Izrada informacijsko komunikacijskog sustava za detekciju anomalija prometnog toka na urbanim prometnicama

master's thesis

• Title (english): Development of an Information and Communication System for the Detection of Traffic Flow Anomalies on Urban Roads
• Author: Željko Majstorović
• Mentor: Tonči Carić (mentor)
• Committee member: Ivan Grgurević (predsjednik povjerenstva)
• Committee member: Mario Muštra (član povjerenstva)
• Committee member: Marko Matulin (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: 2020-07-14, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Traffic and Transport Technology; Postal and Telecommunications Traffic

Abstract

Zagušenja na prometnicama su česta pojava s kojom se svakodnevno susreće veliki broj ljudi. Ona nepovoljno utječu ne samo na sudionike u prometu nego i na stanovnike u gradu i okoliš. U ovom radu opisana je metoda za detekciju anomalija korištenjem prikupljenih GPS podataka, prikazanih koristeći koncept prijelaznih matrica brzina na području grada Zagreba. Opisane su metode pristupa detekciji anomalija te izrada sustava za pohranu podataka, kao i metode korištene za obradu prometnih podataka. U radu je opisan postupak određivanja težišta i mjere udaljenosti između težišta promatrane i referentne prijelazne matrice brzina. Cilj rada je izrada informacijsko - komunikacijskog sustava za detekciju anomalija na urbanim prometnicama te usporedba predložene mjere za udaljenost s ostalim mjerama udaljenosti. U tu svrhu je izrađena aplikacija za detekciju anomalija pomoću programskog jezika Python i MongoDB, NoSQL baze podataka, a detektirane anomalije su prikazane na interaktivnoj karti grada Zagreba.

Abstract (english)

This thesis describes the method for anomaly detection using the collected GPS data in form of the speed transition matrices in the city of Zagreb. Methods for anomaly detection and development of data storage system are described, as well as methods used for image processing. The thesis describes the procedure for determining the center of mass and measures the distance between the center of mass of the observed and the reference speed transition matrix. The aim of this thesis is to develop an information and communication system for the detection of anomalies on urban roads and to compare the proposed distance measure with other distance measures. For this purpose, an application for the detection of anomalies using the Python programming language and the MongoDB, NoSQL database was developed. Detected anomalies are shown on an interactive map of the city of Zagreb.

• Keywords: detekcija anomalija; obrada slika; težišta; vizualizacija podataka; GPS; IQR; NoSQL; MongoDB; Python
• Keywords (english): anomaly detection; image processing; center of mass; data visualization; GPS; IQR; NoSQL; MongoDB; Python
• Language: croatian
• URN:NBN: urn:nbn:hr:119:497299
• Study programme: Title: Traffic and Transport; specializations in: Road Traffic and Transport, Railway Traffic and Transport, Water Traffic and Transport, Air Traffic and Transport, Postal Traffic, Information and Communication Traffic, Urban Traffic and Transport; Course: Road Traffic and Transport; 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: 2020-08-21 10:39:50