Home // DBKDA 2025, The Seventeenth International Conference on Advances in Databases, Knowledge, and Data Applications // View article

Evolving the Automated Search for Clusters of Similar Trajectory Groups

Authors:
Friedemann Schwenkreis

Keywords: trajectory sets; SNN clustering; frequent itemsets; tactics recognition

Abstract:
The work presented in this paper builds upon a previous approach to automatically detect tactics based on spatiotemporal data in the context of team handball. It will be shown how the availability of additional data allows us to verify the principal approach. However, it will also be shown that the previous approach for choosing parameters of the applied methods was suboptimal, and an application-oriented approach based on heuristics helps to improve the results significantly. Basically, the combination of Shared Nearest Neighbor Clustering and the search for frequent itemsets is used to find clusters of trajectory groups. These basic methods are enhanced by special notions of distance and cluster quality indexes which allows to find optimal parameter settings for the specific application scenario. Furthermore, an approach is presented to use the existing “composite model” to determine the cluster to which a group of trajectories belongs to (application of the composite model).

Pages: 48 to 57

Copyright: Copyright (c) IARIA, 2025

Publication date: March 9, 2025

Published in: conference

ISSN: 2308-4332

ISBN: 978-1-68558-244-9

Location: Lisbon, Portugal

Dates: from March 9, 2025 to March 13, 2025