Darıcı, Muazzez Buket

Profile Picture
Name Variants
Muazzez Buket, Darici
D., Muazzez Buket
Darıcı,M.B.
D.,Muazzez Buket
Darıcı, M. B.
Darıcı, M.
Darıcı, Muazzez Buket
DARICI, MUAZZEZ BUKET
Darici,M.B.
Darici,Muazzez Buket
M. B. Darıcı
Darici, Muazzez Buket
Darıcı, MUAZZEZ BUKET
DARICI, Muazzez Buket
M. Darıcı
Muazzez Buket DARICI
Muazzez Buket Darıcı
MUAZZEZ BUKET DARICI
Job Title
Araş. Gör.
Email Address
buket.darici@khas.edu.tr
Main Affiliation
Electrical-Electronics Engineering
Status
Website
ORCID ID
0000-0002-0943-9381
Scopus Author ID
Turkish CoHE Profile ID
Google Scholar ID
WoS Researcher ID
CLJ-7924-2022
Scholarly Output

9

Articles

4

Citation Count

6

Supervised Theses

1

Filters

2021 - 20234
Reset filters

Settings

Type: Article

Scholarly Output Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    Article
    Brain Age Estimation From Mri Images Using 2d-Cnn Instead of 3d-Cnn
    (2021) Gezer, Murat; Darıcı, Muazzez Buket; Yıldırım, Şüheda; Darici, Muazzez Buket
    Human Brain Age has become a popular aging biomarker and is used to detect differences among healthy individuals. Because of the specific changes in the human brain with aging, it is possible to estimate patients’ brain ages from their brain images. Due to developments of the ability of CNN in classification and regression from images, in this study, one of the most popular state of the art models, the DenseNet model, is utilized to estimate human brain ages using transfer learning. Since this process requires high memory load with 3D-CNN, 2D-CNN is preferred for the task of Brain Age Estimation (BAE). In this study, some experiments are carried out to reduce the number of computations while preserving the total performance. With this aim, center slices of each three brain planes are used as the inputs of the DenseNet model, and different optimizers such as Adam, Adamax and Adagrad are used for each model. The dataset is selected from the IXI (Information Extraction from Images) MRI data repository. The MAE evaluation metric is used for each model with different input set to evaluate performance. The best achieved Mean Absolute Error (MAE) is 6.3 with the input set which consisted of center slices of the sagittal plane of brain scan and the Adamax parameter.
  • Thumbnail Image
    Article
    Citation - WoS: 7
    Performance Analysis of Combination of Cnn-Based Models With Adaboost Algorithm To Diagnose Covid-19 Disease
    (Gazi Univ, 2023) Darici, Muazzez Buket; Darıcı, Muazzez Buket
    At the end of 2019, Covid-19, which is a new form of Coronavirus, has spread widely all over the world. With the increasing daily cases of this disease, fast, reliable, and automatic detection systems have been more crucial. Therefore, this study proposes a new technique that combines the machine learning algorithm of Adaboost with Convolutional Neural Networks (CNN) to classify Chest X-Ray images. Basic CNN algorithm and pretrained ResNet-152 have been used separately to obtain features of the Adaboost algorithm from Chest X-Ray images. Several learning rates and the number of estimators have been used to compare these two different feature extraction methods on the Adaboost algorithm. These techniques have been applied to the dataset, which contains Chest X-Ray images labeled as Normal, Viral Pneumonia, and Covid-19. Since the used dataset is unbalanced between classes SMOTE method has been used to make the number of images of classes balance. This study shows that proposed CNN as a feature extractor on the Adaboost algorithm(learning rate of 0.1 and 25 estimators) provides higher classification performance with 94.5% accuracy, 93% precision, 94% recall, and 93% F1-score.
  • Thumbnail Image
    Article
    Citation - WoS: 0
    A Comparative Study on Denoising From Facial Images Using Convolutional Autoencoder
    (Gazi Univ, 2023) Darici, Muazzez Buket; Darıcı, Muazzez Buket; Erdem, Zeki
    Denoising is one of the most important preprocesses in image processing. Noises in images can prevent extracting some important information stored in images. Therefore, before some implementations such as image classification, segmentation, etc., image denoising is a necessity to obtain good results. The purpose of this study is to compare the deep learning techniques and traditional techniques on denoising facial images considering two different types of noise (Gaussian and Salt&Pepper). Gaussian, Median, and Mean filters have been specified as traditional methods. For deep learning methods, deep convolutional denoising autoencoders (CDAE) structured on three different optimizers have been proposed. Both accuracy metrics and computational times have been considered to evaluate the denoising performance of proposed autoencoders, and traditional methods. The utilized standard evaluation metrics are the peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM). It has been observed that overall, while the traditional methods gave results in shorter times in terms of computation times, the autoencoders performed better concerning the evaluation metrics. The CDAE based on the Adam optimizer has been shown the best results in terms of PSNR and SSIM metrics on removing both types of noise.
  • Thumbnail Image
    Article
    Covid-19 Hastalığının Teşhisi için Cnn Tabanlı Modeller ile Adaboost Algoritmasının Kombinasyonunun Performans Analizi
    (2023) Darıcı, Muazzez Buket; Darıcı, Muazzez Buket
    2019 yılı sonunda yeni bir Coronavirüs formu olan Covid-19 tüm dünyada hızlı bir şekilde yayıldı. Bu hastalığın artan günlük vakaları ile hızlı, güvenilir ve otomatik tespit sistemlerine olan ihtiyaç arttı. Bu nedenle, bu çalışma, göğüs kafesi röntgen görüntülerini sınıflandırmak için makine öğrenmesi algoritmalarından biri olan Adaboost algoritması ile Evrişimsel Sinir Ağları’nı (CNN) birleştiren yeni bir teknik önermektedir. Adaboost algoritmasının eğitim için ihtiyaç duyduğu özellikler temel CNN algoritması ve önceden eğitilmiş ResNet-152 ile göğüs kafesi röntgen görüntülerinden ayrı ayrı elde edilmiştir. Adaboost algoritmasında bu iki farklı özellik çıkarma yöntemini karşılaştırmak için farklı öğrenme oranı değerleri ve tahmin sayısı kullanılmıştır. Bu teknikler, Normal, Viral Zatürre ve Covid-19 olarak etiketlenmiş göğüs röntgeni görüntülerini içeren veri setinde uygulanmıştır. Kullanılan veri seti sınıflar arasında dengesiz olduğundan, sınıfların görüntü sayısını dengelemek için SMOTE yöntemi kullanılmıştır. Bu çalışma, Adaboost algoritmasında otomatik özellik çıkarıcı olarak kullanılan, önerilen CNN modelin (öğrenme oranı 0.1 ve tahminci sayısı 25) % 94.5 doğruluk,% 93 kesinlik,% 94 duyarlılık ve % 93 F1 skoru değerleri ile daha yüksek sınıflandırma performansı sağladığını göstermektedir.