Consumption Behavior Recognition and Evaluation for TOD Metro Stations: A Machine Learning-Based Method

Abstract

In the context of transit-oriented development (TOD), the comprehensive commercial development around metro stations has become a new trend. However, increased commercial attractions can alter passenger behavior, intensifying space congestion and flow conflicts within metro stations. Consequently, commercial service areas can become critical risk zones. This study explored a recognition and evaluation method for consumption behavior based on passenger trajectory data from TOD metro stations. First, the characteristics of both transfer and consumption behaviors are detailed, distinguishing between strong- and weak-purpose consumption. A dynamic model of the “transfer–consumption–transfer” behavior process is also developed. Second, a machine learning-based method for recognizing and evaluating consumption behavior, grounded in passenger trajectory analysis, is proposed. This method employs machine learning method to detect and track passenger movements. Simultaneously, a coordinate transformation model is constructed to correct data deviations from the pixel-to-world coordinate system. Several analytical indicators, including deviation angles, distances, and conflict points, are introduced to mathematically describe the consumption behavior characteristics at TOD metro stations. Finally, the proposed machine learning-based method is applied to a comprehensive metro station in Shanghai, China. The experimental results validate the effectiveness of the proposed method.

Keywords

Behavior recognition and evaluation / TOD metro station / Machine learning-based methods / Passenger detection and tracking / Passenger trajectory data

References

[1] Knowles RD, Ferbrache F, Nikitas A. Transport’s historical, contemporary and future role in shaping urban development: re-evaluating transit oriented development. Cities, 2020, 99 102607

[2] Dai P, Fu H, Yang X, Han S, Fu G, Wang Y. Exploring the urban renewal strategy based on transit-oriented development concept–a case study of Japan and Hong Kong. Front Mater, 2023, 10: 1098027

[3] Niu SF, Hu A, Shen ZW, Lau SSY, Gan XY. Study on land use characteristics of rail transit TOD sites in new towns-taking Singapore as an example. J Asian Archit Build Eng, 2019, 18(1): 19-30

[4] Lin JJ, Yang SH. Proximity to metro stations and commercial gentrification. Transp Policy, 2019, 77: 79-89

[5] Xu YJ, Chen XS. Uncovering the relationship among spatial vitality, perception, and environment of urban underground space in the metro zone. Undergr Space, 2023, 12: 167-182

[6] Ibraeva A, Correia GHD, Silva C, Antunes AP. Transit-oriented development: a review of research achievements and challenges. Transp Res Part a-Policy Pract, 2020, 132: 110-130

[7] Huang XY, Liang QH, Feng ZH, Chai SS. A TOD planning model integrating transport and land use in urban rail transit station areas. IEEE Access, 2021, 9: 1103-1115

[8] Nigro A, Bertolini L, Moccia FD. Land use and public transport integration in small cities and towns: assessment methodology and application. J Transp Geogr, 2019, 74: 110-124

[9] Sun SN, Her J, Lee SY, Lee JS. Meso-scale urban form elements for bus transit-oriented development: evidence from Seoul, Republic of Korea. Sustainability, 2017, 9 1516

[10] Cao ZJ. Integrating station-area development with rail transit networks: lessons from Japan railway in Tokyo. Urban Rail Transit, 2022, 8(3–4167-174

[11] Bian Y, Li L, Han TS, Jia DZ (2021) TOD typology: a review of research achievements. J Southeast Univ (English Edition) 37(3):306–316

[12] Shi Y, Xu J, Zhang H, Jia L, Qin Y. Walking model on passenger in merging passage of subway station considering overtaking behavior. Phys: Statist Mech Appl, 2022, 585126436

[13] Li CY, Yang RY, Chen L, Tang TQ. A Boarding model for heterogeneous passengers on the platform of high-speed railway station. Simul Modelling Pract Theory, 2021, 106 102188

[14] Huang J, Zou X, Qu X, Ma J, Xu R (2016, October) A structure analysis method for complex social pedestrian groups with symbol expression and relationship matrix. In Proceedings of the 8th International Conference on Pedestrian and Evacuation Dynamics (PED 2016), Shanghai, China

[15] Ma J, Xu R, Li X, Liu L. Simulation modeling of pedestrian exit selection in evacuation process of rail transit station. J Tongji Univ Nat Sci, 2016, 44(9): 1407-1414

[16] Schadschneider A (2008) Modelling of transport and traffic problems. International Conference on Cellular Automata. Berlin, Germany

[17] Zhang Y, Huang X. Social contagion effects in pedestrian behavior in shopping malls. J Soc Psychol, 2021, 161(4): 337-352

[18] Choi S, Jeon G, Kim M. Social influence in pedestrian behavior: an empirical study of shopping mall dynamics. J Consum Res, 2021, 48(3): 527-542

[19] Pizzolato N, Mazzoleni M, Gori S. Pedestrian flow optimization in shopping malls through machine learning models. J Build Perform, 2023, 14(2): 47-60

[20] Yao Q, Liu L, Zhang J. Personalized shopping experiences: the role of smart technologies in shaping pedestrian behavior in malls. Comput Hum Behav, 2022, 127106964

[21] Liu Q, Zhang L, Wang J. Big data analysis of pedestrian movement in retail spaces: implications for mall design and marketing. Int J Retail Distrib Manage, 2023, 51(1): 55-74

[22] Cheng H, Peng F, Huang D, Liu S, Ni Y, Yang L. Experimental study on dynamics characteristic parameter of turning behavior in self-driven mechanism. Phys A Stat Mech its Appl, 2020, 549 124497

[23] Huang SZ, Liu XW, Chen W, Song GQ, Zhang ZX, Yang LY, Zhang BJ. A detection method of individual fare evasion behaviours on metros based on skeleton sequence and time series. Inf Sci, 2022, 589: 62-79

[24] Zhao RY, Wang Y, Jia P, Zhu WJ, Li CL, Ma YL, Li MY. Abnormal behavior detection based on dynamic pedestrian centroid model: case study on U-turn and fall-down. IEEE Trans Intell Transp Syst, 2023, 24(8): 8066-8078

[25] Sun X, Wang FS, Hong L. Enhancing transit-oriented development: an integrated evaluation method for tod subway stations [M]. CICTP, 2024, 2024: 3658-3668

[26] Lu SY, Wang BZ, Wang HJ, Chen LH, Ma LJ, Zhang XY. A real-time object detection algorithm for video. Comput Electr Eng, 2019, 77: 398-408

[27] Vijayakumar A, Vairavasundaram S. YOLO-based object detection models: a review and its applications. Multimed Tools Appl, 2024, 83: 83535-83574

[28] Wang Y, Wang X, Zheng J, Zan Y, Wang X (2023) A method for vehicle micro-trajectory automatic acquisition based on multi-sensor fusion and sensing. J Highw Transp Res Dev 40(4):160–169

[29] Sun L, Yang Z, Rong J, Liu X. Study on the weaving behavior of high density bidirectional pedestrian flow. Math Probl Eng, 2014, 2014(1 765659

[30] Xu H, Tian C, Wang Y. Emergency evacuation simulation for dense passenger flow in a rail transit transfer station. J Syst Simul, 2020, 32(3): 492-500

Funding

Shanghai Science and Technology Program(21JC1400602)

China Postdoctoral Science Foundation(2023M732645)

Shanghai Post-Doctoral Excellence Program(2022570)

RIGHTS & PERMISSIONS

The Author(s)