Mobility mining for time-dependent urban network modeling

  1. Arregui, Harbil
Supervised by:
  1. Oihana Otaegui Madurga Director
  2. Olatz Arbelaitz Gallego Director

Defence university: Universidad del País Vasco - Euskal Herriko Unibertsitatea

Fecha de defensa: 30 April 2021

  1. Sisi Zlatanova Chair
  2. Ibai Gurrutxaga Goikoetxea Secretary
  3. Ainhoa Galarza Rodríguez Committee member
  1. Arquitectura y Tecnología de Computadores

Type: Thesis

Teseo: 154478 DIALNET lock_openADDI editor


Mobility planning, monitoring and analysis in such a complex ecosystem as a city are very challenging.Our contributions are expected to be a small step forward towards a more integrated vision of mobilitymanagement. The main hypothesis behind this thesis is that the transportation offer and the mobilitydemand are greatly coupled, and thus, both need to be thoroughly and consistently represented in a digitalmanner so as to enable good quality data-driven advanced analysis. Data-driven analytics solutions relyon measurements. However, sensors do only provide a measure of movements that have already occurred(and associated magnitudes, such as vehicles per hour). For a movement to happen there are two mainrequirements: i) the demand (the need or interest) and ii) the offer (the feasibility and resources). Inaddition, for good measurement, the sensor needs to be located at an adequate location and be able tocollect data at the right moment. All this information needs to be digitalised accordingly in order to applyadvanced data analytic methods and take advantage of good digital transportation resource representation.Our main contributions, focused on mobility data mining over urban transportation networks, can besummarised in three groups. The first group consists of a comprehensive description of a digitalmultimodal transport infrastructure representation from global and local perspectives. The second groupis oriented towards matching diverse sensor data onto the transportation network representation,including a quantitative analysis of map-matching algorithms. The final group of contributions covers theprediction of short-term demand based on various measures of urban mobility.