Araştırmacılar(20)

• Akar, Funda
• Akgül, İsmail
• Akin, Erhan
• Alici-Karaca, Demet
• Aslan Yıldız, Özge
• Aslay, Fulya
• Atakan, Ahmet
• Aydın, Yıldız
• Baran, Ahmet
• Deniz, Numan
• Doǧan, Tunca
• Han Taş, Mehmet Bilge
• Karakose, Mehmet
• Kaya, Volkan
• Orman, Kamil
• Ozdemir, Durmus
• Ozyer, Gulsah Tumuklu
• Öksüz, Mehmet Kürşat
• Tastimur, Canan
• Yildiz, Eyyup

• ArticleYalnız künye2027/r/ebyu/10689
  Single-image generation using multi-scale vector quantization with autoregressive prior

  Yildiz, Eyyup

  Single-image generative models aim to learn internal statistics of a single training image and synthesize diverse, realistic samples without using large-scale datasets. However, current models rely either on multi-scale generative adversarial network (GAN) pyramids or on diffusion models, both of which require controlling the continuous latent space of the training image. In this paper, we introduce a new single-image generative model that utilizes image-specific discrete latent representation by integrating vector quantization with a coarse-to-fine multi-scale pyramid. Vector quantization serves as a dictionary of high-frequency textural features, ensuring preservation of local textures and fine details that are typically lost in continuous latent space. To generate new image samples, our model trains an autoregressive prior over the quantized token maps, allowing image synthesis to be performed in a quantized latent space rather than directly in pixel space. Extensive quantitative and qualitative experiments on Places50, SIGD, and COCO50 datasets demonstrate that our model consistently achieves competitive performance in image quality, diversity, and computational efficiency, as measured by SIFID, NIQE, NIMA, LPIPS, and MS-SSIM, compared with existing models. We further demonstrate the versatility of our model through various image manipulation tasks, including paint-to-image, harmonization, editing, and outpainting. In conclusion, we show that vector-quantized latent modeling is an effective alternative to GAN- and diffusion-based approaches for high-quality and diverse single-image generation and represents a notable improvement over existing models.

  RDL Kalıcı Kaydıİncele
• ArticleYayıncıda açık erişim2026/r/ebyu/17951
  Multi-Modal Attention-Based Automatic Diagnosis of Bearing Vibration Faults for Robust Mechanical Condition Monitoring

  Tastimur, Canan; Kaya, Volkan

  Bearing components are critical elements of rotating machinery, and their failures can lead to sudden shutdowns, reduced efficiency, and increased maintenance costs. To address the limitations of conventional fault diagnosis methods, this study proposes a multimodal deep learning framework that integrates raw time-domain vibration signals with stationary wavelet transform (SWT)-based time-frequency representations using a novel bidirectional cross-attention mechanism. This architecture enables effective and mutual interaction between heterogeneous features, significantly enhancing discriminative representation learning and fault classification performance in complex operating environments. The proposed model was evaluated on the public SUBVF1.0 dataset under three fault conditions, achieving training and validation accuracies of 99.17% and 95.63%, respectively. The model also demonstrated strong performance in terms of precision, recall, F1-score, and ROC analysis. An ablation study further confirms the contribution of each model component. These results indicate that the proposed approach is accurate, robust, and suitable for practical industrial fault diagnosis applications.

  RDL Kalıcı Kaydıİncele
• ArticleYayıncıda açık erişim2026/r/ebyu/19308
  LandTrendr Algoritması ve Makine Öğrenme Kullanılarak Orman Tahribatı ve İyileşme Süreçlerinin Sınıflandırılması: Milas-Bodrum Örneği

  Taş, Mehmet Akif

  Bu çalışma, zengin orman varlığına rağmen Türkiye'nin yangına en hassas bölgelerinden olan Muğla'nın Milas-Bodrum yöresindeki orman dinamiğini, 2013-2024 periyodu için uzaktan algılama ve makine öğrenmesi yöntemleriyle analiz etmektedir. Analizde, 49 adet Landsat 8 görüntüsünden oluşan zaman serisi verileri kullanılmıştır. Normalize Edilmiş Yanma Oranı (NBR) indeksine dayalı bu veriler, LandTrendr algoritması ile işlenmiş ve ardından Random Forest makine öğrenmesi modeliyle her yıl için "Sağlıklı Orman", "Bozulma" ve "İyileşme" olmak üzere, ekosistemin durumunu yansıtan üç dinamik sınıfa ayrılmıştır. Kantitatif bulgular, 2014-2021 arasında "Bozulma" oranının %24'e gerilediği bir iyileşme döneminin, 2021'deki büyük yangınla dramatik şekilde kesintiye uğradığını ortaya koymuştur. Hem sağlıklı hem de iyileşmekte olan ormanları etkileyen bu olay, "Bozulma" oranını tek bir yılda %47'ye fırlatmış; ancak 2024 itibarıyla "İyileşme" kategorisi tekrar %29'a ulaşarak yeni bir rejenerasyon döngüsünün başladığını teyit etmiştir. Bu çalışma, geleneksel sınıflandırmaların ötesine geçerek, makine öğrenmesi ve zaman serisi analizinin büyük afetlerin ekosistem etkilerini belgelemek ve iyileşme süreçlerini izlemek için sunduğu güçlü metodolojik çerçeveyi ortaya koymaktadır.

  RDL Kalıcı Kaydıİncele
• ArticleYayıncıda açık erişim2026/r/ebyu/19291
  Görüntü Şifrelemede RC4 ve Kaotik RC4 Yöntemlerinin Karşılaştırmalı Performans Analizi

  Akar, Funda; Karhan, Muhammed Baki

  Dijital görüntülerin güvenliği hem bireysel kullanıcılar hem de kurumsal uygulamalar için büyük bir öneme sahiptir. Özellikle görüntülerin şifrelenmesi, veri güvenliğini artırmak ve yetkisiz erişimleri engellemek için etkili bir yöntem olarak kullanılmaktadır. Bu bağlamda, simetrik şifreleme algoritmaları ve kaotik sistemlerin bir arada kullanımı, son yıllarda yoğun ilgi görmüştür. Bu çalışmada, yaygın olarak kullanılan RC4 şifreleme algoritması ile kaotik bir sistem olan Logistic Map tabanlı güçlendirilmiş RC4 yöntemi kullanılarak görüntü şifreleme ve şifre çözme işlemleri gerçekleştirilmiş ve karşılaştırmalı analizler yapılmıştır. Performans değerlendirmesi, histogram analizi, korelasyon analizi ve entropi analizi gibi yöntemlerle gerçekleştirilmiştir. Elde edilen sonuçlar, RC4 algoritmasının, görüntü şifreleme ve şifre çözme süresi kaotik sistemle güçlendirilmiş RC4’e göre daha hızlı bir performans sergilediğini göstermiştir. Ancak, kaotik sistemle güçlendirilmiş RC4 yöntemi, histogram, korelasyon ve entropi analizlerinde daha başarılı bulunmuş ve bu yönüyle daha yüksek bir güvenlik sağladığı görülmüştür.

  RDL Kalıcı Kaydıİncele
• ArticleYalnız künye2026/r/ebyu/11545
  Automated fabric defect inspection with fuzzy c-means, conditional random fields and refined U-Net

  Tastimur, Canan

  In this study, multiple segmentation methods were applied sequentially to enhance the classification for fabric data. First, fuzzy c-means (FCM) segmentation was employed on fabric images, effectively separating in homogeneous regions. Subsequently, these results were refined using conditional random fields (CRF), which provided sharper and more accurate delineation of pixel boundaries. In the final stage, I applied the refined U-Net model to the segmentation results enhanced by CRF, ensuring the preservation of small details in complex and irregularly structured fabric images. In industrial applications such as fabric flaw identification, the distinct contribution of categorizing based on the segmentation results significantly enhanced classification capabilities, particularly in low-quality images. This innovative hybrid strategy serves as an effective technique for improving outcomes, especially in images with uneven textures. Compared to the original dataset, the results are markedly better and pave the way for future advancements in industrial fabric analysis procedures.

  RDL Kalıcı Kaydıİncele
• ArticleAçık Erişim2026/r/ebyu/10780
  A new approach for lung cancer diagnosis: parallel feature learning

  Tastimur, Canan

  Lung cancer, one of the most common types of cancer worldwide, can be fatal. Early diagnosis saves lives. Computed tomography (CT) is used in the diagnosis of the disease. Since the radiology specialist evaluates this X-ray result, the specialist's interpretation can vary. Furthermore, the analysis by the radiologist is both time-consuming and costly. However, a cancer diagnosis approach based on deep learning models supports the radiologist's decision. In this study, a parallel feature learning architecture developed for lung CT images was designed. This architecture focuses on learning different features from each parallel path by using deformable and dilated convolution layers together. Dilated convolution captures semantic features in images with different dilated rates ratios by expanding receptive field, while deformable convolution better captures structural changes. This mechanism allows for more flexible and distinctive feature extraction without significantly increasing computational complexity. The proposed architecture was tested on three different lung cancer datasets: the Public Lung Cancer Dataset, IQ-OTH/NCCD, and LIDC-IDRI. Experimental findings demonstrate robust and consistent classification performance, achieving accuracy rates of 99.44%, 98.75%, and 98.62%, respectively. This shows that the proposed architecture offers a reliable solution for lung cancer diagnosis.

  RDL Kalıcı Kaydıİncele
• ArticleYayıncıda açık erişim2026/r/ebyu/10720
  Double Deep Q-Network-Based Solution for the Dynamic Electric Vehicle Routing Problem

  Taş, Mehmet Bilge Han; Özkan, Kemal; Sarıçiçek, İnci; Yazıcı, Ahmet

  The Dynamic Electric Vehicle Routing Problem (D-EVRP) presents a framework that requires electric vehicles to meet demand with limited energy capacity. When dynamic demand flows and charging requirements are considered together, traditional methods cannot provide sufficient adaptation for real-time decision-making. Therefore, a learning-based approach was chosen to ensure that decision-making processes respond quickly to changing conditions. The solution utilizes a model with a Double Deep Q-Network (DDQN) architecture and a discrete valuation structure. Prioritized Experience Replay (PER) was implemented to increase model stability, allowing infrequent but effective experiments to contribute more to the learning process. The state representation is constructed using the vehicle’s location, battery level, load status, and current customer demands. Scalability is ensured by dividing customer locations into clusters using the K-means method, with each cluster handled by an independent representative. The approach was tested with real-world road data obtained from the Meşelik Campus of Osmangazi University in Eskişehir. Experiments conducted under different demand levels and data sizes have shown that the PER-assisted DDQN structure produces more stable and shorter route lengths in dynamic scenarios, but random selection, greedy method and genetic algorithm experience significant performance losses as dynamicity increases.

  RDL Kalıcı Kaydıİncele
• ArticleYayıncıda açık erişim2026/r/ebyu/10711
  Multiscale Color-R2D2 Features and Alignment-Based Filtering for Reliable Copy–Move Forgery Detection

  Aydın, Yıldız

  This study presents a robust and descriptor-agnostic framework for copy–move forgery detection (CMFD) that combines handcrafted and deep features within a unified geometric refinement stage. The proposed approach integrates a lightweight alignment-based filtering (ABF) mechanism with multiple descriptors to reduce false positives left unresolved by RANSAC. Initially, ABF was evaluated with classical keypoint features Scale-Invariant Feature Descriptor (SIFT), Color-SIFT, and Color-RootSIFT on three benchmark datasets: CoMoFoD (200 images), MICC-F220 (220 images), and GRIP (80 forged + 80 authentic images). Compared with baseline RANSAC-only pipelines on the CoMoFoD dataset, ABF achieved consistent precision gains of 2%–5%, raising F1-scores from 0.811 to 0.834 (SIFT), 0.815 to 0.828 (Color-SIFT), and 0.854 to 0.861 (Color-RootSIFT). On the MICC-F220 dataset, the proposed Color-RootSIFT + ABF configuration reached an F1-score of 0.888, surpassing several recent deep-learning methods (0.84–0.85). To further validate its generality, ABF was combined with a Multiscale Color-R2D2 deep descriptor that extracts LAB-channel features across three scales. This configuration achieved a perfect F1-score of 0.9937 on the GRIP dataset and an F1-score of 0.9149 on the Image Manipulation Dataset (IMD, 48 forged and 48 authentic images). The obtained results are competitive with those of recent deep-learning–based CMFD methods. Moreover, the proposed framework requires no retraining and substantially lower computational resources. These results demonstrate that ABF provides a simple yet powerful geometric verification layer, offering a transparent, computationally efficient, and interpretable alternative to complex deep-learning–based CMFD frameworks.

  RDL Kalıcı Kaydıİncele
• ArticleAçık Erişim2026/r/ebyu/10606
  Explainable AI for accurate diagnosis of papillary thyroid carcinoma via fine-needle aspiration cytopathology

  Kilicarslan, Ahmet; Tastimur, Canan; Gundogdu, Gokhan; Akin, Erhan

  Papillary thyroid carcinoma (PTC) represents most thyroid cancer cases worldwide, making early and accurate diagnosis crucial for successful treatment. This study introduces an explainable AI framework for the automated analysis of fine-needle aspiration (FNA) cytopathology images. By integrating handcrafted features with deep learning-derived abstract features, the proposed model achieves high classification performance (~ 92% accuracy and ~ 96% AUC). The proposed architecture, incorporating multi-scale dilated and deformable convolutions, effectively captures irregularities in cell morphology. Visualizations demonstrate alignment with pathologists’ diagnostic criteria, enhancing the model’s clinical applicability and reliability. The code, dataset, and comprehensive documentation are publicly available via Zenodo (https://zenodo.org/records/18428647), ensuring full reproducibility of the experiments and results presented.

  RDL Kalıcı Kaydıİncele
• ArticleAçık Erişim2026/r/ebyu/10523
  LAViT: Class-Aware Vision Transformer with Learnable Attention for Pest Recognition in Agricultural Fields

  Tastimur, Canan; Kaya, Volkan

  Insect pests pose a significant threat to agricultural productivity, making early and accurate identification essential for effective pest management. This study proposes a novel deep learning-based classification framework for multi-class pest recognition from field images. The proposed approach enhances discriminative region representation by integrating a patch embedding module, a Vision Transformer backbone, and a learnable spatial attention mask. This hybrid design enables the model to focus on critical visual cues without requiring segmentation-based preprocessing. The attention mask, learned via convolutional layers, is pooled and directly applied to Transformer-encoded patch tokens to refine spatial feature emphasis. Positional embeddings are further employed to preserve spatial context within the tokenized image representation. Experimental evaluations conducted on publicly available pest datasets with 5, 9, and 12 classes demonstrate the effectiveness and robustness of the proposed framework. The model achieves accuracies of 99.67%, 99.52%, and 97.00% on the Pest5, Pest9, and Pest12 datasets, respectively, indicating strong generalization across varying classification complexities. To enhance model transparency and reliability, visual interpretability is provided through Grad-CAM and attention heatmap visualizations that reveal the model’s focus regions. Additionally, t-SNE-based feature visualization illustrates clear separability in the learned embedding space. The proposed framework shows strong potential for practical deployment in smart agriculture and precision pest monitoring systems.

  RDL Kalıcı Kaydıİncele