dc.contributor.author | Uzun, Süleyman | |
dc.date.accessioned | 2022-02-09T12:30:24Z | |
dc.date.available | 2022-02-09T12:30:24Z | |
dc.date.issued | 2021 | |
dc.identifier.issn | 19516355 | |
dc.identifier.uri | https://doi.org/10.1140/epjs/s11734-021-00346-z | |
dc.identifier.uri | https://hdl.handle.net/20.500.14002/437 | |
dc.description.abstract | In this study, the classification of time series belonging to three different chaotic systems has been proposed using machine learning methods. For this purpose, the time series of Lorenz, Chen, and Rossler systems, three of the well-known chaotic systems, are classified using machine learning methods. In the study, the classification of chaotic systems has been made with 18 sub-methods of Naive Bayes, Support Vector Machines, K-Nearest Neighborhood, and Tree methods. As a result, the K-Nearest Neighborhood method has classified time series belonging to chaotic systems with very high accuracy of 99.2%. In this way, it has become possible to associate the chaotic-random signals with a mathematical system. © 2021, The Author(s), under exclusive licence to EDP Sciences, Springer-Verlag GmbH Germany, part of Springer Nature. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Springer Science and Business Media Deutschland GmbH | en_US |
dc.relation.ispartof | European Physical Journal: Special Topics | en_US |
dc.rights | info:eu-repo/semantics/closedAccess | en_US |
dc.title | Machine learning-based classification of time series of chaotic systems | en_US |
dc.type | article | en_US |
dc.department | Fakülteler, Teknoloji Fakültesi, Bilgisayar Mühendisliği Bölümü | en_US |
dc.institutionauthor | Uzun, S. | |
dc.identifier.doi | 10.1140/epjs/s11734-021-00346-z | |
dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | en_US |
dc.authorscopusid | 57365485500 | |
dc.identifier.scopus | 2-s2.0-85120754326 | en_US |