Utilizing an Adaptive Neuro-Fuzzy Inference System (ANFIS) for Overcrowding Level Risk Assessment in Railway Stations
Source abstract
Abstract
The railway network plays a significant role (both economically and socially) in assisting the reduction of urban traffic congestion. It also accelerates the decarbonization in cities, societies and built environments. To ensure the safe and secure operation of stations and capture the real-time risk status, it is imperative to consider a dynamic and smart method for managing risk factors in stations. In this research, a framework to develop an intelligent system for managing risk is suggested. The adaptive neuro-fuzzy inference system (ANFIS) is proposed as a powerful, intelligently selected model to improve risk management and manage uncertainties in risk variables. The objective of this study is twofold. First, we review current methods applied to predict the risk level in the flow. Second, we develop smart risk assessment and management measures (or indicators) to improve our understanding of the safety of railway stations in real-time. Two parameters are selected as input for the risk level relating to overcrowding: the transfer efficiency and retention rate of the platform. This study is the world’s first to establish the hybrid artificial intelligence (AI) model, which has the potency to manage risk uncertainties and learns through artificial neural networks (ANNs) by integrated training processes. The prediction result shows very high accuracy in predicting the risk level performance, and proves the AI model capabilities to learn, to make predictions, and to capture risk level values in real time. Such risk information is extremely critical for decision making processes in managing safety and risks, especially when uncertain disruptions incur (e.g., COVID-19, disasters, etc.). The novel insights stemmed from this study will lead to more effective and efficient risk management for single and clustered railway station facilities towards safer, smarter, and more resilient transportation systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Traffic Prediction and Management Techniques · Traffic and Road Safety · Transportation Planning and Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Birmingham Centre for Railway Research and Education, The University of Birmingham, Birmingham B15 2TT, UK
The School of Science, Engineering and Environment, The University of Salford, Manchester M5 4WT, UK
Funding
H2020 Marie Skłodowska-Curie Actions
References (100+)
Show source-provided references
1. An algorithm for improved performance of railway condition monitoring equipment: Alternating-current point machine case study10.1016/j.trc.2013.01.008 ↗
2. Chen, S., Di, Y., Liu, S., and Wang, B. (2017). Modelling and analysis on emergency evacuation from metro stations. Math. Probl. Eng., 2017.10.1155/2017/2623684 ↗
3. Urban rail transit in China: Progress report and analysis (2008–2015)10.1007/s40864-016-0048-7 ↗
4. Munro, A. (2018). HS2 railway, UK—Why the country needs it. Proc. Inst. Civ. Eng. Transp., 1–9.
5. Delivering better transport? An evaluation of the ten-year plan for the railway industry10.1111/1467-9302.00317 ↗
6. Gavin, K., Oslakovic, I.S., Vajdic, M., Puz, G., and Sporcic, V. (2012, January 7–9). Smart maintenance and analysis of railway transport infrastructure (smart rail). Proceedings of the 2nd International Conference on Road and Rail Infrastructure, Dubrovnik, Croatia.
7. Health and safety hazards associated with subways: A review10.1093/jurban/jti004 ↗
8. Lathia, N., and Capra, L. (2011, January 17–21). How Smart is your smartcard? Measuring travel behaviours, perceptions, and incentives. Proceedings of the 13th International Conference on Ubiquitous Information Management and Communication, Beijing, China.10.1145/2030112.2030152 ↗
9. Alawad, H., and Kaewunruen, S. (2018). Wireless sensor networks: Toward smarter railway stations. Infrastructures, 3.10.3390/infrastructures3030024 ↗
10. Exploring time variants for short-term passenger flow10.1016/j.jtrangeo.2010.04.003 ↗
11. Urban flows prediction from spatiotemporal data using machine learning: A survey10.1016/j.inffus.2020.01.002 ↗
12. Rail passenger crowding, stress, health and safety in Britain10.1016/j.tra.2005.07.001 ↗
13. Framework for centralized and dynamic pedestrian management in railway stations
14. A fuzzy reasoning and fuzzy-analytical hierarchy process based approach to the process of railway risk information: A railway risk management system10.1016/j.ins.2011.04.051 ↗
15. Crowd monitoring using image processing10.1049/ecej:19950106 ↗
16. Alawad, H., Codru, S., and Kaewunruen, S. (2018, January 17–19). Complex-system decision framework for managing risks to rail stations at airports from terrorist threats. Proceedings of the 5th International Conference on Road and Rail Infrastructure, Zadar, Croatia.10.5592/CO/CETRA.2018.665 ↗
17. Congestion risk evaluation and precaution of passenger flow in metro stations10.2174/1874149501610010093 ↗
18. Zhu, B., Liu, T., and Tang, Y. (2008, January 22–25). Research on pedestrian evacuation simulation based on fuzzy logic. Proceedings of the 2008 9th International Conference on Computer-Aided Industrial Design and Conceptual Design, Kunming, China.
19. Ibrahim, A.M., Venkat, I., Subramanian, K.G., Khader, A.T., and De Wilde, P. (2016). Intelligent evacuation management systems: A review. ACM Trans. Intell. Syst. Technol., 7.10.1145/2842630 ↗
20. A dynamic multiagent simulation of mobility in a train station10.1016/j.trpro.2017.12.100 ↗
21. Wei, Y., and Chen, M.-C. (2012). Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks. Transp. Res. Part C Emerg. Technol.10.1016/j.trc.2011.06.009 ↗
22. Crowding in public transport systems: Effects on users, operation and implications for the estimation of demand10.1016/j.tra.2013.06.005 ↗
23. Katz, D., and Rahman, M. (2010). Levels of overcrowding in bus system of Dhaka, Bangladesh. Transp. Res. Record J. Transp. Res. Board, 85–91.10.3141/2143-11 ↗
24. Exploring passenger anxiety associated with train travel
25. Measuring rail passenger crowding: Scale development and psychometric properties10.1016/j.trf.2011.11.006 ↗
26. Rose, W. (2003, January 8–10). Modelling the impact of alternative fare structures on train overcrowding. Proceedings of the European Transport Conference, Strasbourg, France.
27. Zhang, Y., Han, J., Liu, J., Zhou, T., Suni, J., and Luo, J. (2017, January 24–26). Safety prediction of rail transit system based on deep learning. Proceedings of the 16th IEEE/ACIS International Conference on Computer and Information Science, Wuhan, China.10.1109/ICIS.2017.7960111 ↗
28. Bus passenger flow congestion risk evaluation model based on the pressure-state-response framework: A case study in Beijing
29. Ning, Y., Huang, Y., Li, J., Liu, Q., Yang, D., Zheng, W., and Liu, H. (2018, January 8–13). ST-DRN: Deep residual networks for spatio-temporal metro stations crowd flows forecast. Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil.10.1109/IJCNN.2018.8489234 ↗
30. Lu, L., and Peng, H. (2018, January 21–23). Research on urban rail transit operation safety evaluation system based on ISM. Proceedings of the APCIM & ICTTE 2018, Beijing, China.10.1145/3321619.3321632 ↗
31. Risk evaluation of railway rolling stock failures using FMECA technique: A case study of passenger door system10.1007/s40864-016-0043-z ↗
32. Research on safety risk assessment of large-scale railway passenger station10.4028/www.scientific.net/AMM.361-363.1923 ↗
33. Huang, Z., Xu, R., and Zhou, F. (2017, January 8–10). A multilevel fuzzy comprehensive evaluation model for operation safety of the large high-speed railway passenger station. Proceedings of the 2017 4th International Conference on Transportation Information and Safety, Banff, AB, Canada.
34. Research and application on risk assessment DEA model of crowd crushing and trampling accidents in subway stations10.1016/j.proeng.2012.08.085 ↗
35. Safety risks in rail stations: An interactive approach
36. An incident database for improving metro safety: The case of shanghai10.1016/j.ssci.2015.11.023 ↗
37. Gu, X., Zhang, L., Li, D., and Ma, L. (2012, January 20–21). Analysis on operation risk factors of urban rail transit based on fuzzy analytical hierarchy process. Proceedings of the 2012 International Conference on Information Management, Innovation Management and Industrial Engineering, Sanya, China.10.1109/ICIII.2012.6339958 ↗
38. Zhang, H., and Sun, Q. (2020). An integrated MCDM approach to train derailment risk response strategy selection. Symmetry (Basel), 12.10.3390/sym12010047 ↗
39. Sun, Y., Zhang, G., and Yin, H. (2014). Passenger flow prediction of subway transfer stations based on nonparametric regression model. Discret. Dyn. Nat. Soc., 2014.10.1155/2014/397154 ↗
40. Tu, Q., Weng, J.C., and Wang, C. (2017, January 8–10). A dynamic identification method of passenger flow congestion risk in rail transit hub station based on grey clustering. Proceedings of the 2017 4th International Conference on Transportation Information and Safety, Banff, AB, Canada.10.1109/ICTIS.2017.8047860 ↗
41. Huang, W., and Zhang, Y. (2020). Railway dangerous goods transportation system risk assessment: An approach combining FMEA with pessimistic–optimistic fuzzy information axiom considering acceptable risk coefficient. IEEE Trans. Reliab.10.1109/TR.2020.2973431 ↗
42. Traffic-incident detection-algorithm based on nonparametric regression10.1109/TITS.2004.843112 ↗
43. Gong, Y., Li, Z., Zhang, J., Liu, W., and Zheng, Y. (2020). Online spatio-temporal crowd flow distribution prediction for complex metro system. IEEE Trans. Knowl. Data Eng., 1.
44. Short-term abnormal passenger flow prediction based on the fusion of SVR and LSTM10.1109/ACCESS.2019.2907739 ↗
45. Zhang, Q., Zhuang, Y., Wei, Y., Jiang, H., and Yang, H. (2020). Railway safety risk assessment and control optimization method based on FTA-FPN: A case study of chinese high-speed railway station. J. Adv. Transp., 2020.10.1155/2020/3158468 ↗
46. Railway passenger flow recognition algorithm for terminal station based on cost theory and automatic frequency control10.1109/ACCESS.2020.2968721 ↗
47. Heidarysafa, M., Kowsari, K., Barnes, L., and Brown, D. (2018, January 17–20). Analysis of railway accidents’ narratives using deep learning. Proceedings of the 17th IEEE International Conference on Machine Learning and Applications, Orlando, FL, USA.10.1109/ICMLA.2018.00235 ↗
48. Forecasting short-term subway passenger flow under special events scenarios using multiscale radial basis function networks10.1016/j.trc.2017.02.005 ↗
49. Learning from accidents: Machine learning for safety at railway stations10.1109/ACCESS.2019.2962072 ↗
50. Hua, L., Zheng, W., and Gao, S. (2019, January 27–30). Extraction and analysis of risk factors from Chinese railway accident reports. Proceedings of the 2019 IEEE Intelligent Transportation Systems Conference, ITSC, Auckland, New Zealand.10.1109/ITSC.2019.8917094 ↗
51. Liu, P., Xie, M., Bian, J., Li, H., and Song, L. (2020). A hybrid PSO–SVM model based on safety risk prediction for the design process in metro station construction. Int. J. Environ. Res. Public Health, 17.10.3390/ijerph17051714 ↗
52. Noor Syeda, K., Noorulhassan Shirazi, S., Asad Ali Naqvi, S., Parkinson, H.J., and Bamford, G. (2017). Big Data and Natural Language Processing for Analysing Railway Safety. Innovative Applications of Big Data in the Railway Industry, IGI Global Publishing.10.4018/978-1-5225-3176-0.ch011 ↗
53. Coppola, P., and Silvestri, F. (2020). Assessing travelers’ safety and security perception in railway stations. Case Stud. Transp. Policy.10.1016/j.cstp.2020.05.006 ↗
54. A risk-based analysis of design practices in regard to passenger hazard exposure in open mass transit stations10.1007/s40864-019-00119-x ↗
55. Ying, M., Kaminishi, K., Duysters, G., De Hoyos, A., Takala, J., and Yusof, R. (The Safety Risk Assessment of Railway Station under Terrorist Attacks Based on AHP, 2016). The Safety Risk Assessment of Railway Station under Terrorist Attacks Based on AHP.
56. The safety management of urban rail transit based on operation fault log10.1016/j.ssci.2016.12.015 ↗
57. Risk analysis on Beijing metro operation initiated by human factors
58. Peng, W., and Lin, Z. (2018, January 21–22). Research on risk assessment of railway freight station based on nonlinear combination of ahp-entropy. Proceedings of the 2018 15th International Conference on Service Systems and Service Management, ICSSSM, Hangzhou, China.10.1109/ICSSSM.2018.8465075 ↗
59. DeepPF: A deep learning based architecture for metro passenger flow prediction10.1016/j.trc.2019.01.027 ↗
60. Traffic flow prediction with big data: A deep learning approach
61. Jiang, R., Song, X., Wang, Z., Huang, D., Song, X., Kim, K.S., Xia, T., Cai, Z., and Shibasaki, R. (2019, January 4–8). Deepurbanevent: A system for predicting citywide crowd dynamics at big events. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.10.1145/3292500.3330654 ↗
62. A Deep Learning Approach Towards Railway Safety Risk Assessment10.1109/ACCESS.2020.2997946 ↗
63. Lopez, A.J., Semanjski, I., Gautama, S., and Ochoa, D. (2017). Assessment of smartphone positioning data quality in the scope of citizen science contributions. Mob. Inf. Syst., 2017.10.1155/2017/4043237 ↗
64. Monitoring the performance of the pedestrian transfer function of train stations using automatic fare collection data10.1016/j.trpro.2014.09.107 ↗
65. Van Den Heuvel, J., Voskamp, A., Daamen, W., and Hoogendoorn, S.P. (2015). Using bluetooth to estimate the impact of congestion on pedestrian route choice at train stations. Traffic and Granular Flow ‘13, Springer International Publishing.10.1007/978-3-319-10629-8_9 ↗
66. Ganansia, F., Carincotte, C., Descamps, A., and Chaudy, C. (2014, January 14–17). A promising approach to people flow assessment in railway stations using standard CCTV networks. Proceedings of the Transport Research Arena (TRA), Paris, France.
67. Kaewunruen, S., Alawad, H., and Cotruta, S. (2018). A Decision Framework for Managing the Risk of Terrorist Threats at Rail Stations Interconnected with Airports. Safety, 4.10.3390/safety4030036 ↗
68. Ceapa, I., Smith, C., and Capra, L. (2012, January 12–16). Avoiding the crowds: Understanding Tube station congestion patterns from trip data. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Beijing, China.10.1145/2346496.2346518 ↗
69. Health and Safety Laboratory (2005). Health and Safety Effects of Crowding.
70. Rail Safety and Standards Board Limited (2017). RIS-3703-TOM/3:2017—Passenger Train Dispatch and Platform Safety Measures, Rail Safety and Standards Board.
71. Helbing, D., Johansson, A., and Al-Abideen, H.Z. (2007). Dynamics of crowd disasters: An empirical study. Phys. Rev. E Stat. Nonlinear, Soft Matter Phys., 75.10.1103/PhysRevE.75.046109 ↗
72. Rational use of face masks in the COVID-19 pandemic10.1016/S2213-2600(20)30134-X ↗
73. Social force model for pedestrian dynamics10.1103/PhysRevE.51.4282 ↗
74. ACP-based control and management of urban rail transportation systems10.1109/MIS.2011.25 ↗
75. Rail accident analysis using large-scale investigations of train derailments on switches and crossings: Comparing the performances of a novel stochastic mathematical prediction and various assumptions10.1016/j.engfailanal.2019.04.010 ↗
76. Bayesian network-based human error reliability assessment of derailments10.1016/j.ress.2020.106825 ↗
77. Modelling the spillover effects of rail passenger crowding on individual well being and organisational behaviour
78. Negnevitsky, M. (2002). Artificial Intelligence—A Guide to Intelligent Systems, Addison Wesley.
79. Self-learning fuzzy controllers based on temporal back propagation10.1109/72.159060 ↗
80. ANFIS: Adaptive-network-based fuzzy inference system10.1109/21.256541 ↗
81. Neuro-fuzzy rule generation: Survey in soft computing network10.1109/72.846746 ↗
82. A survey on analysis and design of model-based fuzzy control systems10.1109/TFUZZ.2006.883415 ↗
83. Recent advances in neuro-fuzzy system: A survey10.1016/j.knosys.2018.04.014 ↗
84. Nelles, O. (2001). Nonlinear System Identification, Springer.10.1007/978-3-662-04323-3 ↗
85. Neuro-fuzzy systems: A survey
86. Construction project risk assessment by using adaptive-network-based fuzzy inference system: An empirical study10.1007/s12205-014-0139-5 ↗
87. Zhu, W., and Cao, D. (2009, January 10–11). Expressway management risk evaluation based on fuzzy neural networks. Proceedings of the 2009 Second International Conference on Intelligent Computation Technology and Automation, Changsha, Hunan, China.
88. A model of adaptive neural-based fuzzy inference system (ANFIS) for prediction of friction coefficient in open channel flow
89. ANFIS model for assessing near-miss risk during tanker shipping voyages10.1080/03088839.2019.1569765 ↗
90. Value of rescheduling of rail inspection10.1177/0954409718820968 ↗
91. Öztaysi, B., Behret, H., Kabak, Ö., Sarı, I.U., and Kahraman, C. (2013). Fuzzy inference systems for disaster response. Decision Aid Models for Disaster Management and Emergencies, Atlantis Press.10.2991/978-94-91216-74-9_4 ↗
92. Risk assessment of construction projects using network based adaptive fuzzy system
93. Zhao, J., and Bose, B.K. (2002, January 5–8). Evaluation of membership functions for fuzzy logic controlled induction motor drive. Proceedings of the IEEE 2002 28th Annual Conference of the Industrial Electronics Society, IECON 02, Sevilla, Spain.
94. Nedjah, N., and Mourelle, L.d.M. (2006). Fuzzy Systems Engineering: Theory and Practice, Springer.10.1007/b102051 ↗
95. Comparison of Mamdani-type and Sugeno-type fuzzy inference systems for air conditioning system
96. Identification using ANFIS with intelligent hybrid stable learning algorithm approaches and stability analysis of training methods10.1016/j.asoc.2008.11.001 ↗
97. Fuzzy identification of systems and its applications to modeling and control10.1109/TSMC.1985.6313399 ↗
98. Neuro-fuzzy approaches for pipeline condition assessment10.1080/10589750701327858 ↗
99. Adaptive neuro-fuzzy inference system in predicting the success of student’s in a particular course10.7763/IJCTE.2015.V7.926 ↗
100. Neuro-fuzzy methods for nonlinear system identification10.1016/S1367-5788(03)00009-9 ↗