| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Uporaba grafovskih samokodirnikov za odkrivanje anomalij v kompleksnih mrežah : magistrsko delo
Authors:ID Kramberger, Nika (Author)
ID Jesenko, David (Mentor) More about this mentor... New window
ID Bizjak, Marko (Comentor)
Files:.pdf MAG_Kramberger_Nika_2025.pdf (2,37 MB)
MD5: EDDE71F9C5BE5666F52A1DC606A223AE
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V magistrskem delu raziskujemo uporabo grafovskih samokodirnikov za odkrivanje anomalij v kompleksnih mrežah. Najprej predstavimo temeljne pojme s področja kompleksnih mrež, grafovskih nevronskih mrež, anomalij in samokodirnikov. Nato opišemo pripravo podatkov, zasnovo modela ter postopek dodajanja atributnih in strukturnih anomalij. Poseben poudarek namenimo vlogi rekonstrukcijskih napak pri prepoznavanju anomalij, uspešnost modela pa ovrednotimo z uporabo metrike F1. Na koncu predstavimo rezultate testiranj in v zaključku povzamemo glavne ugotovitve raziskave.
Keywords:samokodirniki, anomalije, kompleksne mreže, grafovske nevronske mreže, metrika F1
Place of publishing:Maribor
Place of performance:Maribor
Publisher:[N. Kramberger]
Year of publishing:2025
Number of pages:1 spletni vir (1 datoteka PDF (IX, 45 str.))
PID:20.500.12556/DKUM-95096 New window
UDC:004.8:519.17(043.2)
COBISS.SI-ID:259547651 New window
Publication date in DKUM:15.10.2025
Views:144
Downloads:22
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and 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:04.09.2025

Secondary language

Language:English
Title:Application of graph autoencoders for anomaly detection in complex networks
Abstract:The thesis explores the application of graph autoencoders for anomaly detection in complex networks. First, we introduce the basic concepts of complex networks, graph neural networks, anomalies, and autoencoders. We then describe the data preparation process, the model design, and the process of adding attribute and structural anomalies. We pay special attention to the role of reconstruction errors in anomaly detection, while the model’s performance is evaluated using the F1 score. Finally, we present the results of the testing and summarize the main findings of the research in the conclusion.
Keywords:autoencoders, anomalies, complex networks, graph neural networks, F1 score


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica