Primjena umjetne inteligencije na sustav za detekciju, praćenje i vrednovanje degradacije tramvajskih tračnica u javnom prometu

master's thesis

• Title (english): Application of artificial intelligence to the system for detection, monitoring and evaluation of tram track degradation in public transport
• Author: Šime Kožul
• Mentor: Siniša Fajt (mentor)
• Committee member: Siniša Fajt (predsjednik povjerenstva)
• Committee member: Ivan Đurek (član povjerenstva)
• Committee member: Marko Horvat (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-05, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Sustavi za nadgledanje i održavanje tramvajskih trasa su skupi, komplicirani i dugotrajni, stoga trebaju modernizaciju. Ovaj rad donosi umjetnu inteligenciju kao sredstvo predviđanja degradacije. Za treniranje različitih modela strojnog učenja bilo je potrebno prikupiti senzorske podatke, analizirati ih i označiti kako bi se mogli okoristiti nadziranim učenjem. Podaci su prikupljeni s napravljenom aplikacijom i mobilnim uređajem koji ima inercijske senzore akcelerometar i žiroskop. Uz mogućnost GPS-a implementirani sustav može oslikati područja različite alarmantnosti degradacije, informacija koja bi mogla biti prijeko potrebna nadležnim tijelima za ekonomičniju raspodjelu resursa.

Abstract (english)

Tram route monitoring and maintenance systems are expensive, complicated and time consuming, so they need modernization. This paper brings artificial intelligence as a means of predicting degradation. To train different models of machine learning, it was necessary to collect sensory data, analyze them and label them, so that they could benefit from supervised learning. An android application for gathering data was developed and installed on a mobile device that has inertial sensors accelerometer and gyroscope. With the utillization of GPS, the implemented system can map areas of different degradation levels, information that could be indispensable to the monitoring authorities for a more economical allocation of resources.

• Keywords: Sustavi za nadgledanje i održavanje tramvajskih trasa; umjetna inteligencija; strojno učenje; senzori; android aplikacija
• Keywords (english): Tram route monitoring; artifitial inteligence; machine learning; sensors; android application
• Language: croatian
• URN:NBN: urn:nbn:hr:168:924284
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 09:10:28