Multidimensional Clustering for Machine Data Analysis

Information

• Publication Type: Bachelor Thesis
• Workgroup(s)/Project(s):
  • Visualization Group
• Date: July 2024
• Date (Start): 11. November 2023
• Date (End): 11. July 2024
• Matrikelnummer: 12120487
• First Supervisor: Eduard Gröller

Abstract

Machine data analysis is an important aspect in modern industrial facilities, as stakeholders want their machinery to be as efficient as possible. To this end, they utilize the IIoT, enabling the analysis of gathered machine data. To gain useful information through the aggregated data, Big Data analytics are invaluable to the domain experts conducting machine data analysis. The insights gained through Big Data analytics allow for a better efficiency of the facility by enabling data-driven decisions. This thesis sets out to explore the feasibility of multidimensional clustering for machine data analysis in a web-based environment. To do this, we developed an application that combines statistical methods and several visualization techniques into a web interface. We evaluated the tool based on its real-world applicability and performance. The developed application has produced promising results, when employed on multivariate time series from industrial machinery, and thereby provides a robust foundation for future improvements.

Additional Files and Images

Weblinks

No further information available.

BibTeX

@bachelorsthesis{Klaus2024,
  title =      "Multidimensional Clustering for Machine Data Analysis",
  author =     "Sebastian  Klaus",
  year =       "2024",
  abstract =   "Machine data analysis is an important aspect in modern
               industrial facilities, as stakeholders want their machinery
               to be as efficient as possible. To this end, they utilize
               the IIoT, enabling the analysis of gathered machine data. To
               gain useful information through the aggregated data, Big
               Data analytics are invaluable to the domain experts
               conducting machine data analysis. The insights gained
               through Big Data analytics allow for a better efficiency of
               the facility by enabling data-driven decisions. This thesis
               sets out to explore the feasibility of multidimensional
               clustering for machine data analysis in a web-based
               environment. To do this, we developed an application that
               combines statistical methods and several visualization
               techniques into a web interface. We evaluated the tool based
               on its real-world applicability and performance. The
               developed application has produced promising results, when
               employed on multivariate time series from industrial
               machinery, and thereby provides a robust foundation for
               future improvements.",
  month =      jul,
  address =    "Favoritenstrasse 9-11/E193-02, A-1040 Vienna, Austria",
  school =     "Research Unit of Computer Graphics, Institute of Visual
               Computing and Human-Centered Technology, Faculty of
               Informatics, TU Wien ",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2024/Klaus2024/",
}