Nonlinear feature extraction based on centroids and kernel functions

被引：21

作者：

Park, CH ^{[1
]}

Park, H ^{[1
]}

机构：

[1] Univ Minnesota, Dept Comp Sci & Engn, Minneapolis, MN 55455 USA

来源：

PATTERN RECOGNITION | 2004年 / 37卷 / 04期

基金：

美国国家科学基金会;

关键词：

cluster structure; dimension reduction; kernel functions; kernel orthogonal centroid method; linear discriminant analysis; nonlinear feature extraction; pattern classification; support vector machines;

D O I：

10.1016/j.patcog.2003.07.011

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A nonlinear feature extraction method is presented which can reduce the data dimension down to the number of classes, providing dramatic savings in computational costs. The dimension reducing nonlinear transformation is obtained by implicitly mapping the input data into a feature space using a kernel function, and then finding a linear mapping based on an orthonormal basis of centroids in the feature space that maximally separates the between-class relationship. The experimental results demonstrate that our method is capable of extracting nonlinear features effectively so that competitive performance of classification can be obtained with linear classifiers in the dimension reduced space. (C) 2003 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

引用

页码：801 / 810

页数：10

共 50 条

[1] Modified kernel-based nonlinear feature extraction
Dai, G
Qian, YT
Jia, S
[J]. 2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL V, PROCEEDINGS: DESIGN AND IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS INDUSTRY TECHNOLOGY TRACKS MACHINE LEARNING FOR SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING SIGNAL PROCESSING FOR EDUCATION, 2004, : 721 - 724
[2] A Subspace Kernel for Nonlinear Feature Extraction
Wu, Mingrui
Farquhar, Jason
[J]. 20TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2007, : 1125 - 1130
[3] An MRF-based kernel method for nonlinear feature extraction
Hsieh, Pi-Fuei
Chou, Po-Wen
Chung, Hsueh-Yi
[J]. IMAGE AND VISION COMPUTING, 2010, 28 (03) : 502 - 517
[4] The nonlinear feature extraction with parsimonious components based on multiple Kernel function
[J]. Liang, S. (lightsun@cqu.edu.cn), 1600, ICIC Express Letters Office, Tokai University, Kumamoto Campus, 9-1-1, Toroku, Kumamoto, 862-8652, Japan (07):
[5] Feature extraction based on kernel UDP
Yang, Wankou
Wang, Jianguo
Ren, Mingwu
Yang, Jingyu
[J]. Journal of Computational Information Systems, 2008, 4 (06): : 2833 - 2840
[6] Image quality assessment method based on nonlinear feature extraction in kernel space
Ding, Yong
Li, Nan
Zhao, Yang
Huang, Kai
[J]. FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING, 2016, 17 (10) : 1008 - 1017
[7] Image quality assessment method based on nonlinear feature extraction in kernel space
Yong Ding
Nan Li
Yang Zhao
Kai Huang
[J]. Frontiers of Information Technology & Electronic Engineering, 2016, 17 : 1008 - 1017
[8] Reformative nonlinear feature extraction using kernel MSE
Zhu, Qi
[J]. NEUROCOMPUTING, 2010, 73 (16-18) : 3334 - 3337
[9] Bilinear analysis for Kernel selection and nonlinear feature extraction
Yang, Shu
Yan, Shuicheng
Zhang, Chao
Tang, Xiaoou
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (05): : 1442 - 1452
[10] Nonlinear feature extraction and classification of multivariate process data in kernel feature space
Cho, Hyun-Woo
[J]. EXPERT SYSTEMS WITH APPLICATIONS, 2007, 32 (02) : 534 - 542

← 1 2 3 4 5 →