Publicación: Neural network model, based on time series, to forecast availability in the bike-shared systems
Cargando...
Fecha
2021-09-30
Autores
Editor/a
Tutor/a
Coordinador/a
Prologuista
Revisor/a
Ilustrador/a
Derechos de acceso
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial
Resumen
The rental of the public system of shared bicycles is a service aimed at all citizens of the city of Madrid and Barcelona, as an alternative element of clean transport that contributes to a more sustainable mobility model and the promotion of more balanced transport habits and healthy. Mobility services are increasingly based on technology and data collection, not only directly related to mobility flows, but also to other variables that affect it to a greater extent such as meteorology, pollution, strikes and temporary events. Knowing where, when and how people move is key to matching supply with demand. A better understanding of their behavior will allow us to better adapt these transport systems and optimize resources. It is necessary to predict how the system will behave to anticipate movements. Deep learning techniques have shown significant improvements in prediction over traditional models, but some difficulties and open questions remain regarding their applicability, accuracy, and ability to provide practical information. Our approach in this paper is based on comparing different models capable of predicting at least 6 hours in advance which stations are likely to be full or empty.
Descripción
Categorías UNESCO
Palabras clave
Citación
Centro
Facultades y escuelas::E.T.S. de Ingeniería Informática
Departamento
Inteligencia Artificial