Multi-Day Activity Pattern Inference Using Constrained Gaussian Mixture Model (GMM) Classification
Urban Science · 17.06.2026 · 10 (6) · 331
DOI: 10.3390/urbansci10060331 ↗Kurz gefasst
Fachartikel in der Zeitschrift Urban Science, online erschienen am 17.06.2026. Verfasst von Nikhita Kannam und 2 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: US Department of Transportation.
Abstract (Originalsprache)
Multi-day travel diaries are often associated with high rates of partial completion, limiting their value for activity-based demand modeling. This paper develops a probabilistic framework that encodes daily activity sequences, clusters them with a Gaussian Mixture Model (GMM) to obtain soft (probabilistic) memberships, and predicts missing days through a constrained Lagrangian regression that guarantees valid probability distributions. Applied to the New York City Citywide Mobility Survey for 2019 and 2022, the soft-clustering approach achieves an RMSE as low as 0.17—substantially outperforming hard-clustering baselines (16–36% accuracy)—and reconstructs population-level time-use profiles with approximately 5–6% mean absolute error. Results show that post-pandemic activity patterns are more home-anchored and less varied, with pronounced socioeconomic divergence in recovery trajectories.
Förderung
- US Department of Transportation
Zitieren
APA
Kannam, N., Allahviranloo, M., & Vatin, L. A. R. (2026). Multi-Day Activity Pattern Inference Using Constrained Gaussian Mixture Model (GMM) Classification. Urban Science, 10(6), 331. https://doi.org/10.3390/urbansci10060331
Vancouver
Kannam N, Allahviranloo M, Vatin LAR. Multi-Day Activity Pattern Inference Using Constrained Gaussian Mixture Model (GMM) Classification. Urban Science. 2026;10(6):331. doi:10.3390/urbansci10060331
BibTeX
@article{Kannam2026,
author = {Kannam, Nikhita and Allahviranloo, Mahdieh and Vatin, Laure Alice Raymonde},
title = {Multi-Day Activity Pattern Inference Using Constrained Gaussian Mixture Model (GMM) Classification},
journal = {Urban Science},
year = {2026},
volume = {10},
number = {6},
pages = {331},
doi = {10.3390/urbansci10060331}
}
EUVIMED