An approach for kernel selection based on data distribution

被引：0

作者：

Wang, Wenjian ^{[1
]}

Guo, Jinling ^{[2
]}

Men, Changqian ^{[1
]}

机构：

[1] Shanxi Univ, Inst Syst Engn, Fac Comp & Informat Technol, Taiyuan 030006, Peoples R China

[2] Univ Taiyuan, Dept Informat & Engn Business, Taiyuan, Peoples R China

来源：

ROUGH SETS AND KNOWLEDGE TECHNOLOGY | 2008年 / 5009卷

基金：

中国国家自然科学基金;

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a data based kernel selection approach, which utilizes the geometry distribution of data. Once the approximate distribution can be confirmed as a special one like circle, cirque, sphere cylinder, et al, some known kernel functions corresponding to the special distribution can then be used. Four datasets are used to verify the presented approach, and simulation results demonstrate the rationality and effectiveness of the presented approach.

引用

页码：596 / +

页数：3

共 50 条

[1] A Data Complexity Approach to Kernel Selection for Support Vector Machines
Valerio, Roberto
Vilalta, Ricardo
[J]. PROCEEDINGS OF THE TWENTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2014, : 3138 - 3139
[2] Kernel feature selection with side data using a spectral approach
Shashua, A
Wolf, L
[J]. COMPUTER VISION - ECCV 2004, PT 3, 2004, 3023 : 39 - 53
[3] Robust Gaussian kernel based approach for feature selection
Hsiao, Chih-Ching
Chuang, Chen-Chia
Su, Shun-Feng
[J]. Advances in Intelligent Systems and Computing, 2014, 268 : 25 - 33
[4] Score distribution approach to automatic kernel selection for image retrieval systems
Doloc-Mihu, Anca
Raghavan, Vijay V.
[J]. FOUNDATIONS OF INTELLIGENT SYSTEMS, PROCEEDINGS, 2006, 4203 : 238 - 247
[5] A novel power-based approach to Gaussian kernel selection in the kernel-based association test
Zhan, Xiang
Ghosh, Debashis
[J]. STATISTICAL METHODOLOGY, 2016, 33 : 180 - 191
[6] An Efficient Data Encrypting Approach Based on DBMS Kernel
Duan Guoding
[J]. SOFTWARE ENGINEERING AND KNOWLEDGE ENGINEERING: THEORY AND PRACTICE, VOL 1, 2012, 114 : 1081 - 1088
[7] A new approach to kernel based data analysis algorithms
Mussa, H. Y.
Glen, R. C.
[J]. CHEMISTRY CENTRAL JOURNAL, 2009, 3
[8] A new approach to kernel based data analysis algorithms
HY Mussa
RC Glen
[J]. Chemistry Central Journal, 3
[9] A distribution function based bandwidth selection method for kernel quantile estimation
Faucher, D
Rasmussen, PF
Bobée, B
[J]. JOURNAL OF HYDROLOGY, 2001, 250 (1-4) : 1 - 11
[10] Data based bandwidth selection in kernel density estimation with parametric start via kernel contrasts
Ahmad, IA
Ran, IS
[J]. JOURNAL OF NONPARAMETRIC STATISTICS, 2004, 16 (06) : 841 - 877

← 1 2 3 4 5 →