Noise Reduction for Chaotic Time Series Based on Singular Entropy
暂无分享,去创建一个
The method is proposed for noise reduction of chaotic time series technique based on singularity spectrum. On the one hand, singularity spectrum has a good performance in the noise reduction for chaotic time series. On the other hand, what determine the order of singularity spectrum have not proposing. If the order selected is too high, full reduction of noise is not achieved. If the order selected is too low, the completeness of signal suffers distortion. So the order selected is a very important in chaotic noise reduction technique based on singularity spectrum. A novel arithmetic based on singularity entropy is introduced in this paper. The increment of singularity Entropy is sensitive with change of the order of singularity spectrum. Finally, experimental results show that the method is quite effective for determining noise reduction order in the field of chaotic time series.
[1] R. Gilmore,et al. Topological analysis and synthesis of chaotic time series , 1992 .
[2] David L. Donoho,et al. De-noising by soft-thresholding , 1995, IEEE Trans. Inf. Theory.
[3] Athanasios Kehagias,et al. Modular neural networks for MAP classification of time series and the partition algorithm , 1996, IEEE Trans. Neural Networks.
[4] R. Vautard,et al. Singular-spectrum analysis: a toolkit for short, noisy chaotic signals , 1992 .