Background and Purpose: COVID-19, which started in December 2019, caused significant loss of life and economic losses. Early diagnosis of the COVID-19 is important to reduce the risk of death. Therefore, studies have increased to detect COVID-19 with machine learning methods automatically. Materials and Methods: In this study, the dataset consists of 15153 X-ray images for 4961 patient cases in three classes: Viral Pneumonia, Normal and COVID-19. Firstly, the dataset was preprocessed. And then, the dataset was given to the Cubic Support Vector Machine (Cubic SVM), Linear Discriminant (LD), Quadratic Discriminant (QD), Ensemble, Kernel Naive Bayes (KNB), K-Nearest Neighbor Weighted (KNN Weighted) classification methods as input data. Then, the Local Binary Model (LBP) texture operator was applied for feature extraction. Results: These values were increased from 94.1% (without LBP) to 98.05% using the LBP method. The Cubic SVM method's highest accuracy was observed in these two applications. Conclusions: This study demonstrates that the performance of the presented methods with LBP feature extraction is improved.
: Covid-19 local binary pattern feature extraction machine learning classification Covid-19
Birincil Dil | İngilizce |
---|---|
Bölüm | TJST |
Yazarlar | |
Yayımlanma Tarihi | 30 Eylül 2022 |
Gönderilme Tarihi | 24 Mart 2022 |
Yayımlandığı Sayı | Yıl 2022 Cilt: 17 Sayı: 2 |