Razvoj klasifikacijskega modela za računalniško opremo

Perko, Bojan

| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

First page > Show document

Show document

Title:	Razvoj klasifikacijskega modela za računalniško opremo
Authors:	ID Perko, Bojan (Author) ID Kljajić Borštnar, Mirjana (Mentor) More about this mentor...
Files:	MAG_Perko_Bojan_2021.pdf (2,09 MB) MD5: 4D555E6B2B480774C54823E91DC64A1A PID: 20.500.12556/dkum/20410870-f8f1-4b46-9f17-7cc6bca625fa
Language:	Slovenian
Work type:	Master's thesis/paper
Typology:	2.09 - Master's Thesis
Organization:	FOV - Faculty of Organizational Sciences in Kranj
Abstract:	Zaključna naloga obravnava načrtovanje in razvoj celovite rešitve, ki vključuje razvoj več razrednega klasifikacijskega modela in razvoj modelov razvrščanja v skupine z uporabo strojnega učenja. Glavni namen rešitve je nadomestitev ročnega uvrščanja podatkov o računalniških izdelkih v vnaprej določene skupine izdelkov, in sicer z avtomatizirano celovito rešitvijo, katere namen je izboljšanje procesa izračuna indeksa cen življenjskih potrebščin. Izdelki, razvrščeni v skupine, so namreč osnova za zajem podatkov pri izračunu indeksa cen življenjskih potrebščin, ki se uporablja za merilo inflacije. Rešitev smo razvili po metodologiji CRISP-DM, z uporabo različnih tehnologij, in sicer relacijske podatkovne baze Microsoft SQL Server, ogrodja .NET Core, ogrodja ML.NET in programskega jezika C#. Rezultat zaključnega dela je celovita rešitev, ki omogoča samodejno izvajanje napovedi oziroma klasifikacije podatkov o računalniških izdelkih ter v nadaljevanju združevanje teh podatkov v homogene skupine, hkrati pa preko aplikacijskega vmesnika uporabnikom omogoča nadzor nad izvajanjem delovanja rešitve. Rešitev, ki smo jo razvili v zaključni nalogi, pripomore k bolj konsistentni, kakovostni in učinkoviti obdelavi podatkov ter s tem olajša delo pri naročniku. Možnosti nadaljnjega razvoja se kažejo v več segmentih, pri čemer je bistvenega pomena uporaba večje količine podatkov in s tem bolj natančna klasifikacija.
Keywords:	strojno učenje, klasifikacija, gručenje, ML.NET, podatkovna baza
Place of publishing:	Maribor
Year of publishing:	2021
PID:	20.500.12556/DKUM-79339
COBISS.SI-ID:	73305091
Publication date in DKUM:	18.08.2021
Views:	1431
Downloads:	92
Metadata:
Categories:	FOV
:	Copy citation

Average score:	(0 votes)
Your score:	Voting is allowed only for logged in users.
Share:

Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:	CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

Link:	http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:	The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:	14.06.2021

Secondary language

Language:	English
Title:	Development of computer hardware classification model
Abstract:	This Master'sthesis deals with the design and development of a comprehensive solution, which includes the development of a multi-class classification model and the development of clustering models using machine learning. The main purpose of the solution is to replace the manual data classification of computer products into predefined product groups with an automated comprehensive solution, the purpose of which is to improve the process of calculating the consumer price index. Products classified into groups are the basis for calculation of the consumer price index, which is used as a measure of inflation. The solution was developed according to the CRISP-DM methodology. Using a variety of technologies, namely the Microsoft SQL Server relational database, the .NET Core framework, the ML.NET framework, and the C # programming language. The result is a comprehensive solution that enables the automatic implementation of forecasts or classification of data on computer products and further aggregation of this data into homogeneous groups. At the same time, it allows the user to manage and control the operation of the solution through the user interface. The solution we developed in the final Master's thesis contributes to a more consistent, high-quality and efficient data processing, thus facilitating the work of the client. The possibilities for further development are reflected in several segments, with the use of a larger amount of data being essential and thus a more accurate classification.
Keywords:	machine learning, classification, clustering, ML.NET, database

Comments

Leave comment

You must log in to leave a comment.

Comments (0)

0 - 0 / 0

There are no comments!

Back