Origin-Destination Flow and Traffic Parameter Estimation Based on Cellular Network Data and Vehicle Movement Historical Records

master's thesis

• Title (croatian): Određivanje izvorišno-odredišnih protoka vozila te prometnih parametara zasnovano na podatcima celularne mreže i povijesnih zapisa kretanja vozila
• Author: Nikola Mardešić
• Mentor: Tonči Carić (mentor)
• Mentor: Leo Tišljarić (komentor)
• Committee member: Edouard Ivanjko (predsjednik povjerenstva)
• Committee member: Pero Škorput (član povjerenstva)
• Committee member: Miroslav Vujić (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: 2021-09-22, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Traffic and Transport Technology; Intelligent Transport Systems and Logistics

Abstract

With suitable algorithms, it is possible to ascertain a certain spatiotemporal logic for a given area by combining cellular and vehicular data. This thesis proposes a set of methods that aim to estimate trajectories of sparse cellular data by reconstructing a road network using the Floating Car Data (FCD). Thenceforth, generating a pool of alternative paths of the reconstructed network with a shortest-path algorithm and conclusively computing an algorithm that allocates the user an alternative route with the highest spatial and temporal similarity to the observed ground-truth origin-destination pair (user) trajectory. With the data on the user trajectories used through a transportation network, this thesis aims to develop a model which calculates the networks traffic flow estimates.

Abstract (croatian)

Pomoću prikladnih algoritama, moguće je utvrditi određenu prostorno-vremensku zakonitost prometnog toka obuhvaćenog područja kombiniranjem podataka o celularnoj mreži i povijesnih zapisa kretanja vozila. U ovom se radu predlaže skup metoda kojima je cilj procijeniti putanje kretanja korisnika celularne mreže rekonstrukcijom cestovne mreže pomoću plutajućih podataka o vozilu (FCD). Nadalje, nad rekonstruiranom cestovnom mrežom se izvršava algoritam najkraćeg puta te se generira n alternativnih trajektorija. Konačni korak procjene trajektorije predstavlja izvršavanje algoritma koji korisniku dodjeljuje alternativni put s najvećom prostornom i vremenskom sličnošću s promatranim parom ishodišno-odredišne putanje korisnika. Pomoću podataka o korisničkim putanjama korištenim kroz prometnu mrežu, ovaj rad teži razviti model koji izračunava procjene protoka prometa na mreži.

• Keywords: NoSQL; C#; large data sets; traffic data analysis; trajectory estimation; traffic flow estimation
• Keywords (croatian): NoSQL; C#; veliki skupovi podataka; analiza prometnih podataka; procjena trajektorija kretanja korisnika; procjena prometnog toka
• Language: english
• URN:NBN: urn:nbn:hr:119:515723
• Study programme: Title: Intelligent Transport Systems and Logistics; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka prometa (magistar/magistra inženjer/inženjerka prometa)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2021-10-25 15:07:25