caa a22 4500 605468478 CHVBK 20210128100316.0 cr unu---uuuuu 210128e20150101xx s 000 0 eng 10.1007/s00500-014-1238-4 doi (NATIONALLICENCE)springer-10.1007/s00500-014-1238-4 Mesoscopic forecasting of vehicular consumption using neural networks [Elektronische Daten] [Michail Masikos, Konstantinos Demestichas, Evgenia Adamopoulou, Michael Theologou] Accurate forecasting of vehicular consumption is a task of primary importance for several applications. Herein, a vehicular consumption prediction model is proposed, with special emphasis on robustness and reliability. Both features are enabled due to the selection of general regression neural networks (GRNNs) for the implementation of the proposed model. GRNNs are widely used among neural networks because of their capabilities for fast learning and successful convergence to the solution. In particular, the designed GRNN is responsible for approximating the nonlinearities and the specificities between the factors identified as major contributors in vehicular consumption. In order to evaluate its efficiency, a case study involving the application of the introduced model in fully electric vehicles (FEVs) is examined. The performance of the proposed model is successfully validated using real measurements collected during a data acquisition field campaign. Springer-Verlag Berlin Heidelberg, 2014 Energy-efficient routing nationallicence Mesoscopic consumption model nationallicence Context-aware prediction nationallicence FEV nationallicence Masikos Michail School of Electrical and Computer Engineering, National Technical University of Athens, 15780, Zografou, Greece aut Demestichas Konstantinos School of Electrical and Computer Engineering, National Technical University of Athens, 15780, Zografou, Greece aut Adamopoulou Evgenia School of Electrical and Computer Engineering, National Technical University of Athens, 15780, Zografou, Greece aut Theologou Michael School of Electrical and Computer Engineering, National Technical University of Athens, 15780, Zografou, Greece aut Soft Computing Springer Berlin Heidelberg 19/1(2015-01-01), 145-156 1432-7643 19:1<145 2015 19 500 https://doi.org/10.1007/s00500-014-1238-4 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00500-014-1238-4 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Masikos Michail School of Electrical and Computer Engineering, National Technical University of Athens, 15780, Zografou, Greece aut NATIONALLICENCE 700 1- Demestichas Konstantinos School of Electrical and Computer Engineering, National Technical University of Athens, 15780, Zografou, Greece aut NATIONALLICENCE 700 1- Adamopoulou Evgenia School of Electrical and Computer Engineering, National Technical University of Athens, 15780, Zografou, Greece aut NATIONALLICENCE 700 1- Theologou Michael School of Electrical and Computer Engineering, National Technical University of Athens, 15780, Zografou, Greece aut NATIONALLICENCE 773 0- Soft Computing Springer Berlin Heidelberg 19/1(2015-01-01), 145-156 1432-7643 19:1<145 2015 19 500