Xiangtan to Changsha peaks at 9 AM to 11 AM, whereas the ridership from Changsha to Xiangtan peaks at 5 PM to 9 PM, which shows a clear tourism pattern. That is, many passengers living in Xiangtan went to Changsha for sightseeing, shopping, etc., as Changsha is one of hottest tourist destinations in China. In addition, the intercity ridership on weekends is much higher than that on weekdays.
- (2)
- The travel time shows no significant differences by direction or day of the week. Based on travel time, the GMM classified intercity ridership into two groups, i.e., the short-travel-time group with the average travel time being 32.9 min, and the long-travel-time group with the average travel time being 68.93 min, with the latter being the majority. For ridership from Xiangtan to Changsha, the short-travel-time group mainly alights around the Yanghu area, which is the closest well-developed community in Changsha to Xiangtan, whereas the long-travel-time group mainly alights around the city center of Changsha.
- (3)
- The stay time shows significant differences between weekends and weekdays. Based on stay time in Changsha, the GMM divided intercity ridership into two categories as well. Most passengers stay around 4.3 h, whereas the rest stay around 23.47 h. On weekends, the intercity passengers for tourism have different stay modes, but their destinations are similar. On weekdays, there are large differences in travel destinations between the short-stay-time group and the long-stay-time group, and their travel purposes are more diverse, including commuting (work, school, etc.), leisure, and services (medical, etc.).
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Pan, Z.; Zhang, T.; Tang, H.; Wang, Y. Research on the“Four-Network Integration”System of Multi-Level Rail Transit. J. Transp. Eng. 2020, 20, 1–8. [Google Scholar]
- Shanghai and Suzhou Subways Are Connected, Why Are There More and More Cross-City Lines? Available online: https://www.thepaper.cn/newsDetail_forward_22169506?commTag=true (accessed on 10 September 2024).
- Xiao, Y. Intercity Subways Should Not Be Widely Promoted. Rev. Econ. Res. 2013, 71, 37. [Google Scholar]
- Zhao, Z.; Zhao, S.; Han, Z.; Liu, L.; Jia, J.; Wang, S. The Impact Of The Covid-19 Pandemic On Intercity Travel During Chinese Festivals. Hum. Geogr. 2022, 37, 141–149+172. [Google Scholar]
- Zhan, W.; Xi, G.; Ju, Y.; Shi, F. Temporal Heterogeneity and Impact Mechanism of Intercity Travel Time in the Yangtze River Delta Region. Trop. Geogr. 2024, 44, 850–863. [Google Scholar]
- Zhong, J.; Deng, Q.; Zhou, J. Railway Passenger Flow Characteristics Between Shenzhen and Cities in the Guangdong Hong Kong Macao Greater Bay Area. Traffic Transp. 2024, 37, 152–155. [Google Scholar]
- Wang, S.; Zhao, M. Intercity Trips and Activities: The Case of Guangzhou and Foshan. Urban Plan. Forum 2012, 3, 23–29. [Google Scholar]
- El Mahrsi, M.K.; Come, E.; Oukhellou, L.; Verleysen, M. Clustering Smart Card Data for Urban Mobility Analysis. IEEE Trans. Intell. Transp. Syst. 2017, 18, 712–728. [Google Scholar] [CrossRef]
- Zhao, X.; Wu, Y.; Ren, G.; Ji, K.; Qian, W. Clustering Analysis of Ridership Patterns at Subway Stations: A Case in Nanjing, China. J. Urban Plan. Dev. 2019, 145, 04019005. [Google Scholar] [CrossRef]
- Zhang, S.; Huang, J.; Zhu, G.; Xu, X.; Zhang, Z. Passenger Flow Trajectory Prediction Model of Urban Rail Transit Based on Passenger Flow Category. Comput. Eng. Des. 2023, 44, 1829–1835. [Google Scholar]
- Yao, Z.; Gao, G.; Zheng, H.; Huang, Z. Time Distribution Types of Passenger Flow Between Urban Rail Transit Stations Based on Spectral Clustering. Urban Rapid Rail Transit 2022, 35, 99–104+116. [Google Scholar]
- Zhang, H.; Ma, W. Subway Passenger Flow Forecasting Model Based on Temporal and Spatial Characteristics. Comput. Sci. 2019, 46, 292–299. [Google Scholar]
- Zhu, Y.; Huang, D.; Zhang, B. Clustering with Distributional Factors Based on Gaussian Mixture Model. Stat. Res. 2024, 41, 147–160. [Google Scholar]
- McLachlan, G.J.; Lee, S.X.; Rathnayake, S.I. Finite Mixture Models. Annu. Rev. Stat. Its Appl. 2019, 6, 355–378. [Google Scholar] [CrossRef]
- Wang, Y.; Liu, H.; Peng, S.; Hu, Z.; Wu, L. Short-Term Power Forecasting Method of Wind Farm Based on Gaussian Mixture Model Clustering. Autom. Electr. Power Syst. 2021, 45, 37–43. [Google Scholar]
- Li, Z.; Tian, X.; Li, Z.; Zhou, W.; Zhou, Z.; Zhong, M. Risk Analysis of Metro Station Passenger Flow Based on Passenger Flow Patterns. J. Tsinghua Univ. (Sci. Technol.) 2019, 59, 854–860. [Google Scholar]
- Zhenhong, Y.; Feng, C.; Zijia, W.; Jianling, H.; Bo, W. Classifications of Metro Stations by Clustering Smart Card Data Using the Gaussian Mixture Model. Urban Rapid Rail Transit 2017, 30, 48–51+107. [Google Scholar]
- Mirzal, A. Statistical Analysis of Microarray Data Clustering Using NMF, Spectral Clustering, Kmeans, and GMM. IEEE-ACM Trans. Comput. Biol. Bioinform. 2022, 19, 1173–1192. [Google Scholar] [CrossRef]
- Yue, Y.; Lan, T.; Yeh, A.G.O.; Li, Q.Q. Zooming into Individuals to Understand the Collective: A Review of Trajectory-Based Travel Behaviour Studies. Travel Behav. Soc. 2014, 1, 69–78. [Google Scholar] [CrossRef]
- Yang, C.; Fu, X.; Dong, R. Investigating Spatial-Temporal Characteristics of Joint Activity/Travel Behaviour with Smart Card Data. Travel Behav. Soc. 2025, 38, 100899. [Google Scholar] [CrossRef]
- Arana, P.; Cabezudo, S.; Peñalba, M. Influence of Weather Conditions on Transit Ridership: A Statistical Study Using Data from Smartcards. Transp. Res. Part A Policy Pract. 2014, 59, 1–12. [Google Scholar] [CrossRef]
- Ali, A.; Kim, J.; Lee, S. Travel Behavior Analysis Using Smart Card Data. KSCE J. Civ. Eng. 2016, 20, 1532–1539. [Google Scholar] [CrossRef]
- Fang, Q.; Homma, R.; Inoue, T.; Liu, Q.; Zheng, Q. Spatio-Temporal Variation of Urban Bus Ridership Using Smart Card Data in a Compact City. Int. Rev. Spat. Plan. Sustain. Dev. 2023, 11, 192–207. [Google Scholar] [CrossRef] [PubMed]
- Zhang, Y.; Manley, E.; Martens, K.; Batty, M. A Metro Smart Card Data-Based Analysis of Group Travel Behaviour in Shanghai, China. J. Transp. Geogr. 2024, 114, 103764. [Google Scholar] [CrossRef]
- Wu, Y.; Liu, T.; Gong, L.; Luo, Q.; Du, B. Mining Smart Card Data to Estimate Transfer Passenger Flow in a Metro Network. IET Intell. Transp. Syst. 2024, 18, 1830–1846. [Google Scholar] [CrossRef]
- Redner, R.A.; Walker, H.F. Mixture Densities, Maximum Likelihood and the EM Algorithm. SIAM Rev. 1984, 26, 195–239. [Google Scholar] [CrossRef]
- Zhang, M.; Li, L.; Yang, X.; Sun, G.; Cai, Y. A Load Classification Method Based on Gaussian Mixture Model Clustering and Multi-Dimensional Scaling Analysis. Power Syst. Technol. 2020, 44, 4283–4296. [Google Scholar]
- Yu, J.; Qin, S.J. Multimode Process Monitoring with Bayesian Inference-Based Finite Gaussian Mixture Models. AIChE J. 2008, 54, 1811–1829. [Google Scholar] [CrossRef]
Type | Serving Area | Designed Speed/(km/h) | Distance Between Stations/km | Line Length/km | |
---|---|---|---|---|---|
Urban rail transit | Urban areas of cities | 80~100 | 0.5~1 | <40 | |
Intracity railway | Connecting urban areas and suburbs | 100~160 | 3~7 | 30~80 | |
Intercity railway | Metropolitan areas | 120~200 | 5~20 | >100 | |
Trunk railway | General railway | Long-distance travels in the country | <160 | 10~50 | >300 |
High-speed railway | Long-distance travels in the country | 250~350 | 30~60 | >300 |
Passenger ID | Boarding Time | Boarding Station | Boarding Line | Alighting Time | Alighting Station | Alighting Line |
---|---|---|---|---|---|---|
309672939 | 6 September 2023 6:26 | Xiangtan North | Xihuan Line | 6 September 2023 7:32 | Kaifu Temple | Line 1 |
308326233 | 6 September 2023 6:23 | Guanziling | Line 4 | 6 September 2023 7:47 | Xiangtan North | Xihuan Line |
… | … | … | … | … | … | … |
Direction | Wednesday | Thursday | Saturday | Sunday |
---|---|---|---|---|
Xiangtan to Changsha | 3054 | 3102 | 6185 | 5403 |
Changsha to Xiangtan | 3166 | 3084 | 5997 | 6679 |
Type | Weight | Mean | Standard Deviation |
---|---|---|---|
Gaussian distribution 1 | 0.1854 | 32.90 | 6.83 |
Gaussian distribution 2 | 0.8146 | 68.93 | 15.59 |
Type | Weight | Mean | Standard Deviation |
---|---|---|---|
Gaussian distribution 1 | 0.7912 | 4.30 | 2.75 |
Gaussian distribution 2 | 0.2088 | 23.47 | 5.25 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Xie, Y.; Cheng, B.; Ren, W.; Zhou, C.; Liu, C. Exploration of Travel Patterns of Intercity Metro Passengers—A Case Study in Changsha–Zhuzhou–Xiangtan Metropolitan Area, China. Appl. Sci. 2025, 15, 2947. https://doi.org/10.3390/app15062947
Xie Y, Cheng B, Ren W, Zhou C, Liu C. Exploration of Travel Patterns of Intercity Metro Passengers—A Case Study in Changsha–Zhuzhou–Xiangtan Metropolitan Area, China. Applied Sciences. 2025; 15(6):2947. https://doi.org/10.3390/app15062947
Chicago/Turabian StyleXie, Yao, Biao Cheng, Wei Ren, Cuizhu Zhou, and Chenhui Liu. 2025. "Exploration of Travel Patterns of Intercity Metro Passengers—A Case Study in Changsha–Zhuzhou–Xiangtan Metropolitan Area, China" Applied Sciences 15, no. 6: 2947. https://doi.org/10.3390/app15062947
APA StyleXie, Y., Cheng, B., Ren, W., Zhou, C., & Liu, C. (2025). Exploration of Travel Patterns of Intercity Metro Passengers—A Case Study in Changsha–Zhuzhou–Xiangtan Metropolitan Area, China. Applied Sciences, 15(6), 2947. https://doi.org/10.3390/app15062947