Support vector machine-based image classification for genetic syndrome diagnosis

Amit David; Boaz Lerner

doi:10.1016/j.patrec.2004.09.048

Support vector machine-based image classification for genetic syndrome diagnosis

Amit David, Boaz Lerner

Department of Electrical & Computer Engineering

Research output: Contribution to journal › Article › peer-review

40 Scopus citations

Abstract

We implement structural risk minimization and cross-validation in order to optimize kernel and parameters of a support vector machine (SVM) and multiclass SVM-based image classifiers, thereby enabling the diagnosis of genetic abnormalities. By thresholding the distance of patterns from the hypothesis separating the classes we reject a percentage of the miss-classified patterns reducing the expected risk. Accurate performance of the SVM in comparison to other state-of-the-art classifiers demonstrates the benefit of SVM-based genetic syndrome diagnosis.

Original language	English
Pages (from-to)	1029-1038
Number of pages	10
Journal	Pattern Recognition Letters
Volume	26
Issue number	8
DOIs	https://doi.org/10.1016/j.patrec.2004.09.048
State	Published - 1 Jun 2005

Keywords

Fluorescence in situ hybridization (FISH)
Genetics
Multiclass classification by error correcting output code (ECOC)
Rejection
Support vector machine (SVM)

ASJC Scopus subject areas

Software
Signal Processing
Computer Vision and Pattern Recognition
Artificial Intelligence

Access to Document

10.1016/j.patrec.2004.09.048

Cite this

@article{b80afabe39aa4f689a678afe83e58d1f,

title = "Support vector machine-based image classification for genetic syndrome diagnosis",

abstract = "We implement structural risk minimization and cross-validation in order to optimize kernel and parameters of a support vector machine (SVM) and multiclass SVM-based image classifiers, thereby enabling the diagnosis of genetic abnormalities. By thresholding the distance of patterns from the hypothesis separating the classes we reject a percentage of the miss-classified patterns reducing the expected risk. Accurate performance of the SVM in comparison to other state-of-the-art classifiers demonstrates the benefit of SVM-based genetic syndrome diagnosis.",

keywords = "Fluorescence in situ hybridization (FISH), Genetics, Multiclass classification by error correcting output code (ECOC), Rejection, Support vector machine (SVM)",

author = "Amit David and Boaz Lerner",

note = "Funding Information: This work was supported in part by the Paul Ivanier Center for Robotics and Production Management, Ben Gurion University, Beer-Sheva, Israel.",

year = "2005",

month = jun,

day = "1",

doi = "10.1016/j.patrec.2004.09.048",

language = "English",

volume = "26",

pages = "1029--1038",

journal = "Pattern Recognition Letters",

issn = "0167-8655",

publisher = "Elsevier B.V.",

number = "8",

}

TY - JOUR

T1 - Support vector machine-based image classification for genetic syndrome diagnosis

AU - David, Amit

AU - Lerner, Boaz

N1 - Funding Information: This work was supported in part by the Paul Ivanier Center for Robotics and Production Management, Ben Gurion University, Beer-Sheva, Israel.

PY - 2005/6/1

Y1 - 2005/6/1

N2 - We implement structural risk minimization and cross-validation in order to optimize kernel and parameters of a support vector machine (SVM) and multiclass SVM-based image classifiers, thereby enabling the diagnosis of genetic abnormalities. By thresholding the distance of patterns from the hypothesis separating the classes we reject a percentage of the miss-classified patterns reducing the expected risk. Accurate performance of the SVM in comparison to other state-of-the-art classifiers demonstrates the benefit of SVM-based genetic syndrome diagnosis.

AB - We implement structural risk minimization and cross-validation in order to optimize kernel and parameters of a support vector machine (SVM) and multiclass SVM-based image classifiers, thereby enabling the diagnosis of genetic abnormalities. By thresholding the distance of patterns from the hypothesis separating the classes we reject a percentage of the miss-classified patterns reducing the expected risk. Accurate performance of the SVM in comparison to other state-of-the-art classifiers demonstrates the benefit of SVM-based genetic syndrome diagnosis.

KW - Fluorescence in situ hybridization (FISH)

KW - Genetics

KW - Multiclass classification by error correcting output code (ECOC)

KW - Rejection

KW - Support vector machine (SVM)

UR - http://www.scopus.com/inward/record.url?scp=17644374175&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2004.09.048

DO - 10.1016/j.patrec.2004.09.048

M3 - Article

AN - SCOPUS:17644374175

SN - 0167-8655

VL - 26

SP - 1029

EP - 1038

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

IS - 8

ER -

Support vector machine-based image classification for genetic syndrome diagnosis

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this