Metaheuristic techniques for Support Vector Machine model selection

James Blondin; Ashraf Saad

doi:10.1109/HIS.2010.5600086

Metaheuristic techniques for Support Vector Machine model selection

James Blondin, Ashraf Saad

Electrical & Computer Engineering

Georgia Southern University

Research output: Contribution to book or proceeding › Conference article › peer-review

11 Scopus citations

Abstract

The classification accuracy of a Support Vector Machine is dependent upon the specification of model parameters. The problem of finding these parameters, called the model selection problem, can be very computationally intensive, and is exacerbated by the fact that once selected, these model parameters do not carry across from one dataset to another. This paper describes implementations of both Ant Colony Optimization and Particle Swarm Optimization techniques to the SVM model selection problem. The results of these implementations on some common datasets are compared to each other and to the results of other SVM model selection techniques.

Original language	English
Title of host publication	2010 10th International Conference on Hybrid Intelligent Systems, HIS 2010
Pages	197-200
Number of pages	4
DOIs	https://doi.org/10.1109/HIS.2010.5600086
State	Published - 2010
Event	2010 10th International Conference on Hybrid Intelligent Systems, HIS 2010 - Atlanta, GA, United States Duration: Aug 23 2010 → Aug 25 2010

Publication series

Name	2010 10th International Conference on Hybrid Intelligent Systems, HIS 2010

Conference

Conference	2010 10th International Conference on Hybrid Intelligent Systems, HIS 2010
Country/Territory	United States
City	Atlanta, GA
Period	08/23/10 → 08/25/10

Scopus Subject Areas

Artificial Intelligence
Information Systems

Keywords

Ant colony optimization
Metaheuristics
Particle swarm optimization
Support vector machines

Access to Document

10.1109/HIS.2010.5600086

Cite this

@inproceedings{8c0f788b736246e0afb65849c169599c,

title = "Metaheuristic techniques for Support Vector Machine model selection",

abstract = "The classification accuracy of a Support Vector Machine is dependent upon the specification of model parameters. The problem of finding these parameters, called the model selection problem, can be very computationally intensive, and is exacerbated by the fact that once selected, these model parameters do not carry across from one dataset to another. This paper describes implementations of both Ant Colony Optimization and Particle Swarm Optimization techniques to the SVM model selection problem. The results of these implementations on some common datasets are compared to each other and to the results of other SVM model selection techniques.",

keywords = "Ant colony optimization, Metaheuristics, Particle swarm optimization, Support vector machines",

author = "James Blondin and Ashraf Saad",

year = "2010",

doi = "10.1109/HIS.2010.5600086",

language = "English",

isbn = "9781424473656",

series = "2010 10th International Conference on Hybrid Intelligent Systems, HIS 2010",

pages = "197--200",

booktitle = "2010 10th International Conference on Hybrid Intelligent Systems, HIS 2010",

note = "2010 10th International Conference on Hybrid Intelligent Systems, HIS 2010 ; Conference date: 23-08-2010 Through 25-08-2010",

}

Blondin, J & Saad, A 2010, Metaheuristic techniques for Support Vector Machine model selection. in 2010 10th International Conference on Hybrid Intelligent Systems, HIS 2010., 5600086, 2010 10th International Conference on Hybrid Intelligent Systems, HIS 2010, pp. 197-200, 2010 10th International Conference on Hybrid Intelligent Systems, HIS 2010, Atlanta, GA, United States, 08/23/10. https://doi.org/10.1109/HIS.2010.5600086

TY - GEN

T1 - Metaheuristic techniques for Support Vector Machine model selection

AU - Blondin, James

AU - Saad, Ashraf

PY - 2010

Y1 - 2010

N2 - The classification accuracy of a Support Vector Machine is dependent upon the specification of model parameters. The problem of finding these parameters, called the model selection problem, can be very computationally intensive, and is exacerbated by the fact that once selected, these model parameters do not carry across from one dataset to another. This paper describes implementations of both Ant Colony Optimization and Particle Swarm Optimization techniques to the SVM model selection problem. The results of these implementations on some common datasets are compared to each other and to the results of other SVM model selection techniques.

AB - The classification accuracy of a Support Vector Machine is dependent upon the specification of model parameters. The problem of finding these parameters, called the model selection problem, can be very computationally intensive, and is exacerbated by the fact that once selected, these model parameters do not carry across from one dataset to another. This paper describes implementations of both Ant Colony Optimization and Particle Swarm Optimization techniques to the SVM model selection problem. The results of these implementations on some common datasets are compared to each other and to the results of other SVM model selection techniques.

KW - Ant colony optimization

KW - Metaheuristics

KW - Particle swarm optimization

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=78650166972&partnerID=8YFLogxK

U2 - 10.1109/HIS.2010.5600086

DO - 10.1109/HIS.2010.5600086

M3 - Conference article

AN - SCOPUS:78650166972

SN - 9781424473656

T3 - 2010 10th International Conference on Hybrid Intelligent Systems, HIS 2010

SP - 197

EP - 200

BT - 2010 10th International Conference on Hybrid Intelligent Systems, HIS 2010

T2 - 2010 10th International Conference on Hybrid Intelligent Systems, HIS 2010

Y2 - 23 August 2010 through 25 August 2010

ER -

Metaheuristic techniques for Support Vector Machine model selection

Abstract

Publication series

Conference

Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this