İlgi alanları

Sürdürülebilir Kalkınma Amaçları

• 1
• 1

• MakaleYalnız künye2026/r/gumushane/13713
  Burned area detection using Sentinel-1 and Sentinel-2 features and analysis of ensemble models with explainable AI

  Günen, Mehmet Akif; Türk, Salih

  Wildfires are serious environmental disasters that threaten ecosystem sustainability, reduce biodiversity, and disrupt the global carbon cycle. This study aimed to improve the accuracy and interpretability of burned area mapping in the Bodrum, Köyceğiz, and Marmaris districts of Muğla province, Türkiye, by integrating multi-sensor satellite data with ensemble machine learning and explainable artificial intelligence (XAI). Sentinel-1 and Sentinel-2 imagery were processed to derive 50 optical and radar-based features, which were classified using four ensemble methods: AdaBoost.M1, Random Forest, GentleBoost, and RUSBoost. The SHapley Additive exPlanations framework was applied to quantify the contribution of each feature and guide feature selection. Results indicated that Sentinel-2 spectral indices, particularly NBR, NBRSWIR, and bands B12 and B8, were the most decisive variables for burned area classification, while Sentinel-1 features contributed less strongly overall but the IVH_ratio variable emerged as the most informative radar-based indicator. Among the classifiers, AdaBoost.M1 achieved the most stable and accurate performance, Random Forest showed strong sensitivity to spectral variability, GentleBoost performed effectively with reduced feature sets, and RUSBoost addressed class imbalance but showed weaker spatial continuity. Importantly, classification accuracy saturated after approximately 15 features, demonstrating that high accuracy can be achieved with fewer inputs and lower computational demand. Moreover, McNemar’s statistical test confirmed that the observed differences among classifiers were significant, highlighting GentleBoost’s clear superiority over other methods. Overall, the integration of optical and radar data with XAI provides a transparent, efficient, and replicable framework for operational burned area monitoring in Mediterranean ecosystems.

  • 
  • 
  İncele
• Derleme MakaleYalnız künye2026/r/gumushane/13408
  A systematic and evolutionary analysis of software design pattern detection and recommendation approaches (2015–2025)

  Turk, Salih; Coskuncay, Ahmet

  Context: Automated detection and recommendation of software design patterns is crucial for software maintenance, reverse engineering, and architectural quality. Despite decades of research, the field has undergone a significant transformation with the emergence of deep learning and large language models (LLMs), leading to a fragmented landscape of methodologies and evaluation settings. Objective: This study aims to provide a systematic and evolutionary synthesis of design pattern detection and recommendation approaches published between 2015 and 2025, categorizing them into distinct technological paradigms and identifying open research challenges. Method: Following Kitchenham’s evidence-based software engineering guidelines and PRISMA principles, a systematic literature review was conducted. We executed a structured search on the Web of Science database, identifying 212 initial records. After rigorous multi-stage screening and quality assessment, 66 primary studies were selected for final synthesis and analysis. Results: The evolution of the field is characterized through six distinct paradigms: Rule-Based, Graph-Based, Feature-Driven Machine Learning, Representation Learning (Deep Learning), Hybrid, and Contextual Intelligence (LLM). Findings reveal a clear methodological shift from structural exactness to semantic and contextual understanding. However, the analysis also identifies a high concentration on specific datasets (JHotDraw and P-MARt) and a lack of standardized benchmarks for variant detection and multi-modal analysis. Conclusions: While LLM-based approaches show promise in handling pattern variants and semantic context, the field requires more diverse benchmarks and explainable models. This review provides a comprehensive research roadmap, emphasizing the need for multi-modal frameworks and industry-scale validation to bridge the gap between academic research and practical software engineering.

  İncele
• MakaleAçık Erişim2025/r/gumushane/14251
  A Video-Based Mobile Palmprint Dataset and an Illumination-Robust Deep Learning Architecture for Unconstrained Environments

  Koşmaz Sünnetci, Betül; Bingöl, Özkan; Gedikli, Eyüp; Ekinci, Murat; Doğan, Ramazan Özgür; Türk, Salih; Güngör, Nihan

  Featured Application: The proposed framework facilitates secure and user-friendly biometric authentication on mobile platforms, particularly in mobile payment and access control scenarios, under unconstrained conditions. The widespread adoption of mobile devices has made secure and user-friendly biometric authentication critical. However, widely used modalities such as fingerprint and facial recognition show limited robustness under uncontrolled illumination and on heterogeneous devices. In contrast, palmprint recognition offers strong potential because of its rich textural patterns and high discriminative power. This study addresses the limitations of laboratory-based datasets that fail to capture real-world challenges. We introduce MPW-180, a novel dataset comprising videos of 180 participants recorded on their own smartphones in everyday environments. By systematically incorporating diverse illumination conditions (with and without flash) and natural free-hand movements, MPW-180 is the first dataset to adopt a bring-your-own-device paradigm, providing a realistic benchmark for evaluating generalization in mobile biometric models. In addition, we propose PalmWildNet, an SE-block-enhanced deep learning architecture trained with Triplet Loss and a cross-illumination sampling strategy. The experimental results show that conventional methods suffer over 50% performance degradation under cross-illumination conditions. In contrast, our method reduces the Equal Error Rate to 1–2% while maintaining an accuracy above 97%. These findings demonstrate that the proposed framework not only tolerates illumination variability but also learns robust illumination-invariant representations, making it well-suited for mobile biometric authentication.

  İncele
• MakaleYalnız künye2025/r/gumushane/13417
  A comparative study of Kolmogorov-Arnold networks and multilayer perceptrons for software defect prediction with SHAP analysis

  Turk, Salih; Coskuncay, Ahmet

  Software defect prediction is essential for enhancing software quality by detecting software errors early in the development lifecycle. This article presents the usage and a detailed evaluation of Kolmogorov-Arnold Networks (KAN) and Multilayer Perceptrons (MLP) over eleven prevalent software defect prediction datasets, namely CM1, JM1, KC1, KC3, MC1, MC2, MW1, PC1, PC3, PC4, and PC5. The defect prediction models were established and evaluated using five principal performance metrics: Accuracy, Precision, Recall, F1 Score, and Area Under the Curve (AUC). The experimental findings indicate that KAN consistently surpasses MLP in all datasets and metrics. KAN attains an average accuracy enhancement of almost 12% compared to MLP and demonstrates substantial improvements in precision and recall, rendering it more dependable in detecting defected modules. The paired t-test findings indicate that the performance disparities between KAN and MLP are statistically significant (p-value< 0.05) for the majority of metrics. Also SHAP analysis was performed to determine the important rankings of features for all datasets according to the FastKAN model. This study underscores the promise of KAN as a superior alternative to traditional neural networks for software defect prediction. The results highlight the significance of the usage of sophisticated neural network topologies in tackling intricate software engineering challenges.

  İncele
• BildiriAçık Erişim2024/r/gumushane/12679
  Super-Resolution Based ROI Enhancement Approaches for Palmprint Recognition; [Avu Izi Tanima I in S per z n rl k Tabanli ROI Iyilestirme Yaklasimlari]

  MacAn, Huseyin Furkan; Bingol, Ozkan; Turk, Salih; Ekinci, Murat

  The sizes of regions of interest (ROI) obtained from images captured by cameras in palmprint recognition may vary depending on the camera specifications and the position of the hand. The regions of interest that recognition systems can use are typically rescaled through interpolation techniques and then defined as inputs to the system. In such cases, there may be some loss of biometric data. This study aims to enhance the quality of the palmprint ROI images, which are critical for palmprint recognition systems. To achieve this, various super-resolution techniques were employed to reconstruct low-resolution ROI images to the target sizes while preserving the distinctiveness of their biometric features. This approach is designed to optimize recognition accuracy and improve data reliability in palmprint recognition processes.

  İncele
• MakaleAçık Erişim2024/r/gumushane/11731
  The impact of implementing backbone architectures on fracture segmentation in X-ray images

  Turk, Salih; Bingol, Ozkan; Coskuncay, Ahmet; Aydin, Tolga

  X-ray imaging is widely utilized for the detection of bone fractures due to its affordability, rapid processing capabilities, broad accessibility, and ease of use. Despite these advantages, the intricate analysis of X-ray images necessitates advanced computational techniques to fully exploit their rich informational content. Notably, accurate segmentation of these images plays a critical role in aiding medical professionals with precise diagnoses and effective treatment planning. This study examines the impact of integrating different backbone architectures for the task of fracture segmentation in X-ray images. Specifically, the research focuses on enhancing the widely-used DeepLabV3 model by incorporating pre-trained networks such as ResNet50, ResNet101, and MobileNetV3 into the encoder component to improve feature extraction and segmentation accuracy. The FracAtlas dataset, which presents unique challenges due to its small size and the diversity of fractures from various anatomical regions, was employed for model evaluation. Data augmentation techniques were implemented to expand the dataset, and an additional subset focusing on cropped images of fracture areas was developed. The models were trained over 50 epochs, and their performance was assessed using metrics such as Intersection over Union (IoU), loss values, and Dice scores. The results indicate that the DeepLabV3 model with ResNet-based backbones achieved IoU values exceeding 0.93 on the original dataset and demonstrated outstanding performance on the augmented and cropped datasets, with AUC values reaching up to 0.99. The study also highlights the computational complexity of the models, with ResNet101 exhibiting the highest time complexity, while MobileNetV3 was the most efficient in terms of processing time and memory consumption.

  İncele
• BildiriYalnız künye2015/r/gumushane/15935
  Detection of Copy-Move Forgery Using DoGCode

  Türk, Salih; Bingöl, Ozkan; Ulutas, Guzin

  Copy-move forgery is performed as a part of an image is copied and moved to another region within the same image. For the detection of this type of forgery, usually, feature vectors of the image are created by dividing the image into sub-blocks. Then the feature vector of the region is compared with other regions in the image to reach a conclusion if they are matched. In this study, to determine the copy-move forgery, DoG Coding technique which is more resistant to changes in image brightness is used. Coded new image is formed with the help of this technique often preferred in the palmprint recognition systems and features are determined by dividing the image into sub-blocks. Block based region growing segmentation method have been developed to determine the size of the copied region. Proposed this new approach has been successfully applied on images in the CoMoFod dataset prepared by different scenarios.

  İncele