Rezervuar Hesaplama ile Kaotik Sinyallerde Zaman Serisi Tahmini ve Uygulaması

Yıl 2025, Cilt: 4 Sayı: 1, 8 - 14, 17.06.2025

Kenan Altun

Öz

Bu çalışma, kaotik zaman serisi tahmini için rezervuar hesaplama yönteminin etkinliğini araştırmayı amaçlamaktadır. Kaotik sinyal olarak Sprott-K sistemi seçilmiştir; bu sistem, basit bir yapıyla kaotik davranışlar sergiler. Sprott-K sisteminin matematiksel modeli detaylı bir şekilde sunulmuş, rezervuar hesaplama algoritmasının teorik temelleri açıklanmış ve Python programlama dili kullanılarak bir tahmin modeli geliştirilmiştir. Çalışmanın temel hedefi, kaotik sistemlerin kısa vadeli tahmininde rezervuar hesaplamanın potansiyelini ortaya koymaktır. Elde edilen sonuçlar, yöntemin kaotik zaman serilerinde yüksek doğruluk sağladığını göstermektedir.

Anahtar Kelimeler

Rezervuar Hesaplama , Kaotik Sinyaller , Zaman Serisi Tahmini , Sprott-K Sistemi

Time Series Prediction and Application in Chaotic Signals with Reservoir Computing

Öz

This study aims to investigate the effectiveness of the reservoir computing method for chaotic time series prediction. The Sprott-K system has been selected as the chaotic signal; this system exhibits chaotic behavior with a simple structure. The mathematical model of the Sprott-K system is presented in detail, the theoretical foundations of the reservoir computing algorithm are explained, and a prediction model has been developed using the Python programming language. The primary objective of the study is to demonstrate the potential of reservoir computing in the short-term prediction of chaotic systems. The obtained results indicate that the method achieves high accuracy in chaotic time series.

Anahtar Kelimeler

Reservoir Computing , Chaotic Signals , Time Series Prediction , Sprott-K System

Kaynakça

• Box, G. E. P., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: Forecasting and control (5th ed.). Wiley.
• Glass, L., & Mackey, M. C. (1988). From clocks to chaos: The rhythms of life. Princeton University Press.
• Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
• Jaeger, H. (2001). The “echo state” approach to analysing and training recurrent neural networks. German National Research Center for Information Technology, Technical Report.
• Lorenz, E. N. (1963). Deterministic nonperiodic flow. Journal of the Atmospheric Sciences, 20(2), 130-141.
• Lukoševičius, M., & Jaeger, H. (2012). Reservoir computing approaches to recurrent neural network training. Computer Science Review, 3(3), 127-149.
• Mantegna, R. N., & Stanley, H. E. (1999). An introduction to econophysics: Correlations and complexity in finance. Cambridge University Press.
• Ott, E. (1993). Chaos in dynamical systems. Cambridge University Press.
• Sprott, J. C. (2003). Chaos and time-series analysis. Oxford University Press.
• Strogatz, S. H. (1994). Nonlinear dynamics and chaos: With applications to physics, biology, chemistry, and engineering. Perseus Books.
• Van Rossum, G., & Drake, F. L. (2009). Python 3 reference manual. CreateSpace.