Bus line classification using neural networks
Jiménez Alonso, Felipe
Serradilla García, Francisco
Román de Andrés, Alfonso
Naranjo Hernandez, Jose Eugenio
- Publisher: E.T.S.I. Industriales (UPM)
(issn: Transportation Research Part D: Transport and Environment, ISSN 1361-9209, 2014-07, Vol. 30, No. null)
Grouping urban bus routes is necessary when there are evidences of significant differences among them. In Jiménez et al. (2013), a reduced sample of routes was grouped into clusters utilizing kinematic measured data. As a further step, in this paper, the remaining urban bus routes of a city, for which no kinematic measurements are available, are classified. For such purpose we use macroscopic geographical and functional variables to describe each route, while the clustering process is performed by means of a neural network. Limitations caused by reduced training samples are solved using the bootstrap method.