Publikace

informace pocházejí z univerzitní databáze V3S

Autoři:
Ing. Vít Malinovský, Ph.D.
Publikováno:
2021, Neural Network World, 31 (4), p. 239-259), ISSN 1210-0552
Anotace:
Abstract: This paper deals with problems of processing freight statistic data into the form of time series and analysing consequent results by means of two completely different methods. The first method for calculating chosen transport trends uses the transport model Trans-Tools based on conventional mathematical and statistical functions while the second one uses the Scikit Learn software providing users with development environment including algorithms of neural networks. The obtained results are similar to a certain extent which shows new possibilities of progressive use of neural networks in future and enables modern approach to analysing time series not only in transportation sector. Comparative analysis of results obtained from the same transport data processed by “standard” mathematical (Trans-Tool) method and neuron-network (Scikit Learn) method as well as a research focused on some trends development within the scope of freight transport in EU represent goals of this work.
DOI:
Typ:
Článek v periodiku excerpovaném SCI Expanded

Autoři:
Ing. Vít Malinovský, Ph.D.; Meyer-Rühle, O.; Kyster-Hansen, H.; Böhmann, A.; Heinrich, Ch.; Leonhardt, S.; Zuiver, H.
Publikováno:
2019, 2019 Konference - 25 let Fakulty dopravní, Praha, České vysoké učení technické v Praze), ISBN 978-80-01-06545-7
Anotace:
The paper deals with problems of determination and assessment of external factors (dependency on fossil fuels, GFG production, congestions, and road fatalities) for processing by a transport model by means of common mathematical and econometical methods (Trans-Tools model). Results are used as grounds for forecasting freight transport trends in time horizons 2035 and 2050.
Typ:
Stať ve sborníku z fakultní konference cizojazyčně