Extension of First-Order Stable Spline Kernel to Encode Relative DegreeThis work is supported by Grant-in-Aid for JSPS Research Fellow grant number JP15J05700, JSPS KAKENHI grant number JP16H06093, and JSPS KAKENHI grant number JP16K14284

This paper focuses on the kernel-based system identification methods, which estimate the impulse response of the target system in the Bayesian estimation framework. This paper discusses about continuous-time systems, and proposes a new kernel based on a prior that the relative degree of the target s...

Full description

Saved in:
Bibliographic Details
Published inIFAC-PapersOnLine Vol. 50; no. 1; pp. 14016 - 14021
Main Authors Fujimoto, Yusuke, Maruta, Ichiro, Sugie, Toshiharu
Format Journal Article
LanguageEnglish
Published Elsevier Ltd 01.07.2017
Subjects
Bayesian estimation
impulse responses
non-parametric estimation
System identification
Bayesian estimation
System identification
impulse responses
non-parametric estimation
Online AccessGet full text

Cover

More Information
Summary:This paper focuses on the kernel-based system identification methods, which estimate the impulse response of the target system in the Bayesian estimation framework. This paper discusses about continuous-time systems, and proposes a new kernel based on a prior that the relative degree of the target system is higher than or equal to two. Such a prior is identical to a prior on the continuity of the impulse response at time zero. The proposed kernel is an extension of the first-order Stable Spline kernel, which is one of the most famous kernels. Numerical examples are shown to demonstrate the effectiveness of the proposed kernel.
ISSN:2405-8963
2405-8963
DOI:10.1016/j.ifacol.2017.08.2425