Reduced set support vector machines

Application for 2-dimensional datasets

Aini Hussain, S. Shahbudin, Hafizah Husain, Salina Abdul Samad, N. Md Tahir

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

This paper presents the performance of the Reduced Set (RS) method to approximate the decision boundary for standard Support Vector Machines (SVM) classifier without affecting its generalization performance. The main focus of this work is to demonstrate the capability of the RS method such that even with fewer set of vectors, the generalization performance is not affected. In evaluating the RS method performance, decision boundaries obtained using RS method were benchmarked against the decision boundaries obtained from the standard SVM using Sequential Minimal Optimization (SMO) method. Specifically, the generalization ability of the two methods is not evaluated since the main objective is to analyze the effect of reduced set vector in producing approximation of SVM decision rules. Results obtained demonstrated that the SVM classifier using RS method is comparable with the standard SVM using SMO method. In fact, the RS method is better since it uses fewer set of vectors to produce similar decision boundaries while maintaining the generalization performances.

Original languageEnglish
Title of host publication2nd International Conference on Signal Processing and Communication Systems, ICSPCS 2008 - Proceedings
DOIs
Publication statusPublished - 2008
Event2nd International Conference on Signal Processing and Communication Systems, ICSPCS 2008 - Gold Coast, QLD
Duration: 15 Dec 200817 Dec 2008

Other

Other2nd International Conference on Signal Processing and Communication Systems, ICSPCS 2008
CityGold Coast, QLD
Period15/12/0817/12/08

Fingerprint

Support vector machines
Classifiers
performance
ability

Keywords

  • 2-dimensional (2D) dataset
  • Decision boundaries
  • Number of support vectors
  • Reduced Set (RS) Method

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Computer Networks and Communications
  • Communication

Cite this

Hussain, A., Shahbudin, S., Husain, H., Abdul Samad, S., & Tahir, N. M. (2008). Reduced set support vector machines: Application for 2-dimensional datasets. In 2nd International Conference on Signal Processing and Communication Systems, ICSPCS 2008 - Proceedings [4813667] https://doi.org/10.1109/ICSPCS.2008.4813667

Reduced set support vector machines : Application for 2-dimensional datasets. / Hussain, Aini; Shahbudin, S.; Husain, Hafizah; Abdul Samad, Salina; Tahir, N. Md.

2nd International Conference on Signal Processing and Communication Systems, ICSPCS 2008 - Proceedings. 2008. 4813667.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hussain, A, Shahbudin, S, Husain, H, Abdul Samad, S & Tahir, NM 2008, Reduced set support vector machines: Application for 2-dimensional datasets. in 2nd International Conference on Signal Processing and Communication Systems, ICSPCS 2008 - Proceedings., 4813667, 2nd International Conference on Signal Processing and Communication Systems, ICSPCS 2008, Gold Coast, QLD, 15/12/08. https://doi.org/10.1109/ICSPCS.2008.4813667
Hussain A, Shahbudin S, Husain H, Abdul Samad S, Tahir NM. Reduced set support vector machines: Application for 2-dimensional datasets. In 2nd International Conference on Signal Processing and Communication Systems, ICSPCS 2008 - Proceedings. 2008. 4813667 https://doi.org/10.1109/ICSPCS.2008.4813667
Hussain, Aini ; Shahbudin, S. ; Husain, Hafizah ; Abdul Samad, Salina ; Tahir, N. Md. / Reduced set support vector machines : Application for 2-dimensional datasets. 2nd International Conference on Signal Processing and Communication Systems, ICSPCS 2008 - Proceedings. 2008.
@inproceedings{3112102272f6429d8f3884ff6680be7d,
title = "Reduced set support vector machines: Application for 2-dimensional datasets",
abstract = "This paper presents the performance of the Reduced Set (RS) method to approximate the decision boundary for standard Support Vector Machines (SVM) classifier without affecting its generalization performance. The main focus of this work is to demonstrate the capability of the RS method such that even with fewer set of vectors, the generalization performance is not affected. In evaluating the RS method performance, decision boundaries obtained using RS method were benchmarked against the decision boundaries obtained from the standard SVM using Sequential Minimal Optimization (SMO) method. Specifically, the generalization ability of the two methods is not evaluated since the main objective is to analyze the effect of reduced set vector in producing approximation of SVM decision rules. Results obtained demonstrated that the SVM classifier using RS method is comparable with the standard SVM using SMO method. In fact, the RS method is better since it uses fewer set of vectors to produce similar decision boundaries while maintaining the generalization performances.",
keywords = "2-dimensional (2D) dataset, Decision boundaries, Number of support vectors, Reduced Set (RS) Method",
author = "Aini Hussain and S. Shahbudin and Hafizah Husain and {Abdul Samad}, Salina and Tahir, {N. Md}",
year = "2008",
doi = "10.1109/ICSPCS.2008.4813667",
language = "English",
isbn = "9781424442423",
booktitle = "2nd International Conference on Signal Processing and Communication Systems, ICSPCS 2008 - Proceedings",

}

TY - GEN

T1 - Reduced set support vector machines

T2 - Application for 2-dimensional datasets

AU - Hussain, Aini

AU - Shahbudin, S.

AU - Husain, Hafizah

AU - Abdul Samad, Salina

AU - Tahir, N. Md

PY - 2008

Y1 - 2008

N2 - This paper presents the performance of the Reduced Set (RS) method to approximate the decision boundary for standard Support Vector Machines (SVM) classifier without affecting its generalization performance. The main focus of this work is to demonstrate the capability of the RS method such that even with fewer set of vectors, the generalization performance is not affected. In evaluating the RS method performance, decision boundaries obtained using RS method were benchmarked against the decision boundaries obtained from the standard SVM using Sequential Minimal Optimization (SMO) method. Specifically, the generalization ability of the two methods is not evaluated since the main objective is to analyze the effect of reduced set vector in producing approximation of SVM decision rules. Results obtained demonstrated that the SVM classifier using RS method is comparable with the standard SVM using SMO method. In fact, the RS method is better since it uses fewer set of vectors to produce similar decision boundaries while maintaining the generalization performances.

AB - This paper presents the performance of the Reduced Set (RS) method to approximate the decision boundary for standard Support Vector Machines (SVM) classifier without affecting its generalization performance. The main focus of this work is to demonstrate the capability of the RS method such that even with fewer set of vectors, the generalization performance is not affected. In evaluating the RS method performance, decision boundaries obtained using RS method were benchmarked against the decision boundaries obtained from the standard SVM using Sequential Minimal Optimization (SMO) method. Specifically, the generalization ability of the two methods is not evaluated since the main objective is to analyze the effect of reduced set vector in producing approximation of SVM decision rules. Results obtained demonstrated that the SVM classifier using RS method is comparable with the standard SVM using SMO method. In fact, the RS method is better since it uses fewer set of vectors to produce similar decision boundaries while maintaining the generalization performances.

KW - 2-dimensional (2D) dataset

KW - Decision boundaries

KW - Number of support vectors

KW - Reduced Set (RS) Method

UR - http://www.scopus.com/inward/record.url?scp=67649635112&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67649635112&partnerID=8YFLogxK

U2 - 10.1109/ICSPCS.2008.4813667

DO - 10.1109/ICSPCS.2008.4813667

M3 - Conference contribution

SN - 9781424442423

BT - 2nd International Conference on Signal Processing and Communication Systems, ICSPCS 2008 - Proceedings

ER -