https://doi.org/10.1140/epjs/s11734-024-01329-6
Regular Article
Classification of sprott chaotic systems via projection of the attractors using deep learning methods
1
Department of Computer Engineering, Faculty of Engineering, Hitit University, 19030, Corum, Turkey
2
Department of Electronics and Automation, Osmancık Omer Derindere Vocational School, Hitit University, 19500, Corum, Turkey
3
Department of Computer Technologies, Vocational School of Technical Sciences, Hitit University, 19169, Corum, Turkey
4
Department of Electronics and Automation, Alaca Avni Celik Vocational School, Hitit University, 19600, Corum, Turkey
a akifakgul@hitit.edu.tr, akgulakif@gmail.com
Received:
24
June
2024
Accepted:
5
September
2024
Published online:
19
September
2024
This study uses deep learning methods to classify the projection of the attractor’s images of five different chaotic systems. The chaotic systems addressed in the research are Sprott C, Sprott F, Sprott G, Sprott H, and Sprott M. A dataset was created for classification using the projection of attractors of these five different chaotic systems. This dataset contains time series images, and the graphs are generated based on initial conditions, Runge–Kutta 4 step size, and time length. Deep learning methods such as ResNet50, ResNet50V2, VGG19, InceptionV3, MobileNetV2, and VGG16 have been utilized for classification. This study's classification accuracy varies between 91.6% and 99.9%, depending on the problem. Therefore, this research accurately determines which chaotic system a projection of the attractors graphic image belongs to. This high accuracy demonstrates the usability of this model in analyzing chaotic systems in real-world applications. Such accuracies can be considered a powerful tool in analyzing industrial systems or other systems with complex structures. This work successfully uses deep learning methods for classifying chaotic systems. Such research could be an important step toward understanding and managing complex systems.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to EDP Sciences, Springer-Verlag GmbH Germany, part of Springer Nature 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
