Robust Statistics for Kernel based NARX Modeling

نویسندگان

  • Jos De Brabanter
  • Kristiaan Pelckmans
  • Johan A.K. Suykens
  • Bart De Moor
  • Joos Vandewalle
چکیده

In this paper we study nonlinear ARX models in relation to a class of kernel based models which make use of kernel induced feature spaces, a methodology which is common in the area of support vector machines (SVMs). Methods are proposed for extending the use of least squares support vector machine (LS-SVM) models towards a robust setting. In order to understand the robustness of these estimators against outliers and non-Gaussian noise, we use the influence functions and maxbias curves. Together with robust versions of LS-SVMs, robust counterparts for the final prediction error criteria are proposed. It is discussed how these robust techniques can be applied to the primal as well as dual representations of LS-SVMs. Examples are given on artificial and real-life data.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A robust least squares fuzzy regression model based on kernel function

In this paper, a new approach is presented to fit arobust fuzzy regression model based on some fuzzy quantities. Inthis approach, we first introduce a new distance between two fuzzynumbers using the kernel function, and then, based on the leastsquares method, the parameters of fuzzy regression model isestimated. The proposed approach has a suitable performance to<b...

متن کامل

Robust Complexity Criteria for Nonlinear Regression in Narx Models

Many different methods have been proposed to construct a smooth regression function, including local polynomial estimators, kernel estimators, smoothing splines and LS-SVM estimators. Each of these estimators use hyperparameters. In this paper a robust version for general cost functions based on the Akaike information criterion is proposed.

متن کامل

Prediction of Above-elbow Motions in Amputees, based on Electromyographic(EMG) Signals, Using Nonlinear Autoregressive Exogenous (NARX) Model

Introduction In order to improve the quality of life of amputees, biomechatronic researchers and biomedical engineers have been trying to use a combination of various techniques to provide suitable rehabilitation systems. Diverse biomedical signals, acquired from a specialized organ or cell system, e.g., the nervous system, are the driving force for the whole system. Electromyography(EMG), as a...

متن کامل

Modeling Identification of the Nonlinear Robot Arm System Using MISO NARX Fuzzy Model and Genetic Algorithm

The PAM robot arm is belonged to highly nonlinear systems where perfect knowledge of their parameters is unattainable by conventional modeling techniques because of the timevarying inertia, hysteresis and other joint friction model uncertainties. To guarantee a good tracking performance, robust-adaptive control approaches combining conventional methods with new learning techniques are required....

متن کامل

Application of a Kernel Method in Modeling Friction Dynamics

A kernel method has been developed to model finite degree, finite memory length and infinite degree, finite memory length Volterra series using polynomial and exponential kernels, respectively. Here, the kernel method is extended to identify NARX (Nonlinear AutoRegressive with eXogenous inputs) models. To verify its effectiveness, the proposed approach is used in modeling friction dynamics, whi...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2004