Keywords
Spatial suitability
Wi-Fi sensing
Machine learning
Random forest
Decision tree
Explainable AI
Published : 2026-08-14
Abstract
Campus planners still rely on surveys and static indicators that miss high-frequency behavioral change. The study developed a Space–Behavior–Decision framework for Wenzhou-Kean University using 243,062 anonymized half-hourly Wi-Fi records (July 2023–March 2025), road-integration for 30 buildings, and functional labels for 35 access points. Seven regression models were compared. Random forest achieved the highest accuracy (R² = 0.9998, RMSE = 0.0025, MAPE = 0.38 %). The decision tree remained nearly as accurate (R² = 0.9986, MAPE = 0.47 %) while offering transparency and easy GIS integration, making it preferable for routine planning. Feature importance gave weights of 0.48 (density), 0.32 (integration), and 0.20 (function). The high fit mainly shows the composite index is learnable. Quarterly updating and post-occupancy checks are required before operational use.
References
Zhao Z, Wang T, Zhang Y, et al., 2023, Geo-Visualization of Spatial Occupancy on Smart Campus Using Wi-Fi Connection Log Data. ISPRS International Journal of Geo-Information, 12(11): 455.
Mosteiro-Romero, M, Miller C, Quintana M, et al., 2023, Leveraging Campus-scale Wi-Fi Data for Activity-based Occupant Modeling in Urban Energy Applications. Journal of Physics: Conference Series, 2600(13): 132008.
Alishahi N, Ouf MM, Nik-Bakht M, 2022, Using WiFi Connection Counts and Camera-based Occupancy Counts to Estimate and Predict Building Occupancy. Energy and Buildings, 2022(257): 111759.
Li T, Liu X, Li G, et al., 2024, A Systematic Review and Comprehensive Analysis of Building Occupancy Prediction. Renewable and Sustainable Energy Reviews, 2024(193): 114284.
Monti L, Tse R, Tang SK, et al., 2022, Edge-Based Transfer Learning for Classroom Occupancy Detection in a Smart Campus Context. Sensors, 22(10): 3692.
Khan I, Zedadra O, Guerrieri A, et al., 2024, Occupancy Prediction in IoT-Enabled Smart Buildings: Technologies, Methods, and Future Directions. Sensors, 24(11): 3276.
Hernando-Cánovas L, Martínez-Sala AS, Sánchez-Aarnoutse JC, & et al., 2025, A Machine Learning Approach for Estimating Person Counts Using Anonymous WiFi Data in a University Library. Sensors, 25(22): 7065.
Shen Y, Pan Y, 2023, BIM-supported Automatic Energy Performance Analysis for Green Building Design Using Explainable Machine Learning and Multi-objective Optimization. Applied Energy, 2023(333): 120575.
Li Y, Zhang H, Shen X, et al., 2025, Interpretable Machine Learning for Predicting and Optimizing Residential Building Performance in Cold Regions. Energy and Buildings, 2025(347): 116321.
Askarizad R, Lamíquiz Daudén PJ, Garau C, 2024, The Application of Space Syntax to Enhance Sociability in Public Urban Spaces: A Systematic Review. ISPRS International Journal of Geo-Information, 13(7): 227.
Banihashemi F, Weber M, Deghim F, et al., 2024, Occupancy Modeling on Non-Intrusive Indoor Environmental Data Through Machine Learning. Building and Environment, 2024(254): 111382.
Guo Y, Sui J, 2025, Post-Occupancy Evaluation of Campus Learning Spaces with Multi-Modal Spatiotemporal Tracking. Buildings, 15(11): 1831.