A New Classification Approach Based On Support Vector Regression For Epileptic Seizure Detection

Esra Betül Kınacı; Hasan Bal; Harun Kınacı

Article Details

A New Classification Approach Based On Support Vector Regression For Epileptic Seizure Detection

Authors:

Esra Betül Kınacı | Hasan Bal | Harun Kınacı

Publisher:

Gazi University

Main Topics:

Mühendislik

Journal:

Politeknik Dergisi Vol.27 Issue 2, pp.587-601

Document Type:

Article

Publication Date:

3/2024

Document Language:

Turkish

Document ID (Org No.):

2001314270

pISSN:

2147-9429

Keywords:

Abstract:

 Although the classification problem is a subject that has been studied by researchers for a long time, it is still up-to-date. Especially the problems that image processing and diagnosis of disease are some of the most current application topics. This study presents a new data classification method based on support vector regression and mathematical programming. The proposed method consists of a two-stage hybrid structure. In the first step, the classification score is obtained for each unit with the support vector regression equation. In the second stage, using the classification scores of the units, a classification rule is created with the help of a mathematical model and the classification of the units is provided. The proposed method offers an alternative innovation to traditional methods. Methods based on traditional mathematical programming separate classes with a linear function. This situation limits the use of algorithms based on mathematical programming. The proposed method can be used in all linear or non-linearly separable data structures, as well as easily transforming into problem types with more than two groups. The model is applied to the classification problem of Electroencephalograph EEG signals and the classification performance is compared with the existing methods. The results obtained are given in the tables and it is shown that the proposed model can be an alternative to the existing algorithms.

 Although the classification problem is a subject that has been studied by researchers for a long time, it is still up-to-date. Especially the problems that image processing and diagnosis of disease are some of the most current application topics. This study presents a new data classification method based on support vector regression and mathematical programming. The proposed method consists of a two-stage hybrid structure. In the first step, the classification score is obtained for each unit with the support vector regression equation. In the second stage, using the classification scores of the units, a classification rule is created with the help of a mathematical model and the classification of the units is provided. The proposed method offers an alternative innovation to traditional methods. Methods based on traditional mathematical programming separate classes with a linear function. This situation limits the use of algorithms based on mathematical programming. The proposed method can be used in all linear or non-linearly separable data structures, as well as easily transforming into problem types with more than two groups. The model is applied to the classification problem of Electroencephalograph EEG signals and the classification performance is compared with the existing methods. The results obtained are given in the tables and it is shown that the proposed model can be an alternative to the existing algorithms.

 Although the classification problem is a subject that has been studied by researchers for a long time, it is still up-to-date. Especially the problems that image processing and diagnosis of disease are some of the most current application topics. This study presents a new data classification method based on support vector regression and mathematical programming. The proposed method consists of a two-stage hybrid structure. In the first step, the classification score is obtained for each unit with the support vector regression equation. In the second stage, using the classification scores of the units, a classification rule is created with the help of a mathematical model and the classification of the units is provided. The proposed method offers an alternative innovation to traditional methods. Methods based on traditional mathematical programming separate classes with a linear function. This situation limits the use of algorithms based on mathematical programming. The proposed method can be used in all linear or non-linearly separable data structures, as well as easily transforming into problem types with more than two groups. The model is applied to the classification problem of Electroencephalograph EEG signals and the classification performance is compared with the existing methods. The results obtained are given in the tables and it is shown that the proposed model can be an alternative to the existing algorithms.

 Although the classification problem is a subject that has been studied by researchers for a long time, it is still up-to-date. Especially the problems that image processing and diagnosis of disease are some of the most current application topics. This study presents a new data classification method based on support vector regression and mathematical programming. The proposed method consists of a two-stage hybrid structure. In the first step, the classification score is obtained for each unit with the support vector regression equation. In the second stage, using the classification scores of the units, a classification rule is created with the help of a mathematical model and the classification of the units is provided. The proposed method offers an alternative innovation to traditional methods. Methods based on traditional mathematical programming separate classes with a linear function. This situation limits the use of algorithms based on mathematical programming. The proposed method can be used in all linear or non-linearly separable data structures, as well as easily transforming into problem types with more than two groups. The model is applied to the classification problem of Electroencephalograph EEG signals and the classification performance is compared with the existing methods. The results obtained are given in the tables and it is shown that the proposed model can be an alternative to the existing algorithms.

Article Details

A New Classification Approach Based On Support Vector Regression For Epileptic Seizure Detection

Authors:

Esra Betül Kınacı | Hasan Bal | Harun Kınacı

Publisher:

Gazi University

Main Topics:

Mühendislik

Journal:

Politeknik Dergisi Vol.27 Issue 2, pp.587-601

Document Type:

Article

Publication Date:

3/2024

Document Language:

Turkish

Document ID (Org No.):

2001314270

pISSN:

2147-9429

Support Vector Machines

Support Vector Regression

Classification

Bonn DatasetDestek Vektör Makineleri

Destek Vektör Regresyon

Sınıflandırma

Bonn Veri Seti

Issues

Article Details

Authors: Esra Betül Kınacı | Hasan Bal | Harun Kınacı

Publisher: Gazi University

Main Topics: Mühendislik

Journal: Politeknik Dergisi Vol.27 Issue 2, pp.587-601

Document Type: Article

Publication Date: 3/2024

Document Language: Turkish

Document ID (Org No.): 2001314270

pISSN: 2147-9429

Issues

Authors:

Esra Betül Kınacı | Hasan Bal | Harun Kınacı

Publisher:

Gazi University

Main Topics:

Mühendislik

Journal:

Politeknik Dergisi Vol.27 Issue 2, pp.587-601

Document Type:

Article

Publication Date:

3/2024

Document Language:

Turkish

Document ID (Org No.):

2001314270

pISSN:

2147-9429