Efficient KPCA-based feature extraction: A novel algorithm and experiments

Yong Xu; David Zhang; Jing Yu Yang; Zhong Jing; Miao Li

doi:10.1007/11816515_23

Efficient KPCA-based feature extraction: A novel algorithm and experiments

Yong Xu^*
, David Zhang
, Jing Yu Yang
, Zhong Jing
, Miao Li

^*Corresponding author for this work

Nanjing University of Science and Technology
Harbin Institute of Technology Shenzhen
Hong Kong Polytechnic University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

KPCA has been widely used for feature extraction. It is noticeable that the efficiency of KPCA-based feature extraction is in inverse proportion to the size of the training sample set. In order to speed up KPCA-based feature extraction, we develop a novel algorithm(i.e. IKPCA) which improves KPCA with a distinctive viewpoint. The algorithm is methodologically consistent with KPCA with clear physical meaning. Experiments on several benchmark datasets illustrate that IKPCA-based feature extraction is much faster than KPCA-based feature extraction. The ratio of IKPCA-based feature extraction time to KPCA-based feature extraction time may be smaller than 0.30. Furthermore, the classification accuracy corresponding to IKPCA is comparable with KPCA.

Original language	English
Title of host publication	Intelligent Computing in Signal Processing and Pattern Recognition
Subtitle of host publication	International Conference on Intelligent Computing, ICIC 2006
Editors	De-Shaung Huang, Kang Li, George William Irwin
Pages	220-229
Number of pages	10
DOIs	https://doi.org/10.1007/11816515_23
State	Published - 2006
Externally published	Yes

Publication series

Name	Lecture Notes in Control and Information Sciences
Volume	345
ISSN (Print)	0170-8643

Access to Document

10.1007/11816515_23

Cite this

Xu, Y., Zhang, D., Yang, J. Y., Jing, Z., & Li, M. (2006). Efficient KPCA-based feature extraction: A novel algorithm and experiments. In D.-S. Huang, K. Li, & G. W. Irwin (Eds.), Intelligent Computing in Signal Processing and Pattern Recognition: International Conference on Intelligent Computing, ICIC 2006 (pp. 220-229). (Lecture Notes in Control and Information Sciences; Vol. 345). https://doi.org/10.1007/11816515_23

Xu, Yong ; Zhang, David ; Yang, Jing Yu et al. / Efficient KPCA-based feature extraction : A novel algorithm and experiments. Intelligent Computing in Signal Processing and Pattern Recognition: International Conference on Intelligent Computing, ICIC 2006. editor / De-Shaung Huang ; Kang Li ; George William Irwin. 2006. pp. 220-229 (Lecture Notes in Control and Information Sciences).

@inproceedings{2c29acb8b33d44d2a89b3716a70fbae7,

title = "Efficient KPCA-based feature extraction: A novel algorithm and experiments",

abstract = "KPCA has been widely used for feature extraction. It is noticeable that the efficiency of KPCA-based feature extraction is in inverse proportion to the size of the training sample set. In order to speed up KPCA-based feature extraction, we develop a novel algorithm(i.e. IKPCA) which improves KPCA with a distinctive viewpoint. The algorithm is methodologically consistent with KPCA with clear physical meaning. Experiments on several benchmark datasets illustrate that IKPCA-based feature extraction is much faster than KPCA-based feature extraction. The ratio of IKPCA-based feature extraction time to KPCA-based feature extraction time may be smaller than 0.30. Furthermore, the classification accuracy corresponding to IKPCA is comparable with KPCA.",

author = "Yong Xu and David Zhang and Yang, \{Jing Yu\} and Zhong Jing and Miao Li",

year = "2006",

doi = "10.1007/11816515\_23",

language = "英语",

isbn = "3540372571",

series = "Lecture Notes in Control and Information Sciences",

pages = "220--229",

editor = "De-Shaung Huang and Kang Li and Irwin, \{George William\}",

booktitle = "Intelligent Computing in Signal Processing and Pattern Recognition",

}

Xu, Y, Zhang, D, Yang, JY, Jing, Z & Li, M 2006, Efficient KPCA-based feature extraction: A novel algorithm and experiments. in D-S Huang, K Li & GW Irwin (eds), Intelligent Computing in Signal Processing and Pattern Recognition: International Conference on Intelligent Computing, ICIC 2006. Lecture Notes in Control and Information Sciences, vol. 345, pp. 220-229. https://doi.org/10.1007/11816515_23

Efficient KPCA-based feature extraction: A novel algorithm and experiments. / Xu, Yong; Zhang, David; Yang, Jing Yu et al.
Intelligent Computing in Signal Processing and Pattern Recognition: International Conference on Intelligent Computing, ICIC 2006. ed. / De-Shaung Huang; Kang Li; George William Irwin. 2006. p. 220-229 (Lecture Notes in Control and Information Sciences; Vol. 345).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Efficient KPCA-based feature extraction

T2 - A novel algorithm and experiments

AU - Xu, Yong

AU - Zhang, David

AU - Yang, Jing Yu

AU - Jing, Zhong

AU - Li, Miao

PY - 2006

Y1 - 2006

N2 - KPCA has been widely used for feature extraction. It is noticeable that the efficiency of KPCA-based feature extraction is in inverse proportion to the size of the training sample set. In order to speed up KPCA-based feature extraction, we develop a novel algorithm(i.e. IKPCA) which improves KPCA with a distinctive viewpoint. The algorithm is methodologically consistent with KPCA with clear physical meaning. Experiments on several benchmark datasets illustrate that IKPCA-based feature extraction is much faster than KPCA-based feature extraction. The ratio of IKPCA-based feature extraction time to KPCA-based feature extraction time may be smaller than 0.30. Furthermore, the classification accuracy corresponding to IKPCA is comparable with KPCA.

AB - KPCA has been widely used for feature extraction. It is noticeable that the efficiency of KPCA-based feature extraction is in inverse proportion to the size of the training sample set. In order to speed up KPCA-based feature extraction, we develop a novel algorithm(i.e. IKPCA) which improves KPCA with a distinctive viewpoint. The algorithm is methodologically consistent with KPCA with clear physical meaning. Experiments on several benchmark datasets illustrate that IKPCA-based feature extraction is much faster than KPCA-based feature extraction. The ratio of IKPCA-based feature extraction time to KPCA-based feature extraction time may be smaller than 0.30. Furthermore, the classification accuracy corresponding to IKPCA is comparable with KPCA.

UR - https://www.scopus.com/pages/publications/33748873925

U2 - 10.1007/11816515_23

DO - 10.1007/11816515_23

M3 - 会议稿件

AN - SCOPUS:33748873925

SN - 3540372571

SN - 9783540372578

T3 - Lecture Notes in Control and Information Sciences

SP - 220

EP - 229

BT - Intelligent Computing in Signal Processing and Pattern Recognition

A2 - Huang, De-Shaung

A2 - Li, Kang

A2 - Irwin, George William

ER -

Xu Y, Zhang D, Yang JY, Jing Z, Li M. Efficient KPCA-based feature extraction: A novel algorithm and experiments. In Huang DS, Li K, Irwin GW, editors, Intelligent Computing in Signal Processing and Pattern Recognition: International Conference on Intelligent Computing, ICIC 2006. 2006. p. 220-229. (Lecture Notes in Control and Information Sciences). doi: 10.1007/11816515_23

Efficient KPCA-based feature extraction: A novel algorithm and experiments

Abstract

Publication series

Access to Document

Other files and links

Fingerprint

Cite this