A Method for Detecting Impulsive Noises in Chaotic Time Series

Ken-ichi ITOH  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E79-A   No.10   pp.1670-1675
Publication Date: 1996/10/25
Online ISSN: 
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section on Nonlinear Theory and its Applications (NOLTA))
Category: Sequence, Time Series and Applications
chaos,  impulsive noise,  time series analysis,  prediction,  

Full Text: PDF(430.1KB)>>
Buy this Article

A method is presented for detecting impulsive noises in chaotic time series, based on a new nonlinear prediction algorithm. A multi-dimensional trajectory is reconstructed from a time series using delay coordinates. The future value of a point on the trajectory is predicted using a local approximation technique revised by adding the Biweight estimation method and then the prediction error is calculated. Impulsive noises are detected by examining the prediction errors for all points on the trajectory. The proposed method is applied to the time series of the pupil area and the refractive power of the lens in the human eye. The Lyapunov exponent analysis for thses time series is conducted. As a result, it is shown that the proposed method is effective in detecting impulsive noises caused by blinking in these time series.