Supervised and Unsupervised Machine Learning Methods for System Log Anomaly Detection – Bc. Júlia Ščensná
Bc. Júlia Ščensná
Master's thesis
Supervised and Unsupervised Machine Learning Methods for System Log Anomaly Detection
Supervised and Unsupervised Machine Learning Methods for System Log Anomaly Detection
Abstract:
Táto práca sa zaoberá implementáciou sady nástrojov, ktoré využívajú algoritmy strojového učenia pre klasifikáciu systémových logov a detekovanie anomálií. Navrhované modely sú postavené na dvoch kategóriách strojového učenia, a to učenie s učiteľom (supervised learning) a učenie bez učiteľa (unsupervised learning). V rámci práce je funkcionalita a správanie vybraných metód vysvetlená teoreticky aj …moreAbstract:
This thesis deals with implementing toolset that uses machine learning algorithms for system logs classification and anomaly detection. The proposed models are built based on supervised and unsupervised machine learning methods. However, the functionality and behavior of these methods have been explained theoretically and practically in the thesis. Sufficient numbers of simulated plots are included …more
Language used: English
Date on which the thesis was submitted / produced: 19. 5. 2020
Identifier:
https://is.muni.cz/th/hxw78/
Thesis defence
- Date of defence: 15. 6. 2020
- Supervisor: RNDr. Radek Ošlejšek, Ph.D.
- Reader: doc. RNDr. Ivan Kopeček, CSc.
Citation record
ISO 690-compliant citation record:
ŠČENSNÁ, Júlia. \textit{Supervised and Unsupervised Machine Learning Methods for System Log Anomaly Detection}. Online. Master's thesis. Brno: Masaryk University, Faculty of Informatics. 2020. Available from: https://theses.cz/id/tc15pj/.
Full text of thesis
Contents of on-line thesis archive
Published in Theses:- světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatikyMasaryk University
Faculty of InformaticsMaster programme / field:
Applied Informatics / Applied Informatics
Theses on a related topic
-
Návrh klasifikátoru parametrů udržitelného rozvoje pomocí Support Vector Machine
Petra Špírková -
Software using random forest for risk prediction of heart valve surgery patients
Georg HERMANUTZ -
Machine Learning for Text Anomaly Detection
Alina Tsykynovska -
Unsupervised Machine Learning Methods for Behaviour Analysis and Anomaly Detection in University Environment
Pavel Strnad -
Unsupervised Time Series Anomaly Detection on Virtualisation host networks
Andrej Černek -
Ensembles for anomaly detection
Tomáš Krutý -
Graph-based Anomaly Detection in Network Traffic
Denisa Šrámková -
Asset allocation with reinforcement learning
Lukáš Galeta