<?xml version="1.0"?><rdf:RDF xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:edm="http://www.europeana.eu/schemas/edm/" xmlns:wgs84_pos="http://www.w3.org/2003/01/geo/wgs84_pos" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:rdaGr2="http://rdvocab.info/ElementsGr2" xmlns:oai="http://www.openarchives.org/OAI/2.0/" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:ore="http://www.openarchives.org/ore/terms/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:dcterms="http://purl.org/dc/terms/"><edm:WebResource rdf:about="http://www.dlib.si/stream/URN:NBN:SI:DOC-Q1RIGLWM/a5694648beb4d8ebc6-4-7778-e8de68-92a/PDF"><dcterms:extent>13678 KB</dcterms:extent></edm:WebResource><edm:WebResource rdf:about="http://www.dlib.si/stream/URN:NBN:SI:DOC-Q1RIGLWM/8aef510c-5a89-483f-905a-9923f17c4910/TEXT"><dcterms:extent>400 KB</dcterms:extent></edm:WebResource><edm:WebResource rdf:about="http://www.dlib.si/stream/URN:NBN:SI:DOC-Q1RIGLWM/e645e889-b67b-4927-8abc-4d8de6e4a867/WEB"><dcterms:extent>0 KB</dcterms:extent></edm:WebResource><edm:ProvidedCHO rdf:about="URN:NBN:SI:DOC-Q1RIGLWM"><dcterms:issued>2011</dcterms:issued><dc:creator>Ištoka Otković, Irena</dc:creator><dc:contributor>Šraml, Matjaž</dc:contributor><dc:contributor>Tollazzi, Tomaž</dc:contributor><dc:format xml:lang="sl">VI, 161 str., 30 cm</dc:format><dc:identifier>COBISSID:15017494</dc:identifier><dc:identifier>URN:URN:NBN:SI:doc-Q1RIGLWM</dc:identifier><dc:language>en</dc:language><dc:publisher xml:lang="sl">I. Ištoka Otković</dc:publisher><dc:source xml:lang="sl">visokošolska dela</dc:source><dc:subject xml:lang="sl">Disertacije</dc:subject><dc:subject xml:lang="sl">kalibracija</dc:subject><dc:subject xml:lang="sl">Krožna križišča</dc:subject><dc:subject xml:lang="sl">mikro simulacija prometnih modelov</dc:subject><dc:subject xml:lang="sl">modeliranje</dc:subject><dc:subject xml:lang="sl">nevronske mreže</dc:subject><dc:subject xml:lang="sl">potovalni čas</dc:subject><dc:subject xml:lang="sl">prometni modeli</dc:subject><dc:subject xml:lang="sl">računalniška kalibracija</dc:subject><dc:subject xml:lang="sl">simulacija</dc:subject><dc:title xml:lang="sl">Using neural networks in the process of calibrating the microsimulation models in the analysis and design of roundabouts in urban areas| thesis|</dc:title><dc:description xml:lang="sl">The thesis researches the application of neural networks in computer program calibration of traffic micro-simulation models. The calibration process is designed on the basis of the VISSIM micro-simulation model of local urban roundabouts. From the five analyzed methods of computer program calibration, Methods I, II and V were selected for a more detailed research. The three chosen calibration methods varied the number of outgoing traffic indicators predicted by neural networks and a number of neural networks in the computer program calibration procedure. Within the calibration program, the task of neural networks was to predict the output of VISSIM simulations for selected functional traffic parameters - traveling time between the measurement points and queue parameters (maximum queue and number of stopping at the roundabout entrance). The Databases for neural network training consisted of 1379 combinations of input parameters whereas the number of output indicators of VISSIM simulations was varied. The neural networks (176 of them) were trained and compared for the calibration process according to training and generalization criteria. The best neural network for each calibration method was chosen by using the two-phase validation of neural networks. The Method Iis the calibration method based on calibration of a traffic indicator -traveling time and it enables validation related to the second observed indicator - queue parameters. Methods II and V connect the previously described calibration and validation procedures in one calibration process which calibrates input parameters according to two traffic indicators. Validation of the analyzed calibration methods was performed on three new sets of measured data - two sets at the same roundabout and one set on another location. The best results in validation of computer program calibration were achieved by the Method I which is the recommended method for computer program calibration. The modeling results of selected traffic parameters obtained by calibrated VISSIM traffic model were compared with: values obtained by measurements in the field, the existing analysis methods of operational roundabouts characteristics (Lausanne method, Kimber-Hollis, HCM) and modeling by the uncalibrated VISSIM model. The calibrated model shows good correspondence with measured values in real traffic conditions. The efficiency of the calibration process was confirmed by comparing the measured and modeled values of delays, of an independent traffic indicator that was notused in the process of calibration and validation of traffic micro-simulation models. There is also an example of using the calibrated model in the impact analysis of pedestrian flows on conflicting input and output flows of vehicles in the roundabout. Different traffic scenarios were analyzed in the real and anticipated traffic conditions</dc:description><dc:description xml:lang="sl">V predloženi doktorski disertaciji je obravnavana in raziskana uporaba nevronskih mrež v procesu računalniške kalibracije (umerjanja) mikro-simulacijskih prometnih modelov. Proces kalibracije je uporabljen na primeru VISSIM mikro-simulacijskega modela, za načrtovanje in analizo krožnih križišč v urbanem okolju. Izmed petih analiziranih metod računalniške kalibracije smo izbrali tri najoptimalnejše (Metodo I, II in IV) v nadaljnjo raziskavo. Izbrane metode temeljijo na spreminjaju izhodnih parametrov prometnega toka, določenih s pomočjo nevronskih mrež in števila nevronskih mrež v postopku računalniške kalibracije. Osnovni cilj uporabe nevronskih mrežje bil, da smo s pomočjo računalniške kalibracije prometnih parametrov dosegli napoved izhodiščnih (VISSIM) simulacij za izbrane prometne kazalce - čas potovanja med mernimi točkami in parametri čakalne vrste (maksimalna čakalna vrsta in število ustavljanj na vhodu v krožno križišče). Baze podatkovza treniranje nevronskih mrež sestavlja 1379 različnih kombinacij vhodnih parametrov, pri čemer smo spreminjali izhodiščne kazalce mikrosimulacij (VISSIM modela). Nadalje smo trenirali 176 nevronskih mrež in rezultate kalibracije primerjali glede na kriterija treniranosti in generalizacije. Tako je bila v nadaljevanju izbrana najbolša nevronska mreža za posamezen model kalibracije, in sicer s pomočjo dvo-fazne validacije nevronskih mrež. Metoda I je metoda kalibracije, ki temelji na kalibraciji prometnega kazalca, t.j. čas potovanja in omogoča validacijo rezultatov glede na drugi opazovan kazalec, t.j. parametre čakalne vrste. Metodi II in IV povezujeta prej omenjeni proceduri kalibracije in validacije v enem samem procesu kalibracije, ki kalibrira vhodne parametre glede na dva prometna kazalca. Potrditev analiziranih kalibracisjkih metod smo izvedli na primeru treh novih nizov izmerjenih podatkov - dva niza smo izmerili na istem krožnem krožišču in enega na drugi lokaciji (drugem krožnem križišču). Najboljše rezultate validacije računalniške kalibracije smo dosegli z uporabo Metode I, ki smo jo v nadaljevanju tudi predlagali kot najbolj primerno metodo za računalniško programsko kalibracijo. Rezultate prometnih parametrov, ki smo jih pridobili s kalibriranim VISSIM prometnim modelom, smo primerjali z: vrednostmi, dobljenimi z meritvami na terenu; obstoječimi metodami analize za operativni izračun karakteristik krožnega križišča (z metodo Lausane, s Kimber-Hollis metodo in HCM) in z rezulttai simulacije, dobljenimi z nekalibriranim VISSIM modelom. Rezultati, dobljeni s kalibriranim modelom, so pokazali zelo dobro ujemanje z realnim dogajanjem v krožnih križiščih. Učinkovitost procesa programske kalibracije smo potrdili s primerjavo emd izmerjenimi in modeliranimi vrednostmi časovnih praznin (zamud), kot neodvisnega prometnega kazalca, saj ga nismo uporabili v procesu kalibraciej in validacije mikrosimulacijskih prometnih modelov. Na koncu je prikazan še praktični primer uporabe kalibriranega modela za analizo vpliva prometnega toka pešcev na vhodne in izhodne prometne tokove motornih vozil v krožnem krožišču. Analizirani so razični možni scenariji v realnih in predpostavljenih prometnih pogojih</dc:description><edm:type>TEXT</edm:type><dc:type xml:lang="sl">visokošolska dela</dc:type><dc:type xml:lang="en">theses and dissertations</dc:type><dc:type rdf:resource="http://www.wikidata.org/entity/Q1266946" /></edm:ProvidedCHO><ore:Aggregation rdf:about="http://www.dlib.si/?URN=URN:NBN:SI:DOC-Q1RIGLWM"><edm:aggregatedCHO rdf:resource="URN:NBN:SI:DOC-Q1RIGLWM" /><edm:isShownBy rdf:resource="http://www.dlib.si/stream/URN:NBN:SI:DOC-Q1RIGLWM/a5694648beb4d8ebc6-4-7778-e8de68-92a/PDF" /><edm:rights rdf:resource="http://rightsstatements.org/vocab/InC/1.0/" /><edm:provider>Slovenian National E-content Aggregator</edm:provider><edm:intermediateProvider xml:lang="en">National and University Library of Slovenia</edm:intermediateProvider><edm:dataProvider xml:lang="sl">Univerza v Mariboru, Fakulteta za gradbeništvo, prometno inženirstvo in arhitekturo</edm:dataProvider><edm:object rdf:resource="http://www.dlib.si/streamdb/URN:NBN:SI:DOC-Q1RIGLWM/maxi/edm" /><edm:isShownAt rdf:resource="http://www.dlib.si/details/URN:NBN:SI:DOC-Q1RIGLWM" /></ore:Aggregation></rdf:RDF>