Hlavní stránka > Výsledky hledání: keywords:"evolutionary algorithm."
Hledej:
Tipy pro vyhledávaní :: Rozšířené hledání
Hledej ve sbírkách:
Seřadit podle: Zobrazit výsledky: Výstupní formát:
Národní úložiště šedé literatury Nalezeno 2 záznamů.  Hledání trvalo 0.00 vteřin. 
Calibration of the high-speed traffic microsimulation
 Korček, Pavol ; Apeltauer, Tomáš (oponent) ; Pospíchal, Jiří (oponent) ; Sekanina, Lukáš (vedoucí práce)
This dissertation thesis is focused on the high-speed simulation of road traffic and its precise calibration with different types of traffic data. The thesis surveys the state of the art in traffic simulation, with a special focus on traffic simulators and the data they utilize. A new traffic microsimulation model inspired by existing cellular automaton-based model is proposed and its features and parameters are discussed. The proposed acceleration techniques allowed the utilization our microsimulation model beyond the real-time simulation even for large scale systems. The complex process of quality assurance is tightly associated with the model calibration. A brand new calibration methodology that is based on the evolutionary algorithms is proposed. It was found that the proposed method does not require a sensitivity analysis. The method is also capable of determining the parameters that are hard to estimate with other well know techniques. The quality of the resulting optimized models was experimentally analyzed and discussed at both the macroscopic and microscopic traffic levels. The method is robust enough to deal with missing samples and other imperfections of the real data. Properties of the proposed model such as the scalability and accuracy were evaluated with respect to the existing solutions, showing a considerable improvement of the state of the art. The software tools that were created within the research are briefly presented. Finally, the thesis also outlines further steps of research and development, especially the use of the proposed tools in practice.
Úplný záznam
Calibration of the high-speed traffic microsimulation
 Korček, Pavol ; Apeltauer, Tomáš (oponent) ; Pospíchal, Jiří (oponent) ; Sekanina, Lukáš (vedoucí práce)
This dissertation thesis is focused on the high-speed simulation of road traffic and its precise calibration with different types of traffic data. The thesis surveys the state of the art in traffic simulation, with a special focus on traffic simulators and the data they utilize. A new traffic microsimulation model inspired by existing cellular automaton-based model is proposed and its features and parameters are discussed. The proposed acceleration techniques allowed the utilization our microsimulation model beyond the real-time simulation even for large scale systems. The complex process of quality assurance is tightly associated with the model calibration. A brand new calibration methodology that is based on the evolutionary algorithms is proposed. It was found that the proposed method does not require a sensitivity analysis. The method is also capable of determining the parameters that are hard to estimate with other well know techniques. The quality of the resulting optimized models was experimentally analyzed and discussed at both the macroscopic and microscopic traffic levels. The method is robust enough to deal with missing samples and other imperfections of the real data. Properties of the proposed model such as the scalability and accuracy were evaluated with respect to the existing solutions, showing a considerable improvement of the state of the art. The software tools that were created within the research are briefly presented. Finally, the thesis also outlines further steps of research and development, especially the use of the proposed tools in practice.
Úplný záznam

Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.
Digitální repozitář :: Hledej :: Nový záznam :: Personalizace :: Nápověda
Powered by Invenio v1.1.2
Spravuje admin.invenio@techlib.cz
Tato stránka je dostupná také v následujících jazycích:
Česky  English