Interval type-2 fuzzy kernel based support vector regression for image denoising

Abstract

In this paper, we focus on the uncertainty associated with the kernel parameter that affects the result values of kernel computation in SVR. To design and manage uncertainty for kernel parameter, we extend a kernel set to interval type-2 fuzzy kernel sets using different kernel parameter which creates uncertainty for the corresponding kernel. Then, we incorporate this interval type-2 fuzzy kernel (IT2FK) into SVR to observe the regression bound by the effect of managing uncertainty from the two different kernel parameters. We also provide some solutions to type-reduction for IT2FK and defuzzification for the IT2FK-based SVR. Several experimental results are given to show the validity of our method.

4 Figures and Tables

Cite this paper

@article{Xu2013IntervalTF, title={Interval type-2 fuzzy kernel based support vector regression for image denoising}, author={Shuqiong Xu and Zhi Liu and Yun Zhang}, journal={Proceedings 2013 International Conference on Mechatronic Sciences, Electric Engineering and Computer (MEC)}, year={2013}, pages={973-977} }