Modelling of chaotic systems based on modified weighted recurrent least squares support vector machines |
| |
| Authors: | Sun Jian-Cheng Zhang Tai-Yi and Liu Feng |
| |
| Affiliation: | Department of Information and Communication Eng., Xi'an Jiaotong University, Xi'an 710049, China |
| |
| Abstract: | Positive Lyapunov exponents cause the errors in modelling of the chaotic time series to grow exponentially. In this paper, we propose the modified version of the support vector machines (SVM) to deal with this problem. Based on recurrent least squares support vector machines (RLS-SVM), we introduce a weighted term to the cost function to compensate the prediction errors resulting from the positive global Lyapunov exponents. To demonstrate the effectiveness of our algorithm, we use the power spectrum and dynamic invariants involving the Lyapunov exponents and the correlation dimension as criterions, and then apply our method to the Santa Fe competition time series. The simulation results shows that the proposed method can capture the dynamics of the chaotic time series effectively. |
| |
| Keywords: | chaotic dynamics dynamical invariants support vector machines least squares |
| 本文献已被 维普 等数据库收录！ |
| 点击此处可从《中国物理 B》浏览原始摘要信息 |
|
点击此处可从《中国物理 B》下载免费的PDF全文 |
|
