A Granular Parakeratosis Classification using SVM Hinge and Cross Validation
Now-a-days, a challenging task in the medical field is the diagnosis of skin illness considering numerous characteristics such as color, size, and the lesion region. Dermoscopy is a technique that has been frequently used to diagnose skin lesions. Researchers have recently demonstrated a keen intere...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tamkang University Press
2022-05-01
|
| Series: | Journal of Applied Science and Engineering |
| Subjects: | |
| Online Access: | http://jase.tku.edu.tw/articles/jase-202301-26-1-0004 |
| _version_ | 1811324554867376128 |
|---|---|
| author | Sheetal Janthakal Girisha Hosalli |
| author_facet | Sheetal Janthakal Girisha Hosalli |
| author_sort | Sheetal Janthakal |
| collection | DOAJ |
| description | Now-a-days, a challenging task in the medical field is the diagnosis of skin illness considering numerous characteristics such as color, size, and the lesion region. Dermoscopy is a technique that has been frequently used to diagnose skin lesions. Researchers have recently demonstrated a keen interest in building an automated diagnosis system, and a satisfying result can be achieved with a high degree of skill, as skin lesion classification necessitates a great deal of knowledge and expertise. Automated skin lesion classification in dermoscopy images is an essential way to improve diagnostic performance. This paper presents the power of convolutional neural networks in classifying the skin lesions into two different categories, namely Granular Parakeratosis and Paraneoplastic Pemphigus. The proposed method includes implementation of Support Vector Machine with hinge loss and linear activation function for classification of lesions and this output is fed to the 10-fold cross validation model, yielding an accuracy of 94%, sensitivity of 93%, and specificity of 91%. The proposed strategy outperforms the SVM kernel Radial basis function (RBF), which was created specifically for binary classification problems. |
| first_indexed | 2024-04-13T14:17:40Z |
| format | Article |
| id | doaj.art-7c07ba8032304383973ed21692c4f49b |
| institution | Directory Open Access Journal |
| issn | 2708-9967 2708-9975 |
| language | English |
| last_indexed | 2024-04-13T14:17:40Z |
| publishDate | 2022-05-01 |
| publisher | Tamkang University Press |
| record_format | Article |
| series | Journal of Applied Science and Engineering |
| spelling | doaj.art-7c07ba8032304383973ed21692c4f49b2022-12-22T02:43:37ZengTamkang University PressJournal of Applied Science and Engineering2708-99672708-99752022-05-01261354210.6180/jase.202301_26(1).0004A Granular Parakeratosis Classification using SVM Hinge and Cross ValidationSheetal Janthakal0 Girisha Hosalli1Department of Computer Science and Engineering Rao Bahadur Y. Mahabaleswarappa Engineering College, Bellary, Karnataka, IndiaDepartment of Computer Science and Engineering Rao Bahadur Y. Mahabaleswarappa Engineering College, Bellary, Karnataka, IndiaNow-a-days, a challenging task in the medical field is the diagnosis of skin illness considering numerous characteristics such as color, size, and the lesion region. Dermoscopy is a technique that has been frequently used to diagnose skin lesions. Researchers have recently demonstrated a keen interest in building an automated diagnosis system, and a satisfying result can be achieved with a high degree of skill, as skin lesion classification necessitates a great deal of knowledge and expertise. Automated skin lesion classification in dermoscopy images is an essential way to improve diagnostic performance. This paper presents the power of convolutional neural networks in classifying the skin lesions into two different categories, namely Granular Parakeratosis and Paraneoplastic Pemphigus. The proposed method includes implementation of Support Vector Machine with hinge loss and linear activation function for classification of lesions and this output is fed to the 10-fold cross validation model, yielding an accuracy of 94%, sensitivity of 93%, and specificity of 91%. The proposed strategy outperforms the SVM kernel Radial basis function (RBF), which was created specifically for binary classification problems.http://jase.tku.edu.tw/articles/jase-202301-26-1-000410-fold cross validationconvolutional neural networkshinge losslinear activation functionsupport vector machine |
| spellingShingle | Sheetal Janthakal Girisha Hosalli A Granular Parakeratosis Classification using SVM Hinge and Cross Validation Journal of Applied Science and Engineering 10-fold cross validation convolutional neural networks hinge loss linear activation function support vector machine |
| title | A Granular Parakeratosis Classification using SVM Hinge and Cross Validation |
| title_full | A Granular Parakeratosis Classification using SVM Hinge and Cross Validation |
| title_fullStr | A Granular Parakeratosis Classification using SVM Hinge and Cross Validation |
| title_full_unstemmed | A Granular Parakeratosis Classification using SVM Hinge and Cross Validation |
| title_short | A Granular Parakeratosis Classification using SVM Hinge and Cross Validation |
| title_sort | granular parakeratosis classification using svm hinge and cross validation |
| topic | 10-fold cross validation convolutional neural networks hinge loss linear activation function support vector machine |
| url | http://jase.tku.edu.tw/articles/jase-202301-26-1-0004 |
| work_keys_str_mv | AT sheetaljanthakal agranularparakeratosisclassificationusingsvmhingeandcrossvalidation AT girishahosalli agranularparakeratosisclassificationusingsvmhingeandcrossvalidation AT sheetaljanthakal granularparakeratosisclassificationusingsvmhingeandcrossvalidation AT girishahosalli granularparakeratosisclassificationusingsvmhingeandcrossvalidation |