Search Results

Now showing 1 - 2 of 2

Some of the metrics are blocked by your
consent settings
Adoption-Driven Data Science for Transportation Planning: Methodology, Case Study, and Lessons Learned
(2020)
Eduardo Graells-Garrido
;
Vanessa Peña-Araya
;
BRAVO CELEDÓN, MARÍA LORETO
The rising availability of digital traces provides a fertile ground for data-driven solutions to problems in cities. However, even though a massive data set analyzed with data science methods may provide a powerful and cost-effective solution to a problem, its adoption by relevant stakeholders is not guaranteed due to adoption barriers such as lack of interpretability and interoperability. In this context, this paper proposes a methodology toward bridging two disciplines, data science and transportation, to identify, understand, and solve transportation planning problems with data-driven solutions that are suitable for adoption by urban planners and policy makers. The methodology is defined by four steps where people from both disciplines go from algorithm and model definition to the development of a potentially adoptable solution with evaluated outputs. We describe how this methodology was applied to define a model to infer commuting trips with mode of transportation from mobile phone data, and we report the lessons learned during the process.
Scopus© Citations 6 3
Some of the metrics are blocked by your
consent settings
Modalflow: Cross-Origin Flow Data Visualization for Urban Mobility
(2020)
Ignacio Pérez-Messina
;
Eduardo Graells-Garrido
;
María Jesús Lobo
;
Christophe Hurter
Pervasive data have become a key source of information for mobility and transportation analyses. However, as a secondary source, it has a different methodological origin than travel survey data, usually relying on unsupervised algorithms, and so it requires to be assessed as a dataset. This assessment is challenging, because, in general, there is not a benchmark dataset or a ground truth scenario available, as travel surveys only represent a partial view of the phenomenon and suffer from their own biases. For this critical task, which involves urban planners and data scientists, we study the design space of the visualization of cross-origin, multivariate flow datasets. For this purpose, we introduce the Modalflow system, which incorporates and adapts different visualization techniques in a notebook-like setting, presenting novel visual encodings and interactions for flows with modal partition into scatterplots, flow maps, origin-destination matrices, and ternary plots. Using this system, we extract general insights on visual analysis of pervasive and survey data for urban mobility and assess a mobile phone network dataset for one metropolitan area.
5Scopus© Citations 5

CRIS

Browse

Filters

Settings

Sort By

Results per page

Search Results