http://dspace.beu.edu.tr:8080/xmlui/handle/123456789/15612 2026-04-23T06:51:36Z http://dspace.beu.edu.tr:8080/xmlui/handle/123456789/16703 THE PLACE OF GENERATIVE ARTIFICIAL INTELLIGENCE IN DIGITAL SECURITY STUDIES AY, Sevinç; KARAKUŞ, Songül Digital security has become critically important today as cyber threats continue to diversify. This study aims to systematically examine the place of generative artificial intelligence in the digital security literature. In this context, documents obtained from a search using the keywords generative artificial intelligence and cybersecurity or information security have been compiled from the Web of Science (WoS) and Scopus databases as of September 3, 2025. As a result of the compilation, 37 duplicate documents were removed, and the remaining 350 papers were analyzed using RStudio, VOSviewer, and Gephi. The research covers themes such as the distribution of academic studies by year, author productivity, collaboration networks, country, institution, resource allocation, keywords, and topics covered. The findings reveal that research in the field increased particularly between 2024 and 2025. According to Lotka's law, author productivity indicates that most authors contribute with a single publication, while a small number of productive authors have played a central role in the development of the field. The keyword analysis demonstrates that generative AI research is developing in two directions, both in the context of health/data privacy and cybersecurity/threat analysis. Finally, a country-bycountry analysis reveals that the USA and India are the leading countries contributing most to the field, while the rate of international collaboration is low. In conclusion, this study demonstrates that generative AI is an important interdisciplinary research theme in digital security and is expected to guide future studies. 2025-01-01T00:00:00Z http://dspace.beu.edu.tr:8080/xmlui/handle/123456789/16702 PERFORMANCE EVALUATION OF DIFFERENT YOLO MODELS FOR LUNG NODULE DETECTION ARUK, İbrahim Lung cancer is one of the leading causes of cancer-related deaths worldwide. The early diagnosis of this disease is critically important for the success of treatment. Computer-aided diagnosis systems and deep learning methods are widely used to ensure accuracy and speed in the automatic detection of lung nodules. In this study, the performance of medium models of four different YOLO architectures (YOLOv8, YOLOv9, YOLOv10, and YOLOv11) in lung nodule detection was comprehensively evaluated on the LUNA16 dataset. The models were compared using metrics such as precision, recall, F1-score, overall accuracy (mAP50, mAP5095), and processing speed. The obtained results have shown that YOLOv8 offers high speed and accuracy, YOLOv10 provides the best sensitivity, and YOLOv11 excels in overall accuracy. To our knowledge, this study presents one of the first comprehensive comparisons of the latest YOLO architectures under fair experimental conditions. By systematically analyzing the relationships between performance metrics, this study fills a gap in the literature. Furthermore, our study demonstrates that deep learning-based YOLO models can be reliable and effective tools for the early diagnosis of lung cancer. The findings obtained are of a nature that will contribute to accurate and rapid diagnostic processes in clinical applications. 2025-01-01T00:00:00Z http://dspace.beu.edu.tr:8080/xmlui/handle/123456789/16701 THE NEW LOCATIONS FOR SOME WASP FAMILIES IN TÜRKİYE KAPLAN, Emin; EFIL, Levent; UZLU, Metehan The present paper is based on the material of the seven families Bembicidae, Crabronidae, Pemphredonidae, Philanthidae, Pompilidae, Sphecidae, and Vespidae collected between 2017 and 2024 in various localities of Bingöl, Çanakkale, and Diyarbakır provinces, Türkiye. In total, 36 species belonging to 26 genera and seven families are recorded: Bembicidae (three genera, four species), Crabronidae (six genera, eight species), Pemphredonidae (two genera, three species), Philanthidae (one genus, one species), Pompilidae (eight genera, 12 species), Sphecidae (five genera, seven species), and Vespidae (one genera, one species). Furthermore, new locality records and distributional data for identified species are provided. 2025-01-01T00:00:00Z http://dspace.beu.edu.tr:8080/xmlui/handle/123456789/16700 DETECTION AND COMPARATIVE ANALYSIS OF MUCILAGE FROM SATELLITE IMAGES USING DEEP LEARNING METHODS ÇUKUR, Yunus Emre; ERDAĞI, Ertürk Mucilage is an environmental problem that threatens biodiversity in marine ecosystems and poses socio-economic risks. In heavily polluted areas like the Marmara Sea, early detection of mucilage is crucial for maintaining ecological balance. Early detection allows policymakers to take swift action. This study utilizes deep learning methods to detect marine mucilage using satellite imagery. The study employed YOLOv7, YOLOv8, YOLOv11, and YOLOv12 models, along with transformer-based RF-DETR and Roboflow 3.0 architectures. A dataset comprising 1113 images from various satellite sources, with mucilage regions marked with bounding boxes, was used. The dataset was expanded using data enhancement techniques. The training process was improved by applying hyperparameters to all models, resulting in performance gains. The performance of the models used in the study was evaluated using precision, recall, mAP@0.5, and mAP@0.5:0.95 metrics. Experimental results show that the YOLOv8 model achieved higher success rates than other methods. Hyperparameter settings were found to significantly impact model performance. Evaluations indicate difficulties in mucilage detection due to lowresolution images and image complexity in coastal areas. This study demonstrates the applicability of artificial intelligence technologies for monitoring environmental problems and provides a decision-support infrastructure for early-warning systems 2025-01-01T00:00:00Z