Yazar "Cengil, Emine" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Classification of the weather images with the proposed hybrid model using deep learning, SVM classifier, and mRMR feature selection methods
    (2022) Yildirim, Muhammed; Çinar, Ahmet; Cengil, Emine
    As in many fields, the use of artificial intelligence methods in the classification of weather images will be very useful. In this study, a data set consisting of five classes such as cloudy, foggy, rainy, shine, and sunrise was used. A hybrid model has been developed to classify the images in the dataset. First of all, the features of the images in the dataset are obtained by using MobilenetV2, Densenet201, and Efficientnetb0 architectures, which are the most popular Convolutional Neural Network (CNN) architectures. These features are combined and optimized so that these optimized features are classified in the Support Vector Machine (SVM) classifier, one of the most popular classifier methods in machine learning. As a result, the developed hybrid model has outperformed the existing pre-trained architectures in the study. In addition, it has been proven that classification by concatenating the features obtained with CNN architectures is a successful method.
  • Küçük Resim
    Öğe
    COVID-19 Detection on Chest X-ray Images with the Proposed Model Using Artificial Intelligence and Classifiers
    (Springer, 2022) Yıldırım, Muhammed; Eroğlu, Orkun; Eroğlu,Yeşim; Çınar, Ahmet; Cengil, Emine
    Coronavirus disease-2019 (COVID-19) is a serious infectious disease that is spreading rapidly all over the world. Scientists are looking for alternative diagnostic methods to detect and control the disease early. Artifcial intelligence applications are promising in the COVID-19 epidemic. This paper proposes a hybrid approach for diagnosing COVID-19 on chest X-ray images and diferentiation from other viral pneumonia. The model we propose consists of three steps. In the frst step, classifcation was made using the MobilenetV2, Efcientnetb0, and Darknet53 deep models. In the second step, the feature maps of the images in the Chest X-ray data set were extracted separately for each architecture using the MobilenetV2, Efcientnetb0, and Darknet53 architectures. NCA method was preferred to reduce the size of these feature maps obtained. The feature maps obtained after dimension reduction were classifed in the classic machine learning classifers. In the third step, the feature maps obtained from each architecture were combined. After dimension reduction was applied to these combined features by applying the NCA method, this feature map is classifed in the classifers. The model we proposed was tested on two diferent data sets. The accuracy values obtained in these data sets are 99.05 and 97.1%, respectively. The obtained accuracy values show that the model is successful.