Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
9 results
Search Results
Article GraphUnet-SS: A Novel Deep Learning Model for Protein Secondary Structure Prediction Based on U-Net Architecture(Elsevier Ltd, 2026-04) Aydin, Zafer; Görmez, Yasin; Sabzekar, MostafaArticle Citation - WoS: 28Citation - Scopus: 31Super Resolution Convolutional Neural Network Based Pre-Processing for Automatic Polyp Detection in Colonoscopy Images(Pergamon-Elsevier Science Ltd, 2021-03) Tas, Merve; Yilmaz, BulentColonoscopy is the most common methodology used to detect polyps on the colon surface. Increasing the image resolution has the potential to improve the automatic colonoscopy based diagnosis and polyp detection and localization. In this study, we proposed a pre-processing approach that uses convolutional neural network based super resolution method (SRCNN) to increase the resolution of the training colonoscopy images before the localization of polyps. We also investigated the use of CNN based models such as the Single Shot MultiBox Detector (SSD) and Faster Regional CNN (RCNN) for real-time polyp detection and localization. Our results showed that using SRCNN method before the training process provides better results in terms of accuracy in both models compared to the low-resolution cases. Furthermore, we reached an F2 score of 0.945 for the correct localization of colon polyps using Faster RCNN with ResNet-101 feature extractor.Article Citation - WoS: 22Citation - Scopus: 29Medical Infrared Thermal Image Based Fatty Liver Classification Using Machine and Deep Learning(Taylor & Francis Ltd, 2023-01-10) Ozdil, Ahmet; Yilmaz, BulentNon-alcoholic fatty liver disease (NAFLD) causes accumulation of excess fat in the liver affecting people who drink little to no alcohol. Non-alcoholic steatohepatitis (NASH) is an aggressive form of fatty liver disease (inflammation in the liver), may progress to cirrhosis and liver failure. Liver function tests, ultrasound (US) and magnetic resonance imaging (MRI) are used to help diagnose and monitor liver disease or damage. In this study, the feasibility of medical infrared thermal imaging (MITI) in automatic detection of NAFLD was investigated, and 167 MITI images (44 positive) from 32 patients (7 positive) were evaluated using image processing and classification methods. Convolutional neural network (CNN) architectures and texture analysis methods were used in the feature selection phase. After feature selection and binary classification, the highest values from different setups for recall, f-score, specificity, accuracy, and area-under-curve (AUC) were 1.00, 1.00, 0.83, 1.0, 0.94, and 0.92, respectively. The highest values were achieved by CNN based methods on different datasets, however, texture analysis method performed lower. Here, it is shown that some of the CNN architectures have high potential on extracting features from thermal images. Finally, machine and deep learning approaches can be combined in detecting NAFLD using infrared thermal images.Article Citation - WoS: 1Citation - Scopus: 1Efficient Relative Localization and Coordination System for Unmanned Ground Vehicle Formations Under Directed Graph Structure(Cambridge Univ Press, 2025-02-24) Kabore, Kader M.; Guler, SametOnboard localization for multi-robot systems stands as a critical area of research with wide-ranging applications. This paper introduces an innovative framework for multi-robot localization, uniquely characterized by its onboard capability, thereby negating the dependency on external infrastructure. Our approach harnesses the inherent capabilities of each robot, enabling them to localize and synchronize their movements independently. The integration of cooperative localization algorithms with formation control mechanisms empowers a group of robots to sustain a predefined formation while following a linear trajectory. The efficacy of our framework is substantiated through comprehensive simulations and real-world experimental validations. We rigorously assess the system's resilience to localization inaccuracies and external disturbances, demonstrating its adaptability and consistency in maintaining formation under diverse conditions. Furthermore, we explore the scalability of our approach, highlighting its potential to manage varying numbers of robots and its applicability in tasks such as collaborative transportation.Article Citation - WoS: 14Citation - Scopus: 15Comparative Analysis of Dimensionality Reduction Techniques for Cybersecurity in the SwaT Dataset(Springer, 2023-07-08) Bozdal, Mehmet; Ileri, Kadir; Ozkahraman, AliThe Internet of Things (IoT) has revolutionized the functionality and efficiency of distributed cyber-physical systems, such as city-wide water treatment systems. However, the increased connectivity also exposes these systems to cybersecurity threats. This research presents a novel approach for securing the Secure Water Treatment (SWaT) dataset using a 1D Convolutional Neural Network (CNN) model enhanced with a Gated Recurrent Unit (GRU). The proposed method outperforms existing methods by achieving 99.68% accuracy and an F1 score of 98.69%. Additionally, the paper explores dimensionality reduction methods, including Autoencoders, Generalized Eigenvalue Decomposition (GED), and Principal Component Analysis (PCA). The research findings highlight the importance of balancing dimensionality reduction with the need for accurate intrusion detection. It is found that PCA provided better performance compared to the other techniques, as reducing the input dimension by 90.2% resulted in only a 2.8% and 2.6% decrease in the accuracy and F1 score, respectively. This study contributes to the field by addressing the critical need for robust cybersecurity measures in IoT-enabled water treatment systems, while also considering the practical trade-off between dimensionality reduction and intrusion detection accuracy.Article Citation - WoS: 4Citation - Scopus: 4Camera-Based Wildfire Smoke Detection for Foggy Environments(SPIE - Society of Photo-Optical Instrumentation Engineers, 2022-10-27) Tas, Merve; Tas, Yusuf; Balki, Oguzhan; Aydin, Zafer; Tasdemir, Kasim; Aydln, ZaferSmoke is the first visible sign of forest fires and the most commonly used feature for early forest fire detection using data from cameras. However, one of the natural challenges is the dense fog that appears in forests, which decreases the detection accuracy or triggers false alarms. In this study, we propose a system with a deep neural network-based image preprocessing approach that significantly improves the smoke segmentation and classification performance by dehazing the camera view. Our experimental results provide that the classification models reach 99% F1 score for the correct classification of smoke when the image dehazing method is used before the training process. The smoke localization system achieves 60% average precision when the mask region-based convolutional neural network is used with the ResNet101-FPN backbone. The proposed approach can be utilized for all smoke segmentation frameworks to increase fire detection performance. (c) 2022 SPIE and IS&TArticle Citation - Scopus: 10Building a Challenging Medical Dataset for Comparative Evaluation of Classifier Capabilities(Elsevier Ltd, 2024-08) Bozkurt, Berat; Coskun, Kerem; Bakal, GokhanSince the 2000s, digitalization has been a crucial transformation in our lives. Nevertheless, digitalization brings a bulk of unstructured textual data to be processed, including articles, clinical records, web pages, and shared social media posts. As a critical analysis, the classification task classifies the given textual entities into correct categories. Categorizing documents from different domains is straightforward since the instances are unlikely to contain similar contexts. However, document classification in a single domain is more complicated due to sharing the same context. Thus, we aim to classify medical articles about four common cancer types (Leukemia, Non-Hodgkin Lymphoma, Bladder Cancer, and Thyroid Cancer) by constructing machine learning and deep learning models. We used 383,914 medical articles about four common cancer types collected by the PubMed API. To build classification models, we split the dataset into 70% as training, 20% as testing, and 10% as validation. We built widely used machine-learning (Logistic Regression, XGBoost, CatBoost, and Random Forest Classifiers) and modern deep-learning (convolutional neural networks - CNN, long short-term memory - LSTM, and gated recurrent unit - GRU) models. We computed the average classification performances (precision, recall, F-score) to evaluate the models over ten distinct dataset splits. The best-performing deep learning model(s) yielded a superior F1 score of 98%. However, traditional machine learning models also achieved reasonably high F1 scores, 95% for the worst-performing case. Ultimately, we constructed multiple models to classify articles, which compose a hard-to-classify dataset in the medical domain. © 2024 Elsevier B.V., All rights reserved.Conference Object Benchmarking CNN Architectures for Eye Disease Detection With Transfer Learning Techniques(Institute of Electrical and Electronics Engineers Inc., 2025-06-27) Keles, Tolgahan; Aykanat, Muhammet Ali; Kurban, RifatIn this study, convolutional neural networks (CNN)-based approaches were compared to classify eye diseases using transfer learning techniques. A series of data augmentation strategies, including random rotation, shifting, shearing, zooming, and horizontal flipping, were applied to increase the training data's robustness and diversity. Several state-of-the-art CNNs, including ResNet50, VGG19, EfficientNetB0, Xception, InceptionV3, DenseNet121, MobileNetV2, NASNetMobile, and ConvNeXtBase, were fine-tuned through transfer learning. During training, models were evaluated based on their accuracy, training time, and validation performance, while early stopping mechanisms were employed to prevent overfitting. Experimental results demonstrated that DenseNet121 achieved the highest validation accuracy (72%) during the training phase and the best test set performance with an accuracy of 68% and an AUC-ROC of 0.93. MobileNetV2, on the other hand, provided a strong balance between classification accuracy (65%) and low inference time (7.28 ms), making it appropriate for real-time uses. The findings highlight the importance of selecting appropriate architectures by considering both predictive performance and computational efficiency, particularly in the context of medical imaging, where real-world deployment constraints are critical. © 2025 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 1A Federated Learning Framework for Classifying the Images in Ultrasonic Nondestructive Testing(Institute of Electrical and Electronics Engineers Inc., 2024-10-26) Gulsen, Abdulkadir; Hacilar, Hilal; Kolukisa, Burak; Bakir-Güngör, BurcuUltrasonic inspection is a critical technique in non-destructive testing that ensures the safety and integrity of the material by detecting internal defects. Defect classification within this context is vital for preventing failures and extending the lifespan of materials. However, the advancement of ultrasonic testing technology is hindered by a scarcity of publicly available, realistic datasets, which are essential for developing accurate models. To address these challenges, this paper introduces a Federated Learning (FL) framework employing a Convolutional Neural Network (CNN) model for defect classification using ultrasonic inspection images. This innovative approach allows for the decentralized training of models on private datasets without the need for data exchange, thus preserving data privacy. Our comparative analysis demonstrates that the FL achieves performance comparable to traditional methods while maintaining the confidentiality of sensitive information. The framework also proves to be robust and scalable with an increase in the number of participating clients. This pioneering study highlights the potential of FL in transforming ultrasonic defect classification and suggests possibilities for its application in other areas of non-destructive testing where publicly available datasets are scarce. These findings would encourage researchers to develop a federated platform for enhanced collaboration and explore advanced CNN architectures to improve training efficiency. © 2025 Elsevier B.V., All rights reserved.