DNA microarray classification using single hidden-layer feedforward networks trained by SVD

Hieu Trung Huynh; Jung Ja Kim; Yonggwan Won

doi:10.1007/978-3-642-10616-3_15

DNA microarray classification using single hidden-layer feedforward networks trained by SVD

Hieu Trung Huynh
, Jung Ja Kim
, Yonggwan Won

Healthcare Information

Chonnam National University

Research output: Contribution to conference › Conference paper › peer-review

Abstract

The development of computational algorithms in analyzing microarray data has attracted many researchers in recent years. Especially statistical and machine learning approaches can provide powerful tools for biomedical research such as gene expression interpretation, classification and prediction for cancer diagnosis, etc. In this paper, we investigate an application of SVD-Neural Classifier for microarray classification. The classifier is a single hidden-layer feedforward neural network (SLFN), of which the activation function of the hidden units is 'tansig'. Its parameters are determined by Singular Value Decomposition (SVD). Experimental results show that the Neural-SVD model is simple, has low computational complexity and can produce better performance with compact network architecture.

Original language	English
Title of host publication	Bio-Science and Bio-Technology - International Conference, BSBT 2009. Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Proceedings
Pages	108-114
Number of pages	7
DOIs	https://doi.org/10.1007/978-3-642-10616-3_15
State	Published - 2009
Event	International Conference on Bio-Science and Bio-Technology, BSBT 2009. Held as Part of the Future Generation Information Technology Conference, FGIT 2009 - Jeju Island, Korea, Republic of Duration: 2009.12.10 → 2009.12.12

Publication series

Name	Communications in Computer and Information Science
Volume	57 CCIS
ISSN (Print)	1865-0929

Conference

Conference	International Conference on Bio-Science and Bio-Technology, BSBT 2009. Held as Part of the Future Generation Information Technology Conference, FGIT 2009
Country/Territory	Korea, Republic of
City	Jeju Island
Period	09.12.10 → 09.12.12

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

classification
DNA microarray
neural network
Singular Value Decomposition
SVD

Quacquarelli Symonds(QS) Subject Topics

Computer Science & Information Systems
Mathematics

Access to Document

10.1007/978-3-642-10616-3_15

Cite this

Huynh, H. T., Kim, J. J., & Won, Y. (2009). DNA microarray classification using single hidden-layer feedforward networks trained by SVD. In Bio-Science and Bio-Technology - International Conference, BSBT 2009. Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Proceedings (pp. 108-114). (Communications in Computer and Information Science; Vol. 57 CCIS). https://doi.org/10.1007/978-3-642-10616-3_15

Huynh, Hieu Trung ; Kim, Jung Ja ; Won, Yonggwan. / DNA microarray classification using single hidden-layer feedforward networks trained by SVD. Bio-Science and Bio-Technology - International Conference, BSBT 2009. Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Proceedings. 2009. pp. 108-114 (Communications in Computer and Information Science).

@inproceedings{4407b7c9399f4d269013354d1c7b7d07,

title = "DNA microarray classification using single hidden-layer feedforward networks trained by SVD",

abstract = "The development of computational algorithms in analyzing microarray data has attracted many researchers in recent years. Especially statistical and machine learning approaches can provide powerful tools for biomedical research such as gene expression interpretation, classification and prediction for cancer diagnosis, etc. In this paper, we investigate an application of SVD-Neural Classifier for microarray classification. The classifier is a single hidden-layer feedforward neural network (SLFN), of which the activation function of the hidden units is 'tansig'. Its parameters are determined by Singular Value Decomposition (SVD). Experimental results show that the Neural-SVD model is simple, has low computational complexity and can produce better performance with compact network architecture.",

keywords = "classification, DNA microarray, neural network, Singular Value Decomposition, SVD",

author = "Huynh, \{Hieu Trung\} and Kim, \{Jung Ja\} and Yonggwan Won",

year = "2009",

doi = "10.1007/978-3-642-10616-3\_15",

language = "English",

isbn = "3642106153",

series = "Communications in Computer and Information Science",

pages = "108--114",

booktitle = "Bio-Science and Bio-Technology - International Conference, BSBT 2009. Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Proceedings",

note = "International Conference on Bio-Science and Bio-Technology, BSBT 2009. Held as Part of the Future Generation Information Technology Conference, FGIT 2009 ; Conference date: 10-12-2009 Through 12-12-2009",

}

Huynh, HT, Kim, JJ & Won, Y 2009, DNA microarray classification using single hidden-layer feedforward networks trained by SVD. in Bio-Science and Bio-Technology - International Conference, BSBT 2009. Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Proceedings. Communications in Computer and Information Science, vol. 57 CCIS, pp. 108-114, International Conference on Bio-Science and Bio-Technology, BSBT 2009. Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Jeju Island, Korea, Republic of, 09.12.10. https://doi.org/10.1007/978-3-642-10616-3_15

DNA microarray classification using single hidden-layer feedforward networks trained by SVD. / Huynh, Hieu Trung; Kim, Jung Ja; Won, Yonggwan.
Bio-Science and Bio-Technology - International Conference, BSBT 2009. Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Proceedings. 2009. p. 108-114 (Communications in Computer and Information Science; Vol. 57 CCIS).

Research output: Contribution to conference › Conference paper › peer-review

TY - GEN

T1 - DNA microarray classification using single hidden-layer feedforward networks trained by SVD

AU - Huynh, Hieu Trung

AU - Kim, Jung Ja

AU - Won, Yonggwan

PY - 2009

Y1 - 2009

N2 - The development of computational algorithms in analyzing microarray data has attracted many researchers in recent years. Especially statistical and machine learning approaches can provide powerful tools for biomedical research such as gene expression interpretation, classification and prediction for cancer diagnosis, etc. In this paper, we investigate an application of SVD-Neural Classifier for microarray classification. The classifier is a single hidden-layer feedforward neural network (SLFN), of which the activation function of the hidden units is 'tansig'. Its parameters are determined by Singular Value Decomposition (SVD). Experimental results show that the Neural-SVD model is simple, has low computational complexity and can produce better performance with compact network architecture.

AB - The development of computational algorithms in analyzing microarray data has attracted many researchers in recent years. Especially statistical and machine learning approaches can provide powerful tools for biomedical research such as gene expression interpretation, classification and prediction for cancer diagnosis, etc. In this paper, we investigate an application of SVD-Neural Classifier for microarray classification. The classifier is a single hidden-layer feedforward neural network (SLFN), of which the activation function of the hidden units is 'tansig'. Its parameters are determined by Singular Value Decomposition (SVD). Experimental results show that the Neural-SVD model is simple, has low computational complexity and can produce better performance with compact network architecture.

KW - classification

KW - DNA microarray

KW - neural network

KW - Singular Value Decomposition

KW - SVD

UR - https://www.scopus.com/pages/publications/78249276866

U2 - 10.1007/978-3-642-10616-3_15

DO - 10.1007/978-3-642-10616-3_15

M3 - Conference paper

AN - SCOPUS:78249276866

SN - 3642106153

SN - 9783642106156

T3 - Communications in Computer and Information Science

SP - 108

EP - 114

BT - Bio-Science and Bio-Technology - International Conference, BSBT 2009. Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Proceedings

T2 - International Conference on Bio-Science and Bio-Technology, BSBT 2009. Held as Part of the Future Generation Information Technology Conference, FGIT 2009

Y2 - 10 December 2009 through 12 December 2009

ER -

Huynh HT, Kim JJ, Won Y. DNA microarray classification using single hidden-layer feedforward networks trained by SVD. In Bio-Science and Bio-Technology - International Conference, BSBT 2009. Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Proceedings. 2009. p. 108-114. (Communications in Computer and Information Science). doi: 10.1007/978-3-642-10616-3_15

DNA microarray classification using single hidden-layer feedforward networks trained by SVD

Abstract

Publication series

Conference

UN SDGs

Keywords

Quacquarelli Symonds(QS) Subject Topics

Access to Document

Other files and links

Fingerprint

Cite this