Detail publikace

Device behavior analysis based on OPC UA

POSPÍŠIL, O. MOŽNÝ, R.

Originální název

Device behavior analysis based on OPC UA

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

Device identification in industrial networks is a significant topic as there is a need to identify devices based on passive scanning. Machine learning (ML) techniques can prove useful in this approach. This paper discusses the applicability of different data sources for device identification and focuses on timing information from network communication, specifically from the open platform communication unified architecture (OPC UA) protocol. The aim was to explore the potential of device identification based on this data. In this study, Random Forest and XGBoost ML algorithms were utilized for device identification. In the case types of devices known in the learning phase, the proposed algorithm achieved an accuracy score of up to 0.99. However, for unknown device types, the accuracy score was only around 0.71. The findings suggest that using time information for device identification is a promising direction for further development.

Klíčová slova

device behavior analysis, machine learning, opcua, random forest, xgboost

Autoři

POSPÍŠIL, O.; MOŽNÝ, R.

Vydáno

25. 4. 2023

Nakladatel

Brno University of Technology, Faculty of Electrical Engineering and Communication

Místo

Brno

ISBN

978-80-214-6153-6

Kniha

Proceedings I of the 29th Conference STUDENT EEICT 2023 General papers

Edice

1

Strany od

445

Strany do

449

Strany počet

5

URL

https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_1.pdf

BibTex

@inproceedings{BUT183347,
  author="Ondřej {Pospíšil} and Radek {Možný}",
  title="Device behavior analysis based on OPC UA",
  booktitle="Proceedings I of the 29th Conference STUDENT EEICT 2023 General papers
",
  year="2023",
  series="1",
  pages="445--449",
  publisher="Brno University of Technology, Faculty of Electrical Engineering and Communication",
  address="Brno",
  isbn="978-80-214-6153-6",
  url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_1.pdf"
}