Repository logoGCRIS

Scopus İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395

Browse

Filters

2022 - 20254

Settings

Subject: search.filters.subject.Convolutional Neural NetworksWoS Q: search.filters.wosQuartile.N/A

Search Results

Now showing 1 - 4 of 4
  • Conference Object
    Citation - Scopus: 4
    Re-Exploring the Kayseri Culture Route by Using Deep Learning for Cultural Heritage Image Classification Cultural Heritage Image Classification by Using Deep Learning: Kayseri Culture Route
    (Association for Computing Machinery, 2024-05-25) Kevseroğlu, Ozlem; Kurban, Rifat
    The categorization of images captured during the documentation of architectural structures is a crucial aspect of preserving cultural heritage in digital form. Dealing with a large volume of images makes this categorization process laborious and time-consuming, often leading to errors. Introducing automatic techniques to aid in sorting would streamline this process, enhancing the efficiency of digital documentation. Proper classification of these images facilitates improved organization and more effective searches using specific terms, thereby aiding in the analysis and interpretation of the heritage asset. This study primarily focuses on applying deep learning techniques, specifically SqueezeNet convolutional neural networks (CNNs), for classifying images of architectural heritage. The effectiveness of training these networks from scratch versus fine-tuning pre-existing models is examined. In this study, we concentrate on identifying significant elements within images of buildings with architectural heritage significance of Kayseri Culture Route. Since no suitable datasets for network training were found, a new dataset was created. Transfer learning enables the use of pre-trained convolutional neural networks to specific image classification tasks. In the experiments, 99.8% of classification accuracy have been achieved by using SqueezeNet, suggesting that the implementation of the technique can substantially enhance the digital documentation of architectural heritage. © 2024 Elsevier B.V., All rights reserved.
  • Conference Object
    Practical Formation Acquisition Mechanism for Nonholonomic Leader-Follower Networks
    (Scitepress, 2022) Kabore, Kader Monhamady; Guler, Samet
    A grand challenge lying ahead of the realization of multi-robot systems is the lack of an adequate coordination mechanism with reliable localization solutions. In some workspaces, external infrastructure needed for precise localization may not be always available to the MRS, e.g., GPS-denied environments, and the robots may need to rely on their onboard resources without explicit communication. We address the practical formation control of nonholonomic ground robots where external localization aids are not available. We propose a systematic framework for the formation maintenance problem that is composed of a localization module and a control module. The onboard localization module relies on heterogeneity in sensing modality comprised of ultrawideband, 2D LIDAR, and camera sensors. Particularly, we apply deep learning-based object detection algorithm to detect the bearing between robots and fuse the outcome with ultrawideband distance measurements for precise relative localization. Integration of the localization outcome into a distributed formation acquisition controller yields high performance. Furthermore, the proposed framework can eliminate the magnetometer sensor which is known to produce unreliable heading readings in some environments. We conduct several realistic simulations and real world experiments whose results validate the competency of the proposed solution.
  • 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, Rifat
    In 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: 1
    A 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, Burcu
    Ultrasonic 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.