Scale and Time Independent Clustering of Time Series Data

Florian Steinwidder, Florian Steinwidder, Istvan Szilagyi, Eva Eggeling, Torsten Ullrich, Torsten Ullrich

2024

Abstract

The analysis of time series, and in particular the identification of similar time series within a large set of time series, is an important part of visual analytics. This paper describes extensions of tree-based index structures to find self-similarities within sets of time series. It also describes filters that extend existing algorithms to better fit real-world, error-prone, incomplete data. The ability of time series clustering to detect common errors in real data is also described. These main contributions are illustrated with real data and the findings and lessons learned are summarised.

Paper Citation

in Harvard Style

Steinwidder F., Szilagyi I., Eggeling E. and Ullrich T. (2024). Scale and Time Independent Clustering of Time Series Data. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: IVAPP; ISBN 978-989-758-679-8, SciTePress, pages 583-592. DOI: 10.5220/0012377000003660

in Bibtex Style

@conference{ivapp24,
author={Florian Steinwidder and Istvan Szilagyi and Eva Eggeling and Torsten Ullrich},
title={Scale and Time Independent Clustering of Time Series Data},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: IVAPP},
year={2024},
pages={583-592},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012377000003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: IVAPP
TI - Scale and Time Independent Clustering of Time Series Data
SN - 978-989-758-679-8
AU - Steinwidder F.
AU - Szilagyi I.
AU - Eggeling E.
AU - Ullrich T.
PY - 2024
SP - 583
EP - 592
DO - 10.5220/0012377000003660
PB - SciTePress