Yazar "Unal, Yavuz" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • [ X ]
    Öğe
    Automated seven-stage diabetic retinopathy grading using optimized deep networks through systematic hyperparameter tuning
    (Springer, 2026) Unal, Yavuz
    Diabetes is a systemic disease that can lead to various pathological changes in the eye. One of these changes, diabetic retinopathy, results from damage to the retinal tissue responsible for light perception and image transmission. High blood glucose levels can damage retinal capillaries, as in other vascular structures, thereby impairing visual function. Early detection of diabetic retinopathy is essential for effective treatment. Accurate classification of disease stages directly affects treatment timing and effectiveness, thereby improving prognosis. Early and accurate staging significantly contributes to preventing disease progression, reducing the risk of complications, and preserving patients' quality of life. In this study, a comprehensive deep learning-based approach was developed to classify the seven stages of diabetic retinopathy using fundus images. The proposed methodology integrates CLAHE (Contrast Limited Adaptive Histogram Equalization) preprocessing to enhance image contrast and reveal subtle pathological features, followed by systematic data augmentation to improve dataset diversity and model generalization. The Optuna optimization framework was employed to systematically identify the best-performing pre-trained deep learning architecture, which was determined to be NASNetLarge. Hyperparameter tuning using Grid Search optimization further refined the model configuration, achieving a classification accuracy of 98.39% with 5-fold cross-validation, demonstrating robust performance (98.50 +/- 0.21%). Furthermore, saliency map visualization confirmed that the model focuses on clinically relevant anatomical structures and pathological features, such as microaneurysms, hemorrhages, and vascular abnormalities, thereby enhancing interpretability and trustworthiness for potential clinical deployment. The results demonstrate that the proposed preprocessing, systematic model selection, and hyperparameter optimization techniques significantly improve classification performance and clinical reliability in diabetic retinopathy diagnosis.
  • [ X ]
    Öğe
    Classification of Turkish hazelnut (Corylus colurna L.) varieties: a comparative study of YOLOv8 and fine-tuned vision transformer
    (Springer, 2026) Unal, Yavuz; Yasin, Elham Tahsin; Cengel, Talha Alperen; Koklu, Murat
    Hazelnut is a shrubby plant well-suited to the temperate and humid climate of the Black Sea region, particularly known for its mild winters. Turkey plays a critical role in global hazelnut production. Hazelnuts are not only an essential agricultural product for the country's economy but are also highly valued for their nutritional content, being particularly rich in healthy oils and proteins, and their associated health benefits. The classification of different hazelnut species using modern deep learning techniques aimed to automatically distinguish between eight commonly cultivated hazelnut types: caklidak, damat, devedisi, sivri, karafindik, palaz, tombul, and yagli. This study employed both YOLOv8 classification models and Vision Transformer (ViT) with fine-tuning to classify a dataset comprising 2,722 labeled images of these hazelnut types. Various configurations of YOLOv8 models were tested, specifically YOLOv8n-cls, YOLOv8s-cls, YOLOv8m-cls, YOLOv8l-cls, and YOLOv8x-cls, alongside ViT-Base/16 with systematic fine-tuning optimization. The results demonstrate that the fine-tuned Vision Transformer achieved the highest classification accuracy of 99.75%, establishing a new state-of-the-art performance for this dataset. Among YOLOv8 models, YOLOv8s-cls and YOLOv8l-cls achieved 99.25% accuracy, while the lightest model, YOLOv8n-cls, recorded 97.38% accuracy. The superior performance of ViT-Base/16 (99.75%) represents a significant advancement over previous studies, demonstrating the effectiveness of transformer-based architectures with transfer learning for agricultural image classification. These findings highlight the strong potential for reliable use in real-world agricultural applications, with the Vision Transformer providing near-perfect classification accuracy. This study shows that advanced computer vision, particularly transformer-based models with fine-tuning, can effectively automate the identification and quality control of agricultural products, enhancing efficiency in food processing and supply chains.
  • [ X ]
    Öğe
    Integrating CBAM and Squeeze-and-Excitation Networks for Accurate Grapevine Leaf Disease Diagnosis
    (Wiley, 2025) Unal, Yavuz
    The vine plant holds significant importance beyond grape farming due to its diverse products. Various grape-derived products, such as wine and molasses, highlight the vine plant's role as a valuable agricultural resource. Additionally, traditional cuisines around the world widely utilize grape leaves, contributing to their substantial economic value. However, diseases affecting grape leaves not only harm the plant and its yield but also render the leaves unsuitable for culinary use, leading to considerable economic losses for producers. Detecting diseases on grape leaves is a challenging and time-consuming task when performed manually. Thus, developing a deep learning-based model to automate the classification of grape leaf diseases is of critical importance. This study aims to classify the most common grape leaf diseases grape-scab (grape leaf blister mite) and downy mildew (grapevine downy mildew) alongside healthy leaves using deep learning techniques. Initially, we conducted a basic classification using pre-trained deep learning models. Subsequently, the Convolutional Block Attention Module (CBAM) and Squeeze-and-Excitation Networks (SE) were integrated into the most successful pre-trained classification model to enhance classification performance. As a result, the classification accuracy improved from 92.73% to 96.36%.