Mobility in Lisbon based on smartphone data

• Autor(a) principal: Leal, Daniel Romão
• Data de Publicação: 2022
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10071/26979
• topic: Smartphone data; Mobility patterns; Visualisation; Vibrant neighbourhoods; Point of interest; DBSCAN; Operadora móvel; Padrões de mobilidade; Visualização; Pontos de interesse

This research covers five months (September, October, November, December 2021, and January 2022) of georeferenced data of the Vodafone mobile phone service, provided by the municipality of Lisbon (CML). The motivation of this research regards the fact that the urban mobility study with mobile phone data is a relatively unexplored topic. This study focused on the city of Lisbon, with a case study conducted in the parish of Santa Maria Maior with the aim to understand the urban mobility patterns of mobile phone users. The number of roaming and non-roaming devices in the case study is related to the subject of a vibrant neighborhood and tourism, characterized by transportation and historical points of interest. We used a data mining approach to analyze mobility trends, adopting a CRISP-DM methodology, to perform statistical analysis, visualization, and clustering (DBSCAN) methods. Results showed eight clusters in Santa Maria Maior, with outstanding clusters along 28-E electric tram and Lisbon Cruise Terminal. Foremost, we looked at these two clusters and performed a forecast model with Prophet, resulting in downward trend, influenced by the pandemic restrictions in December and January data. This thesis contributes considerably to the digital transformation of Lisbon into a smart city by understanding urban mobility patterns with smartphone data of no roaming and roaming users.