Turning Point Prediction of Oscillating Time Series using Local Dynamic Regression Models - Nonlinear Sciences > Chaotic DynamicsReportar como inadecuado




Turning Point Prediction of Oscillating Time Series using Local Dynamic Regression Models - Nonlinear Sciences > Chaotic Dynamics - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Abstract: In the prediction of oscillating time series, the interest is in the turningpoints of successive oscillations rather than the samples themselves. For thispurpose a scheme has been proposed; the state space reconstruction is limitedto the turning points and the local nearest neighbor model is modified inorder to predict the turning point magnitudes and times. This approach isextended here using a local dynamic regression model on both turning pointmagnitudes and times. Simulations on oscillating nonlinear systems show thatthe proposed approach gives better predictions of turning points than thestandard local model applied to all the samples of the oscillating time series.



Autor: D. Kugiumtzis, I. Vlachos

Fuente: https://arxiv.org/







Documentos relacionados