A comparative analysis of perceptions of insecurity in Milan and Beijing metro stations

Abstract

Metro stations, as essential public spaces, not only serve as vital transportation hubs but also form part of the broader built environment that shapes people’s perceptions of insecurity. An important concern for passengers in these environments is safety, particularly in underground public space where the design and organization of the physical surroundings play a crucial role. Despite various modern renovations in older metro stations, newer stations are generally perceived as safer. To understand this discrepancy, this research compares how visual factors in the built environments of old and new metro stations influence people’s perceptions of insecurity. By examining two cities—Milan and Beijing, which follow distinct urban development models—this research also explores how differences in urbanization processes affect the contrast between old and new stations. This research introduces a novel methodology for analyzing underground public space by integrating 360-degree image capture, an enhanced semantic segmentation process, and predictive modeling using XGBoost and SHAP to reveal the complex relationships between these visual factors and safety perceptions. The results indicate that while factors like artificial light, floor, and the presence of people are significant across all stations, certain factors are particularly influential in specific contexts—for example, exposed pipes are more negatively associated with safety perception in Beijing’s old stations, and platform doors have a strongly positive effect in Milan’s new stations. The findings provide valuable insights for guiding the modernization of metro stations in the future, and offering an innovative approach to studying underground public space.

Keywords

Metro station / Underground public space / Perceptions of insecurity / Visual factors / Machine learning models / XGBoost

References

[1] Antrop, M. , 2004. Landscape change and the urbanization process in Europe. Landscape and urban planning. Development of European Landscapes 67, 9- 26.

[2] ATM , 2019. Atm, record di passeggeri e centomila multe in più. Lineadiretta ATM.

[3] ATM Group , 2023. Integrated Annual Report.

[4] Bădău, F. , 2022. Railway interlockings-a review of the current state of railway safety technology in Europe. Promet-Traffic & Transp. 34, 443- 454.

[5] Birch, E.L. , 2016. The new urban agenda's road map for planning urban spatial development: tangible, manageable and measurable. U. N. Chron. 53, 8- 11.

[6] Ceccato, V. , 2013. Moving Safely: Crime and Perceived Safety in Stockholm's Subway Stations. Lexington Books.

[7] Ceccato, V. , Loukaitou-Sideris, A. , 2021. Fear of sexual harassment and its impact on safety perceptions in transit environments: a global perspective. Violence Against Women 28 (1), 26- 48.

[8] Ceccato, V. , Paz, Y. , 2017. Crime in São Paulo's metro system: sexual crimes against women. Crime Prev. Community Saf. Int. J. 19, 211- 226.

[9] Ceccato, V. , Uittenbogaard, A. , Bamzar, R. , 2013. Security in Stockholm's underground stations: the importance of environmental attributes and context. Secur. J. 26, 33- 59.

[10] Chaoju, Y. , Jian, R. , 2024. Road segmentation algorithm based on improved YOLOv8-seg. In: 2024 IEEE 4th International Conference on Electronic Technology, Communication and Information(ICETCI). Presented at the 2024 IEEE 4th International Conference on Electronic Technology, Communication and Information(ICETCI), pp. 1512-1516.

[11] Chen, T. , Guestrin, C. , 2016. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '16. Association for Computing Machinery, New York, NY, USA, pp. 785-794.

[12] Coppola, P. , Silvestri, F. , 2021. Gender inequality in safety and security perceptions in railway stations. Sustainability 13, 4007.

[13] Cozens, P. , Neale, R. , Whitaker, J. , Hillier, D. , 2003. Managing crime and the fear of crime at railway stationseea case study in South Wales (UK). Int. J. Transport Manag. 1, 121- 132.

[14] Cui, Q. , Gong, P. , Yang, G. , Zhang, S. , Huang, Y. , Shen, S. , Wei, B. , Chen, Y. , 2023. Women-oriented evaluation of perceived safety of walking routes between home and mass transit: a case study and methodology test in Guangzhou. Buildings 13, 715.

[15] Dadvand, P. , Bartoll, X. , Basagaña, X. , Dalmau-Bueno, A. , Martinez, D. , Ambros, A. , Cirach, M. , Triguero-Mas, M. , Gascon, M. , Borrell, C. , Nieuwenhuijsen, M.J. , 2016. Green spaces and general health: roles of mental health status, social support, and physical activity. Environ. Int. 91, 161- 167.

[16] Das, A. , Rad, P. , 2020. Opportunities and challenges in explainable artificial intelligence (XAI): a survey. arXiv.2006.11371.

[17] Ding, Y. , Hou, Y. , 2022. Analysis of indoor environment state characteristics of urban rail transit stations based on actual measurements in Chongqing, China. Energy Build. 277, 112544.

[18] Dubey, A. , Naik, N. , Parikh, D. , Raskar, R. , Hidalgo, C.A. , 2016. Deep learning the city: quantifying urban perception at a global scale. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (Eds.), Computer Vision e ECCV 2016, Lecture Notes in Computer Science. Springer International Publishing, Cham, pp. 196-212.

[19] Foot, J. , Rego, R.L. , De Pieri, F. , Farris, J. , Shaw, R. , González, S. , Kahrl, A. , Bloom, N.D. , Lasner, M.G. , Meschiari, C. , Fanghanel, A. , Lou Lobsinger, M. , Jenkins, W. , Macı ás, A. , 2011. Book Reviews. Plan. Perspect. 26, 501- 524.

[20] Guan, F. , Fang, Z. , Wang, L. , Zhang, X. , Zhong, H. , Huang, H. , 2022. Modelling people's perceived scene complexity of realworld environments using street-view panoramas and open geodata. ISPRS J. Photogrammetry Remote Sens. 186, 315- 331.

[21] Guerra, E. , 2015. Suburban transit in Mexico city. ACCESS Magazine 1 (46), 20- 25.

[22] He, L. , Páez, A. , Liu, D. , 2017. Built environment and violent crime: an environmental audit approach using Google Street View. Comput. Environ. Urban Syst. 66, 83- 95.

[23] Hong, J. , Chen, C. , 2014. The role of the built environment on perceived safety from crime and walking: examining direct and indirect impacts. Transportation 41, 1171- 1185.

[24] Ingvardson, J.B. , Nielsen, O.A. , 2022. The influence of vicinity to stations, station characteristics and perceived safety on public transport mode choice: a case study from Copenhagen. Public Transp 14, 459- 480.

[25] Joshi, S. , Bailey, A. , 2023. What happens next? Exploring women's transport motility through the story completion method. J. Transport Geogr. 107, 103547.

[26] Koskela, H. , Pain, R. , 2000. Revisiting fear and place: women's fear of attack and the built environment. Geoforum 31, 269- 280.

[27] Li, J. , Song, Z. , Wen, J. , Cai, C. , Tang, P. , 2024. Exploring nonlinear relationship between built environment and street vitality using machine learning. Presented at the CAADRIA.

[28] Liu, W. , Chen, W. , Feng, Q. , Deo, R.C. , 2018. Situations, challenges and strategies of urban water management in Beijing under rapid urbanization effect. Water Supply 19, 115- 127.

[29] Lundberg, S.M. , Lee, S.-I. , 2017. A Unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems. Curran Associates, Inc.

[30] Navarrete-Hernandez, P. , Vetro, A. , Concha, P. , 2021. Building safer public spaces: exploring gender difference in the perception of safety in public space through urban design interventions. Landsc. Urban Plann. 214, 104180.

[31] Nesoff, E.D. , Milam, A.J. , Pollack, K.M. , Curriero, F.C. , Bowie, J.V. , Gielen, A.C. , Furr-Holden, D.M. , 2018. Novel methods for environmental assessment of pedestrian injury: creation and validation of the inventory for pedestrian safety infrastructure. J. Urban Health 95, 208- 221.

[32] Obiadi, B.N. , Nzewi, N.U. , 2018. The architecture of the urban fronts, the case of urban experience and pressure on the infrastructure. Mgbakoigba: J. Afr. Stud. 7, 114- 130.

[33] Park, Y. , Garcia, M. , 2020. Pedestrian safety perception and urban street settings. International Journal of Sustainable Transportation 14, 860- 871.

[34] Paul, A. , Machavaram, R. , Ambuj, Kumar, D. , Nagar, H. , 2024. Smart solutions for capsicum Harvesting: unleashing the power of YOLO for detection, segmentation, growth stage classification, Counting, and real-time mobile identification. Comput. Electron. Agric. 219, 108832.

[35] Paydar, M. , Kamani-Fard, A. , Etminani-Ghasrodashti, R. , 2017. Perceived security of women in relation to their path choice toward sustainable neighborhood in Santiago, Chile. Cities 60, 289- 300.

[36] Rossetti, T. , Lobel, H. , Rocco, V. , Hurtubia, R. , 2019. Explaining subjective perceptions of public spaces as a function of the built environment: a massive data approach. Landsc. Urban Plann. 181, 169- 178.

[37] Roudbari, A. , Dalvand, M. , Pasiar, N. , Asadi, N. , Yousefi, M. , Masouleh, M.T. , 2023. Autonomous vision-based robotic grasping of household objects: a practical case study. In: 2023 11th RSI International Conference on Robotics and Mechatronics(ICRoM). Presented at the 2023 11th RSI International Conference on Robotics and Mechatronics (ICRoM), pp. 918-924.

[38] Ryu, S.-E. , Shin, D.-H. , Chung, K. , 2020. Prediction model of dementia risk based on XGBoost using derived variable extraction and hyper parameter optimization. IEEE Access 8, 177708- 177720.

[39] Sadeghi, A.R. , Baghi, E.S.M.S. , Shams, F. , Jangjoo, S. , 2023. Women in a safe and healthy urban environment: environmental top priorities for the women's presence in urban public spaces. BMC Wom. Health 23, 163.

[40] Sadeghi, A.R. , Jangjoo, S. , 2022. Women's preferences and urban space: relationship between built environment and women's presence in urban public spaces in Iran. Cities 126, 103694.

[41] Sakip, S.R.M. , Abdullah, A. , 2012. Measuring crime prevention through environmental design in a gated residential area: a pilot survey. Procedia—Social and Behavioral Sciences, ASEAN Conference on Environment-Behaviour Studies (AcE-Bs), Riverside Majestic Hotel, 7-8 July 2010, Kuching, Sarawak, Malaysia 42, 340- 349.

[42] Shao, Q. , Tao, R. , Luca, M.M. , 2022. The effect of urbanization on health care expenditure: evidence from China. Front. Public Health 10, 850872.

[43] Shehadeh, A. , Alshboul, O. , Al Mamlook, R.E. , Hamedat, O. , 2021. Machine learning models for predicting the residual value of heavy construction equipment: an evaluation of modified decision tree, LightGBM, and XGBoost regression. Autom. ConStruct. 129, 103827.

[44] Stjernborg, V. , 2024. Triggers for feelings of insecurity and perceptions of safety in relation to public transport; the experiences of young and active travellers. Applied Mobilities 2024, 1- 21.

[45] The People's Government of Beijing Municipality , 2023. Three Metro Lines to Open for Trial Operation on 30 December, Beijing's Urban Rail Transit Mileage Jumps to First in China (In Chinese).

[46] Tiwari, G. , Phillip, C. , 2021. Development of public transport systems in small cities: a roadmap for achieving sustainable development goal indicator 11.2. IATSS Res. 45, 31- 38.

[47] Valentine, G. , 1990. Women's fear and the design of public space. Built. Environ. 16, 288-303 (1978-).

[48] Wang, Y. , Hayashi, Y. , Kato, H. , 2009. Performance evaluation of subway lines with data envelopment analysis and geographic information systems. A case study of Beijing. Adult Learn 3, 115- 129.

[49] Wu, Y. , Han, Q. , Jin, Q. , Li, J. , Zhang, Y. , 2023. LCA-YOLOv8-Seg: an improved lightweight YOLOv8-Seg for real-time pixel-level crack detection of dams and bridges. Appl. Sci. 13, 10583.

[50] Xiao, L. , Lo, S. , Liu, J. , Zhou, J. , Li, Q. , 2021. Nonlinear and synergistic effects of TOD on urban vibrancy: applying local explanations for gradient boosting decision tree. Sustain. Cities Soc. 72, 103063.

[51] Xu, S. , Li, S. , Wen, R. , 2018. Sensing and detecting traffic events using geosocial media data: a review. Comput. Environ. Urban Syst. 72, 146- 160.

[52] Yao, Y. , Liang, Z. , Yuan, Z. , Liu, P. , Bie, Y. , Zhang, J. , Wang, R. , Wang, J. , Guan, Q. , 2019. A human-machine adversarial scoring framework for urban perception assessment using street-view images. Int. J. Geogr. Inf. Sci. 33, 2363- 2384.

[53] Yue, H. , Xie, H. , Liu, L. , Chen, J. , 2022. Detecting people on the street and the streetscape physical environment from Baidu street view images and their effects on community-level street crime in a Chinese city. IJGI 11, 151.

[54] Yue, X. , Qi, K. , Na, X. , Zhang, Y. , Liu, Y. , Liu, C. , 2023. Improved YOLOv8-Seg network for instance segmentation of healthy and diseased tomato plants in the growth stage. Agriculture 13, 1643.

[55] Zhang, F. , Fan, Z. , Kang, Y. , Hu, Y. , Ratti, C. , 2021. "Perception bias": deciphering a mismatch between urban crime and perception of safety. Landsc. Urban Plann. 207, 104003.

[56] Zhang, F. , Zhou, B. , Liu, L. , Liu, Y. , Fung, H.H. , Lin, H. , Ratti, C. , 2018. Measuring human perceptions of a large-scale urban region using machine learning. Landsc. Urban Plann. 180, 148- 160.

[57] Zhang, X. , Dong, T. , Yan, L. , Yang, Z. , Zhang, J. , 2024. LAtt-Yolov8-seg: video real-time instance segmentation for urban street scenes based on focused linear attention mechanism. In: Proceedings of the International Conference on Computer Vision and Deep Learning, CVDL '24. Association for Computing Machinery, New York, NY, USA, pp. 1-5.

[58] Zhou, B. , Liu, L. , Oliva, A. , Torralba, A. , 2014. Recognizing city identity via attribute analysis of Geo-tagged images. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (Eds.), Computer Vision e ECCV 2014, Lecture Notes in Computer Science. Springer International Publishing, Cham, pp. 519-534.

[59] Zhou, S. , Liu, Z. , Wang, M. , Gan, W. , Zhao, Z. , Wu, Z. , 2022. Impacts of building configurations on urban stormwater management at a block scale using XGBoost. Sustain. Cities Soc. 87, 104235.

RIGHTS & PERMISSIONS

The Author(s). Publishing services by Elsevier B.V. on behalf of Higher Education Press and KeAi.