Analiza utjecaja meteoroloških prilika i stanja kolnika na poštivanje ograničenja brzine

master's thesis

• Title (english): Analysis of Meteorological and Road Conditions on Compliance with Speed Limits
• Author: Zvonimir Batarilo
• Mentor: Martin Gregurić (mentor)
• Committee member: Miroslav Vujić (predsjednik povjerenstva)
• Committee member: Luka Novačko (član povjerenstva)
• Committee member: Edouard Ivanjko (član povjerenstva)
• Granter: University of Zagreb; Faculty of Transport and Traffic Sciences; (Division of Intelligent Transport Systems and Logistics); (Department of Intelligent Transport Systems); Zagreb
• Defense date and country: 2024-09-25, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Traffic and Transport Technology; Intelligent Transport Systems and Logistics

Abstract

Znanost o podacima (engl. Data science) je računalna disciplina koja se bavi problemom
izvlačenja znanja iz strukturiranih i nestrukturiranih podataka, uključujući velike skupove
podataka. Jedna takva velika skupina podataka nudi uvid o brzinama i kategorijama vozila koja se
kreću dionicom Zagreb-Karlovac na autocesti A1 u rasponu od 3 godine od 2018. godine do 2020.
godine. Također, za isti period zabilježeni su i meteorološki podaci za tu istu dionicu. Podaci
sadržavaju informacije kao što su: vrsta i intenzitet oborina; temperatura zraka i kolnika, točke
ledišta kolnika; vidljivosti; debljini vodenog sloja; maksimalnoj brzini vjetra; opasnosti od
poledice i stanju povrtine kolnika. Svaka ta meteorološka značajka i značajka o stanju kolnika
utječe na brzinu vožnje motornih vozila na promatranoj dionici. Unutar diplomskog rada
vizualizirat će se ti utjecaji kako bi se utvrdile one značajke koje najviše utječu na brzinu motornih
vozila. Stvorit će se model korištenjem metoda strojnog učenja, odabir meteoroloških značajki i
značajki stanja kolnika s najvećim utjecajem na brzinu vozila na autocesti. Zatim će se provesti
analiza koja će dovesti u korelaciju poštivanje ograničenja brzine u odnosu na odabrane značajke.
Rezultati će odgovarajuće vizualizirati i interpretirati u kontekstu mogućih intervencija u
povećanju poštivanja ograničenja brzine u nepovoljnim prilikama.

Abstract (english)

Data science is a computational discipline that addresses the problem of extracting
knowledge from structured and unstructured data, including large datasets. One such large dataset
provides insight into the speeds and categories of vehicles traveling the Zagreb-Karlovac section
of the A1 highway over a period of 3 years, from 2018 to 2020. Additionally, meteorological data
for the same section were recorded during the same period. The data include information such as:
type and intensity of precipitation; air and road surface temperatures; freezing points of the road
surface; visibility; thickness of the water layer; maximum wind speed; risk of ice formation, and
the condition of the road surface. Each of these meteorological features, as well as the road
condition features, affects the speed of vehicles on the observed section. Within this thesis, these
influences will be visualized to determine which features have the greatest impact on vehicle
speed. A model will be created using machine learning methods to select the meteorological and
road condition features with the greatest influence on vehicle speed on the highway. Following
this, an analysis will be conducted to correlate speed limit compliance with the selected features.
The results will be appropriately visualized and interpreted in the context of potential interventions
to increase compliance with speed limits under adverse conditions.

• Keywords: meteorološki podaci; prosječna brzina; metoda strojnog učenja; odabrane značajke
• Keywords (english): meteorological data; average speed; machine learning method; feature selection
• Language: croatian
• URN:NBN: urn:nbn:hr:119:127817
• Study programme: Title: Intelligent Transportation Systems and Logistics; Study programme type: university; Study level: graduate; Academic / professional title: sveučilišni/a magistar/magistra inženjer/inženjerka prometa (sveučilišni/a magistar/magistra inženjer/inženjerka prometa)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-12-05 12:46:11