A carregar...
Publicação
Urban Mobility Pattern Using Mobile Phone Geolocation Data: A Smart Mobility Case Study of Oeiras
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 2.21 MB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
This study investigates urban mobility patterns in Oeiras, Portugal, by applying data science
techniques to anonymized mobile phone geolocation data from 2024 to enhance the
municipality's Sustainable Urban Mobility Plan (SUMP). Framed within a Smart Mobility and
CRISP-DM methodology, this research analyzes user activity and origin-destination datasets
aggregated by census statistical sections. The methodology involved preprocessing the data,
followed by Principal Component Analysis (PCA) for dimensionality reduction and K-means
clustering to segment the municipality based on mobility behaviors. The PCA successfully
reduced the data's complexity into three components that explain 82.4% of the variance,
representing the intensity of local activity, connectivity with Lisbon, and connections to the
broader Lisbon Metropolitan Area. The subsequent K-means analysis identified four distinct
clusters: areas of high local activity with limited external connections (Cluster 1); low-activity
baseline areas (Cluster 2); zones with high local activity and strong connections to Lisbon
(Cluster 3); and transit areas with significant connectivity to the wider metropolitan region but
low internal activity (Cluster 4). A comparison with the 2019 Oeiras mobility survey confirms
these patterns while adding significant spatial granularity. The findings provide actionable,
evidence-based insights for optimizing public transport, promoting active mobility, and
informing land-use planning, demonstrating the value of integrating big data analytics with
traditional methods for sustainable urban development.
Descrição
Dissertation presented as the partial requirement for obtaining a Master's degree in Statistics and Information Management, specialization in Information Analysis and Management
Palavras-chave
Urban Mobility Smart Cities Smart Mobility Mobile Phone Data Cluster Analysis SDG 11 - Sustainable cities and communities