Beta
ManageSearchChatDiscover
376696

PNEUMONIA DISEASE DETECTION BY BI-OBJECTIVE SUPPORT VECTOR MACHINE (BO-SVM) ON DEEP FEATURES

Article

Last updated: 29 Dec 2024

OverviewSimilar Items

Subjects

-

Tags

-

Abstract

Abstract—A support vector machine (SVM) learns the decision surface from two different classes of the input points, in many applications there are misclassifications in some of the input points. In this paper a bi-objective quadratic programming model is utilized and different feature quality measures are optimized simultaneously using the weighting method for solving our bi-objective quadratic programming problem. The experimental results, give evidence of the effectiveness of the weighting parameters on reducing the misclassification between two classes of the input points. The main contributions of this paper include constructing a system of a bi-objective support vector machine (BO-SVM) plus deep convolutional neural networks (CNNs)for detection the pneumonia disease using X-ray images.
 

DOI

10.21608/ajmris.2024.376696

Keywords

Keywords—Support vector machine (SVM), Weighting method, Quadratic programming, Deep features, pneumonia

Authors

First Name

Hager Ali

Last Name

Yahia

MiddleName

-

Affiliation

-

Email

-

City

-

Orcid

-

Volume

3

Article Issue

3

Related Issue

50081

Issue Date

2024-08-01

Receive Date

2024-08-28

Publish Date

2024-08-01

Page Start

105

Page End

110

Print ISSN

2974-4318

Online ISSN

2974-4326

Article File

AJMRIS_Volume 3_Issue 3_Pages 105-110.pdf

PDF . 1.0MB

Link

https://ajmris.journals.ekb.eg/article_376696.html

Detail API

https://ajmris.journals.ekb.eg/service?article_code=376696

Order

376,696

Type

Original Article

Type Code

2,816

Publication Type

Journal

Publication Title

Alexandria Journal of Managerial Research and Information Systems

Publication Link

https://ajmris.journals.ekb.eg/

MainTitle

PNEUMONIA DISEASE DETECTION BY BI-OBJECTIVE SUPPORT VECTOR MACHINE (BO-SVM) ON DEEP FEATURES

Details

Type

Article

Created At

20 Dec 2024