On a new class of framelet kernels for support vector regression and regularization networks

Wei-Feng Zhang; Dao-Qing Dai; Hong Yan

doi:10.1007/978-3-540-71701-0_35

On a new class of framelet kernels for support vector regression and regularization networks

Wei-Feng Zhang
, Dao-Qing Dai^*
, Hong Yan

^*Corresponding author for this work

Department of Electrical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

3 Citations (Scopus)

Abstract

Kernel-based machine learning techniques, such as support vector machines, regularization networks, have been widely used in pattern analysis. Kernel function plays an important role in the design of such learning machines. The choice of an appropriate kernel is critical in order to obtain good performance. This paper presents a new class of kernel functions derived from framelet. Framelet is a wavelet frame constructed via multiresolution analysis, and has both the merit of frame and wavelet. The usefulness of the new kernels is demonstrated through simulation experiments. © Springer-Verlag Berlin Heidelberg 2007.

Original language	English
Title of host publication	Advances in Knowledge Discovery and Data Mining
Subtitle of host publication	11th Pacific-Asia Conference, PAKDD 2007, Nanjing, China, May 22-25, 2007, Proceedings
Editors	Zhi-Hua Zhou, Hang Li, Qiang Yang
Place of Publication	Berlin, Heidelberg
Publisher	Springer
Pages	355-366
ISBN (Electronic)	978-3-540-71701-0
ISBN (Print)	9783540717003
DOIs	https://doi.org/10.1007/978-3-540-71701-0_35
Publication status	Published - 2007
Event	11th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2007) - Mandarin Garden Hotel, Nanjing, China Duration: 22 May 2007 → 25 May 2007

Publication series

Name	Lecture Notes in Computer Science
Volume	4426
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	11th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2007)
Place	China
City	Nanjing
Period	22/05/07 → 25/05/07

Access Output

10.1007/978-3-540-71701-0_35

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Zhang, W.-F., Dai, D.-Q., & Yan, H. (2007). On a new class of framelet kernels for support vector regression and regularization networks. In Z.-H. Zhou, H. Li, & Q. Yang (Eds.), Advances in Knowledge Discovery and Data Mining: 11th Pacific-Asia Conference, PAKDD 2007, Nanjing, China, May 22-25, 2007, Proceedings (pp. 355-366). (Lecture Notes in Computer Science; Vol. 4426). Springer . https://doi.org/10.1007/978-3-540-71701-0_35

Zhang, Wei-Feng ; Dai, Dao-Qing ; Yan, Hong. / On a new class of framelet kernels for support vector regression and regularization networks. Advances in Knowledge Discovery and Data Mining: 11th Pacific-Asia Conference, PAKDD 2007, Nanjing, China, May 22-25, 2007, Proceedings. editor / Zhi-Hua Zhou ; Hang Li ; Qiang Yang. Berlin, Heidelberg : Springer , 2007. pp. 355-366 (Lecture Notes in Computer Science).

@inproceedings{c25f61d473bd4b2ca710295d4ebfebd5,

title = "On a new class of framelet kernels for support vector regression and regularization networks",

abstract = "Kernel-based machine learning techniques, such as support vector machines, regularization networks, have been widely used in pattern analysis. Kernel function plays an important role in the design of such learning machines. The choice of an appropriate kernel is critical in order to obtain good performance. This paper presents a new class of kernel functions derived from framelet. Framelet is a wavelet frame constructed via multiresolution analysis, and has both the merit of frame and wavelet. The usefulness of the new kernels is demonstrated through simulation experiments. {\textcopyright} Springer-Verlag Berlin Heidelberg 2007.",

author = "Wei-Feng Zhang and Dao-Qing Dai and Hong Yan",

year = "2007",

doi = "10.1007/978-3-540-71701-0\_35",

language = "English",

isbn = "9783540717003",

series = "Lecture Notes in Computer Science",

publisher = "Springer ",

pages = "355--366",

editor = "Zhou, \{Zhi-Hua \} and Li, \{Hang \} and Yang, \{Qiang \}",

booktitle = "Advances in Knowledge Discovery and Data Mining",

note = "11th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2007) ; Conference date: 22-05-2007 Through 25-05-2007",

}

Zhang, W-F, Dai, D-Q & Yan, H 2007, On a new class of framelet kernels for support vector regression and regularization networks. in Z-H Zhou, H Li & Q Yang (eds), Advances in Knowledge Discovery and Data Mining: 11th Pacific-Asia Conference, PAKDD 2007, Nanjing, China, May 22-25, 2007, Proceedings. Lecture Notes in Computer Science, vol. 4426, Springer , Berlin, Heidelberg, pp. 355-366, 11th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2007), Nanjing, China, 22/05/07. https://doi.org/10.1007/978-3-540-71701-0_35

On a new class of framelet kernels for support vector regression and regularization networks. / Zhang, Wei-Feng; Dai, Dao-Qing; Yan, Hong.
Advances in Knowledge Discovery and Data Mining: 11th Pacific-Asia Conference, PAKDD 2007, Nanjing, China, May 22-25, 2007, Proceedings. ed. / Zhi-Hua Zhou; Hang Li; Qiang Yang. Berlin, Heidelberg: Springer , 2007. p. 355-366 (Lecture Notes in Computer Science; Vol. 4426).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - On a new class of framelet kernels for support vector regression and regularization networks

AU - Zhang, Wei-Feng

AU - Dai, Dao-Qing

AU - Yan, Hong

PY - 2007

Y1 - 2007

N2 - Kernel-based machine learning techniques, such as support vector machines, regularization networks, have been widely used in pattern analysis. Kernel function plays an important role in the design of such learning machines. The choice of an appropriate kernel is critical in order to obtain good performance. This paper presents a new class of kernel functions derived from framelet. Framelet is a wavelet frame constructed via multiresolution analysis, and has both the merit of frame and wavelet. The usefulness of the new kernels is demonstrated through simulation experiments. © Springer-Verlag Berlin Heidelberg 2007.

AB - Kernel-based machine learning techniques, such as support vector machines, regularization networks, have been widely used in pattern analysis. Kernel function plays an important role in the design of such learning machines. The choice of an appropriate kernel is critical in order to obtain good performance. This paper presents a new class of kernel functions derived from framelet. Framelet is a wavelet frame constructed via multiresolution analysis, and has both the merit of frame and wavelet. The usefulness of the new kernels is demonstrated through simulation experiments. © Springer-Verlag Berlin Heidelberg 2007.

UR - https://www.scopus.com/pages/publications/38049125745

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-38049125745&origin=recordpage

U2 - 10.1007/978-3-540-71701-0_35

DO - 10.1007/978-3-540-71701-0_35

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9783540717003

T3 - Lecture Notes in Computer Science

SP - 355

EP - 366

BT - Advances in Knowledge Discovery and Data Mining

A2 - Zhou, Zhi-Hua

A2 - Li, Hang

A2 - Yang, Qiang

PB - Springer

CY - Berlin, Heidelberg

T2 - 11th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2007)

Y2 - 22 May 2007 through 25 May 2007

ER -

Zhang WF, Dai DQ, Yan H. On a new class of framelet kernels for support vector regression and regularization networks. In Zhou ZH, Li H, Yang Q, editors, Advances in Knowledge Discovery and Data Mining: 11th Pacific-Asia Conference, PAKDD 2007, Nanjing, China, May 22-25, 2007, Proceedings. Berlin, Heidelberg: Springer . 2007. p. 355-366. (Lecture Notes in Computer Science). Epub 2007 Jun 21. doi: 10.1007/978-3-540-71701-0_35

On a new class of framelet kernels for support vector regression and regularization networks

Abstract

Publication series

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this