EUVIMEDEUVIMED entdecken
Crossref

Detection of deterministic and chaotic signals on the basis of the LSTM model training results

Pawel Kasprowski iD, Dariusz Augustyn iD, Agnieszka Szczęsna iD, Henryk Josiński iD, Katarzyna Harężlak iD, Adam Świtoński iD

Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.03.2025 · 35 (3)

DOI: 10.1063/5.0224768 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 25.03.2025. Verfasst von Pawel Kasprowski und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Applied Informatics, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology, Akademicka 16, …. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Silesian University of Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Detection of chaos in dynamical signals is an important and popular research area. Traditionally, the chaotic behavior is evaluated by calculating the Largest Lyapunov Exponent (LLE). However, calculating the LLE is sometimes difficult and requires specific data. Moreover, it introduces some subjective assumptions and is sometimes called a “manual” method. Therefore, there are many attempts to provide alternative ways to assess the dynamical signal as chaotic or deterministic. Some of them use deep learning methods. In this paper, we present a novel method of signal classification that is based on the assumption that it is easier to learn deterministic behavior than a chaotic one. We show that based on this assumption, it is possible to calculate the “amount of chaos” in the signal with the help of a simple LSTM (Long Short-Term Memory) neural network. The main advantage of this method is that—contrary to other deep learning-based methods—it does not require prior data to train the network as the results of the training process for a signal being classified are taken into account as the result of this evaluation. We confirm the method’s validity using the publicly available dataset of chaotic and deterministic signals.

Autor:innen und Institutionen

  • Department of Applied Informatics, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland.
  • Department of Computer Graphics, Vision and Digital Systems, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland.

ORCID-Profile: Pawel Kasprowski, Dariusz Augustyn, Agnieszka Szczęsna, Henryk Josiński, Katarzyna Harężlak, Adam Świtoński

Förderung

  • Silesian University of Technology

Zitieren

APA

Kasprowski, P., Augustyn, D., Szczęsna, A., Josiński, H., Harężlak, K., & Świtoński, A. (2025). Detection of deterministic and chaotic signals on the basis of the LSTM model training results. Chaos: An Interdisciplinary Journal of Nonlinear Science, 35(3). https://doi.org/10.1063/5.0224768

Vancouver

Kasprowski P, Augustyn D, Szczęsna A, Josiński H, Harężlak K, Świtoński A. Detection of deterministic and chaotic signals on the basis of the LSTM model training results. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2025;35(3). doi:10.1063/5.0224768

BibTeX
@article{Kasprowski2025,
  author = {Kasprowski, Pawel and Augustyn, Dariusz and Szczęsna, Agnieszka and Josiński, Henryk and Harężlak, Katarzyna and Świtoński, Adam},
  title = {Detection of deterministic and chaotic signals on the basis of the LSTM model training results},
  journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
  year = {2025},
  volume = {35},
  number = {3},
  doi = {10.1063/5.0224768}
}
Kostenlos starten →