RT journal article
T1 Human Mobility Prediction with Region-based Flows and Road Traffic Data
A1 Terroso-Saenz, Fernando
A1 Muñoz Ortega, Andrés
A2 Ingeniería Informática
K1 Human mobility
K1 Machine Learning
K1 open data
K1 road traffic
K1 inductive loop sensor
AB Predicting human mobility is a key element in the development of intelligent transportsystems. Current digital technologies enable capturing a wealth of data on mobility flows betweengeographic areas, which are then used to train machine learning models to predict these flows.However, most works have only considered a single data source for building these models ordifferent sources but covering the same spatial area. In this paper we propose to augment a macroopen-data mobility study based on cellular phones with data from a road traffic sensor locatedwithin a specific motorway of one of the mobility areas in the study. The results show that modelstrained with the fusion of both types of data, especially long short-term memory (LSTM) andGated Recurrent Unit (GRU) neural networks, provide a more reliable prediction than modelsbased only on the open data source. These results show that it is possible to predict the trafficentering a particular city in the next 30 minutes with an absolute error less than 10%. Thus, thiswork is a further step towards improving the prediction of human mobility in interurban areas byfusing open data with data from IoT systems.
PB IICM
SN 0948-6968
YR 2023
FD 2023
LK http://hdl.handle.net/10498/32566
UL http://hdl.handle.net/10498/32566
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 11-nov-2026