A carregar...
Projeto de investigação
Spatio-temporal Pattern Analysis of Big Data in Engineering Systems
Financiador
Autores
Publicações
Data analytics to advance the inference of origin–destination in public transport systems: tracing network vulnerabilities and age-sensitive trip purposes
Publication . Cerqueira, Sofia; Arsenio, Elisabete; Barateiro, José; Henriques, Rui
Knowing the passengers' final destinations, underlying motifs, and commuting habits is critical to optimise public transportation systems, guide urban planning and contribute to a more sustainable urban mobility. In entry-only Automated Fare Collection systems, the body of literature has focused on the spatial dimension by estimating alighting stops, overlooking the inference of robust alighting times. Moreover, discriminating between transfers and activities is pivotal for determining their ultimate destinations. However, current methods often struggle to adapt to the stochastic nature of passenger behaviour, further disregarding the multiplicity of routes and stops to access specific facilities and individual motivations. Further research is required to address an effective spatio-temporal and contextual inference in both challenges. With the above concerns in mind, this research uses data analytics to propose an enhanced methodology for the inference of OD matrices, with the final goal of providing a comprehensive view of OD mobility patterns across distinct age-sensitive profiles-youth, adults, and older adults. Our methodological framework integrates the following approaches: (i) alighting stop-and-time inference, (ii) ensembled model for transfer classification, (iii) indicators retrieved from statistical analysis of network vulnerabilities (e.g., number of transfers, walkability needs), frequent destinations and their underlying putative motifs against the city amenities and others points-of-interest. The reliability of alighting data (timestamp and location) inference is improved by integrating OpenStreetMap data and the past boarding data from bus and railway systems. Considering Lisbon as the target study case, we apply the methodology over smart card data collected both from metro and bus systems. A comparative analysis with state-of-the-art methods revealed that the enhanced framework for alighting and OD inference led to longer journey times for trips. Furthermore, throughout the day, the older adult group experiences longer transfer times on average compared to both the children and young adult segment and the adult segment.
Moving from classical towards machine learning stances for bus passengers’ alighting estimation: A comparison of state-of-the-art approaches in the city of Lisbon
Publication . Cerqueira, Sofia; Arsenio, Elisabete; Barateiro, José; Henriques, Rui
Passenger alighting estimation is a critical task in public transport (PT) management, especially for entry-only Automatic Fare Collection (AFC) transport systems where passenger alighting are not recorded. Effective estimation methods are necessary for trip analysis and route planning, offering valuable insights into passengers’ mobility patterns and, subsequently, improving the quality of service. However, the stochastic nature of passenger behaviour challenges the degree of successful alighting estimates. A classic approach to infer the alighting stops of passengers is the use of trip-chaining principles. Since these principles are dispersed across the literature in the field, their comprehensive review is pivotal to establish the best practice for alighting estimation. Still, trip chaining approaches are unable to infer the alighting of non-commuting passengers. This paper addresses these two research gaps by: i) providing a critical overview of the existing principles and methods for alighting estimation; ii) proposing an approach to improve alighting estimation that consistently integrates the most effective state-of-the-art principles on trip-chaining; and iii) further introducing a frequent pattern mining and densitybased clustering solutions to support alighting estimation for non-commuting passengers. Considering the public bus transport in Lisbon city as the guiding case study, the achieved estimation rate by the proposed assembled model is 92%. Moreover, the density-based clustering solution is found to improve the estimation of 11pp against classic trip-chaining principles. Furthermore, the proposed model and acquired results yield actionable value to enhance PT operations and services, ultimately leading to improved bus routing and quality of service.
Unidades organizacionais
Descrição
Palavras-chave
, Exact sciences ,Exact sciences/Computer and information sciences
Contribuidores
Financiadores
Entidade financiadora
Fundação para a Ciência e a Tecnologia, I.P.
Fundação para a Ciência e a Tecnologia, I.P.
Fundação para a Ciência e a Tecnologia, I.P.
Programa de financiamento
OE
Número da atribuição
2022.13483.BD