Mitigating sensor bias: a location-aware calibration framework for pedestrian analytics

Abstract

The promise of data-driven urbanism is critically undermined by the unreliability of passive sensors. Raw WiFi data systematically undercounts pedestrian volumes by approximately 50% across the eight study sites, rendering it fundamentally unsuitable for strategic decision-making. We present and validate a location-aware calibration framework that treats the scaling factor as an empirically estimated, site-specific coefficient capturing a socio-technical signature of place, shaped by urban morphology, human behaviour, and signal conditions. Derived and validated across eight diverse urban sites in Loughborough Town Centre, UK against multi-day ground-truth observations, our approach elevates data reliability from its unusable baseline to a robust 85.8% accuracy. The application of this calibrated data generates high-resolution pedestrian flow maps. These maps, in turn, provide a closer approximation of the city’s circulatory system by correcting distorted spatial narratives and revealing a functional hierarchy not evident in the raw data. Systematic anomalies in urban sensor records, including undercounting in social spaces and overcounting in congested areas, represent data signatures that reveal user–place interactions and inform evaluation of placemaking quality and infrastructure pressure. This research offers a scalable blueprint for converting low-cost sensor data into reliable intelligence, empowering evidence-based urban planning, design, and mobility management.

Keywords

WiFi sensing / Sensor calibration / High-resolution pedestrian flow / Human dynamics / Urban analytics / Smart cities

References

[1] Angel, A., & Plaut, P. (2023). Pedestrian Movement and the Built Environment – A Big Data-Based Analysis. In Lecture Notes in Intelligent Transportation and Infrastructure: Vol. Part F1378 (p. 728). Springer Nature. https://doi.org/10.1007/978-3-031-23721-8_61

[2] Angel, A., Cohen, A., Nelson, T., & Plaut, P. (2024). Evaluating the relationship between walking and street characteristics based on big data and machine learning analysis. Cities, 151. https://doi.org/10.1016/j.cities.2024.105111

[3] Biljecki F. GeoAI for urban sensing. Handbook of geospatial artificial intelligence, 2023CRC Press351366.

[4] Botchkarev A. A new typology design of performance metrics to measure errors in machine learning regression algorithms. Interdisciplinary Journal of Information, Knowledge, and Management, 2019, 14: 45-76.

[5] Butler, J. J., Carol Johnson, B., & Barnes, R. A. (2005). 10. The Calibration and Characterization of Earth Remote Sensing and Environmental Monitoring Instruments. Experimental Methods in the Physical Sciences, 41(C), 453–534. https://doi.org/10.1016/S1079-4042(05)41010-3

[6] Cabrera, C., & Rowe, F. (2025). A systematic machine learning approach to measure and assess biases in mobile phone population data. ArXiv. http://arxiv.org/abs/2509.02603

[7] Charnwood Borough Council. (2018). Loughborough Town Centre Masterplan. www.uistudio.co.uk

[8] Chen, Y., & Yang, J. (2020). Historic Neighborhood Design Based on Facility Heatmap and Pedestrian Simulation: Case Study in China. Journal of Urban Planning and Development, 146(2). https://doi.org/10.1061/(asce)up.1943-5444.0000554

[9] Chin T, Johansson MA, Chowdhury A, Chowdhury S, Hosan K, Quader MT, Buckee CO, Mahmud AS. Bias in mobility datasets drives divergence in modeled outbreak dynamics. Communications Medicine, 2025, 518.

[10] Cieśla, M. (2021). Modern urban transport infrastructure solutions to improve the safety of children as pedestrians and cyclists. Infrastructures, 6(7). https://doi.org/10.3390/infrastructures6070102

[11] Du, F., Wang, J., Mao, L., & Kang, J. (2024). Daily rhythm of urban space usage: insights from the nexus of urban functions and human mobility. Humanities and Social Sciences Communications, 11(1). https://doi.org/10.1057/s41599-023-02577-y

[12] Dube, S., Kumar, N., Bhatia, O. P., & Narulkar, S. (2023). Study on the Elements Affecting the Pedestrian Movements Around the Bus Stations of Indore BRT. Transportation in Developing Economies, 9(1). https://doi.org/10.1007/s40890-023-00180-z

[13] Eom, S., Kim, H., Hasegawa, D., & Yamada, I. (2024). Pedestrian movement with large-scale GPS records and transit-oriented development attributes. Sustainable Cities and Society, 102. https://doi.org/10.1016/j.scs.2024.105223

[14] Fernández-Avilés Calderón G. Spatial regression analysis vs. kriging methods for spatial estimation. International Advances in Economic Research, 2009, 1514458.

[15] Filomena, G., & Verstegen, J. A. (2021). Modelling the effect of landmarks on pedestrian dynamics in urban environments. Computers, Environment and Urban Systems, 86. https://doi.org/10.1016/j.compenvurbsys.2020.101573

[16] Hayes, S., Charlton, J., Fletcher, D., & Richmond, P. (2022). Validation of Agent-Based Passenger Movement Modeling for Railway Stations Subject to Social Distancing During the COVID-19 Pandemic. Transportation Research Record: Journal of the Transportation Research Board, 036119812210936. https://doi.org/10.1177/03611981221093634

[17] Hennig C, Viroli C. Quantile-based classifiers. Biometrika, 2016, 1032435446.

[18] Huang B, Mao G, Qin Y, Wei Y. Pedestrian flow estimation through passive WiFi sensing. IEEE Transactions on Mobile Computing, 2021, 20415291542.

[19] Ibrahim OT, Gomaa W, Youssef M. CrossCount: A deep learning system for device-free human counting using WiFi. IEEE Sensors Journal, 2019, 192199219928.

[20] Istrate, A. L. (2023). Street Vitality: What Predicts Pedestrian Flows and Stationary Activities on Predominantly Residential Chinese Streets, at the Mesoscale? Journal of Planning Education and Research. https://doi.org/10.1177/0739456X231184607

[21] Kamboj K, Sisodiya S, Mathur AK, Zare A, Verma P. Assessment and spatial distribution mapping of criteria pollutants. Water, Air, & Soil Pollution, 2022, 233382.

[22] Kearney KM, Harley JB, Nichols JA. Inverse distance weighting to rapidly generate large simulation datasets. Journal of Biomechanics, 2023, 158: 111764.

[23] Kirk B, Ha M, Lee S. The relationship between children’s fear of crime and pedestrian volume in school zones. Journal of Asian Architecture and Building Engineering, 2023, 22636653679.

[24] Kurkcu A, Ozbay K. Estimating pedestrian densities, wait times, and flows with Wi-Fi and Bluetooth sensors. Transportation Research Record: Journal of the Transportation Research Board, 2017, 264417282.

[25] Lakshmi, A. V., & Joseph, K. S. (2022). Point of Interest Data (POI) based Safe Route Navigation System. 2022 IEEE Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2022. https://doi.org/10.1109/IATMSI56455.2022.10119273

[26] Li Z, Zhang X, Zhu R, Zhang Z, Weng Z. Integrating data-to-data correlation into inverse distance weighting. Computational Geosciences, 2020, 241203216.

[27] Lu F, Cheng S, Wang P. GeoAI enabled urban computing: Status and challenges. Annals of GIS, 2025, 314537555.

[28] Ma X, Huang Z, Koutsopoulos H. Integrated traffic and emission simulation: A model calibration approach using aggregate information. Environmental Modeling and Assessment, 2014, 194271282.

[29] Meng F, Wong SC, Wong W, Li YC. Estimation of scaling factors for traffic counts based on stationary and mobile sources of data. International Journal of Intelligent Transportation Systems Research, 2017, 153180191.

[30] Pereira MF, Santana P, Vale DS. The impact of urban design on utilitarian and leisure walking—The relative influence of street network connectivity and streetscape features. Urban Science, 2024, 8224.

[31] Prashanthi Devi M, Selvaraj J, Dayalan H. Geospatial modelling of air pollution and its impact on health of urban residents using spatial models: A review. Strategies and tools for pollutant mitigation, 2021Springer International Publishing377389.

[32] Saltarin-Molino, M. A., Moros-Daza, A., & Camacho-Sanchez, C. (2023). Taking steps forward: Innovative evaluation of pedestrian infrastructure through a multivariate analysis. Case Studies on Transport Policy, 14. https://doi.org/10.1016/j.cstp.2023.101091

[33] Sepehr P. Mundane urban governance and AI oversight: The case of Vienna’s intelligent pedestrian traffic lights. Journal of Urban Technology, 2024, 00118.

[34] Sevtsuk A, Kalvo R. Modeling pedestrian activity in cities with urban network analysis. Environment and Planning b: Urban Analytics and City Science, 2025, 522377395.

[35] Sevtsuk, A., Kollar, J., Pratama, D., Basu, R., Haddad, J., Alhassan, A., Chancey, B., Halabi, M., Makhlouf, R., & Abou-Zeid, M. (2024). Pedestrian-oriented development in Beirut: A framework for estimating urban design impacts on pedestrian flows through modeling, participatory design, and scenario analysis. Cities, 149. https://doi.org/10.1016/j.cities.2024.104927

[36] Shamroukh, M., Natapov, A., & Larimian, T. (2025). Spatio-Temporal analysis of pedestrian activity in Loughborough using WiFi data. In Adam Dennett (Ed.), The 19th International Conference on Computational Urban Planning and Urban Management. CUPUM 2025. https://osf.io/w52nm

[37] Shamroukh M, Natapov A, Larimian T. Reliability and scalability of pedestrian monitoring practices: A systematic review. IEEE Access, 2025, 13: 147679-147689.

[38] Shaw S-L, Ye X, Goodchild M, Sui D. Human dynamics research in GIScience: Challenges and opportunities. Computational Urban Science, 2024, 4131.

[39] Shukla K, Kumar P, Mann GS, Khare M. Mapping spatial distribution of particulate matter using Kriging and inverse distance weighting at supersites of megacity Delhi. Sustainable Cities and Society, 2020, 54: 101997.

[40] Smith SF. Smart infrastructure for future urban mobility. AI Magazine, 2020, 411518.

[41] Soundararaj B, Cheshire J, Longley P. Estimating real-time high-street footfall from Wi-Fi probe requests. International Journal of Geographical Information Science, 2020, 342325343.

[42] Taherdoost, H. (2021). Data Collection Methods and Tools for Research; A Step-by-Step Guide to Choose Data Collection Technique for Academic and Business Research Projects. International Journal of Academic Research in Management (IJARM), 2021(1), 10–38. https://hal.science/hal-03741847

[43] Tanida S, Feliciani C, Jia X, Kim H, Aikoh T, Nishinari K. Investigating the congestion levels on a mesoscopic scale during outdoor events. Journal of Disaster Research, 2024, 192347358.

[44] Trasberg T, Soundararaj B, Cheshire J. Using Wi-Fi probe requests from mobile phones to quantify the impact of pedestrian flows on retail turnover. Computers, Environment and Urban Systems, 2021, 87: 101601.

[45] Traunmueller MW, Johnson N, Malik A, Kontokosta CE. Digital footprints: Using WiFi probe and locational data to analyze human mobility trajectories in cities. Computers, Environment and Urban Systems, 2018, 72: 4-12.

[46] Uras M, Ferrara E, Cossu R, Liotta A, Atzori L. MAC address de-randomization for WiFi device counting: Combining temporal- and content-based fingerprints. Computer Networks, 2022, 218: 109393.

[47] Van Zoest V, Osei FB, Hoek G, Stein A. Spatio-temporal regression kriging for modelling urban NO2 concentrations. International Journal of Geographical Information Science, 2020, 345851865.

[48] Wang, J., Sang, H., Liu, Q., Chen, W., & Zhao, Z. (2024). Neural differential constraint-based pedestrian trajectory prediction model in ego-centric perspective. Engineering Applications of Artificial Intelligence, 133. https://doi.org/10.1016/j.engappai.2024.107993

[49] Weng Q, Hou Q, Chen Z, Benediktsson JA, Gamba P, Tuia D, Zhang F, Xu Y, Wu M, Li N, Batty M. Urban visual-spatial intelligence: Linking human and sensor perception for sustainable urban development. Npj Urban Sustainability, 2025, 5165.

[50] Wong PKY, Cheng JCP. Monitoring pedestrian flow on campus with multiple cameras using computer vision and deep learning techniques. Lecture notes in civil engineering, 2020Springer11491154. Vol. 54

[51] Yang L, Ai M, Kwan MP, Zuo Z, Zhang Y, Zhou S, Luo S, Chen Y. Generation of intra-community roads based on human-flow modeling (HFM). International Journal of Geographical Information Science, 2024, 38712561290.

[52] Yilmaz, A., & Kurkcuoglu, E. (2024). Multidimensional dynamics of pedestrian-environment interaction: a micromovement analysis in Istiklal Street, Istanbul*. Journal of Urban Design. https://doi.org/10.1080/13574809.2024.2317813

[53] Yoshimura, Y., Kumakoshi, Y., Fan, Y., Milardo, S., Koizumi, H., Santi, P., Murillo Arias, J., Zheng, S., & Ratti, C. (2022). Street pedestrianization in urban districts: Economic impacts in Spanish cities. Cities, 120. https://doi.org/10.1016/j.cities.2021.103468

[54] Yussif, A. M., Zayed, T., Taiwo, R., & Fares, A. (2024). Promoting sustainable urban mobility via automated sidewalk defect detection. Sustainable Development, 2023, 1–21. https://doi.org/10.1002/sd.2999

[55] Zhang, J., Zhou, W., Lian, H., & Hu, R. (2024). Research on Optimization Strategy of Commercial Street Spatial Vitality Based on Pedestrian Trajectories. Buildings, 14(5). https://doi.org/10.3390/buildings14051240

[56] Zhang, L., Xu, J., Pan, X., Ye, J., Wang, W., Liu, Y., & Wei, Q. (2023). Visual analytics of route recommendation for tourist evacuation based on graph neural network. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-42862-z

Funding

UK Government’s Towns Fund

Rights & permissions

The Author(s)