20.500.12556/DKUM-83150 Razvoj inteligentne rešitve za vrednotenje vozil z uporabo strojnega učenja magistrsko delo Development of an intelligent solution for vehicle evaluation using machine learning Eden izmed ključnih problemov hitrega razvoja inteligentnih rešitev je v tem, kako čim bolj sistematično, avtomatizirano in nadzorovano optimizirati razvojni proces. Željen je čim manjši vpliv hitro vpeljanih sprememb v podatkih ali programski kodi na samo končno rešitev in sledenje vpliva sprememb. Namen magistrskega dela je predvsem vpeljati inženirski pristop ML Ops, ki v veliki meri avtomatizira korake v razvoju programske rešitve, in ga preizkusiti na primeru razvoja inteligentne rešitve za vrednotenje vozil z uporabo strojnega učenja in podatkov s spletnih strani z rabljenimi vozili. Končni rezultati, da je razvojni proces po vpeljavi ML Ops bolj organiziran ter v veliki meri razbremeni sodelujoče na projektu, ne presenečajo, preseneča pa medsebojna kompatibilnost izbranih orodij, ki smo jih izbrali za naš projekt, ter sama pripravljenost na vpeljavo koncepta. One of the key problems of rapid development of intelligent solutions is the problem of how to optimize the development process as systematically, automatically and controlled as possible. It is desired to have as little impact as possible when changes are rapidly introduced in data or program code and to track the impact of changes. The purpose of the master's work is primarily to introduce the ML Ops engineering approach, which largely automates the steps in the development of a software solution, and to test it on the example of the development of an intelligent solution for the evaluation of vehicles using machine learning and data from websites with used vehicles. The results, that the development process after the implementation of ML Ops was managed in a more organized manner and to a large extent relieves the project participants, are not surprising, but the mutual compatibility of the selected tools that we have chosen for our project and the readiness to introduce the concept, are quite surprising. inteligentna rešitev vrednotenje vozil strojno učenje intelligent systems vehicle evaluation machine learning true true false [D. Žele] Slovenski jezik Angleški jezik Magistrsko delo/naloga 2022-09-21 19:32:23 2022-11-07 15:03:13 2023-03-25 03:05:57 0000-00-00 00:00:00 2022 0 Maribor 0 Maribor 1 spletni vir (1 datoteka PDF (XII, 68 f.)) 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.85:004.413043.2) 146410243 MAG_Zele_David_2022.pdf MAG_Zele_David_2022.pdf 1 F910CD4460A4EFA37A87C8CEA753824A 1f265e9ff3d25c18489183bd315aa277c545fea9baff78d8a3eecb91bbe2740f 4d1fb3ca-3d75-11ed-9af8-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=163421 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0