Kadah, NezirÖzbek, Necdet Sinan2025-01-062025-01-0620202148-268310.31590/ejosat.822361https://doi.org/10.31590/ejosat.822361https://search.trdizin.gov.tr/tr/yayin/detay/485168https://hdl.handle.net/20.500.14669/731The sparse identification of nonlinear dynamics (SINDy), which is based on the sparse regression techniques to identify the nonlinear systems, is one of the recent data-driven model identification methods. The model equations of the system are extracted from the data. Although sufficient data is available from most of the engineering, healthcare, and economic sciences, there are few well-defined models to represent the system behaviour that can also be estimated from data-driven methods. With this motivation in mind, this study presents offline data-driven identification techniques to build the mathematical model of nonlinear systems. The data-based sparse identification of nonlinear systems is elaborated with a number of examples. The performance of the identification procedure is discussed in terms of quantitative metrics in the presence of noisy measurements.eninfo:eu-repo/semantics/openAccessBilgisayar BilimleriYazılım MühendisliğiFizikAtomik ve Moleküler KimyaBilgisayar BilimleriTeori ve Metotlarİstatistik ve OlasılıkArticle263Ejosat Özel Sayı 2020 (ISMSIT)2544851680