Gümüşhane ÜniversitesiGümüşhane ÜniversitesiAçık Erişim Arşivi · RDL Open

Sürdürülebilir Kalkınma Amaçları

Yazarlar

Yayınlar

Yeniden eskiyeEskiden yeniye
  • BildiriAçık Erişim2026Scopus SJRQ4
    The New Numerical Solutions of the Atangana-Baleanu Fractional Benney Equation

    Alkan, Aslı; Anaç, Halil; Duman, O.; Erkus-Duman, E.

    This study focuses on the novel Atangana-Baleanu method employed to obtain new numerical solutions for the Benney equation with Atangana-Baleanu fractional derivatives. The Atangana-Baleanu q-Elzaki homotopy analysis transform method is used to numerically solve this equation. This paper presents an investigation of the numerical solutions obtained using this technique. Furthermore, the proposed method has been subjected to numerical simulation using Maple software, considering different fractional orders.

    İncele
  • BildiriYalnız künye2026
    Analysis of Temporal Consistency in Video-Based Palmprint ROI Tracking

    Sunnetci, Betul Kosmaz; Bingol, Ozkan; Gedikli, Eyup

    In real-time palmprint recognition systems, operating under unconstrained conditions, maintaining the defined palmprint region of interest (ROI) throughout hand motion presents a significant challenge. Variations in hand position or orientation may cause the ROI to shift unexpectedly or partially or completely disappear, which can adversely affect subsequent processing steps and their computational cost. In this study, the temporal stability and consistency of palmprint ROIs extracted from video data in the MPW-180 dataset were evaluated using two different approaches. Specifically, the behavior of two methods (optical flow based tracking and keypoint-based MediaPipe Hands detection) was quantitatively analyzed over time using corner position shifts and overlap ratios. Experimental results indicate that although the keypointbased method produces spatially accurate ROI estimates, it may exhibit sudden positional jumps in certain frames. In contrast, the optical flow method provides smoother motion transitions but may introduce positional drift over time due to the accumulation of tracking errors.

    İncele
  • BildiriYalnız künye2026Scopus SJRQ4
    Dynamic Analysis of a High-Rise Building Under Near-Fault and Far-Fault Loads Considering Soil-Structure Interaction

    Kaya, Dilek; Cakir, Tufan; Ozturk, Kasif Furkan; Ilki, A.; Goksu, C.; Cinar, T.; Erdik, M.

    Earthquakes that have occurred in our country and various countries around the world over the past 30 years have clearly indicated that the complex relationship between the soil, structure, and earthquake requires further research. This situation has shown that building behavior under dynamic loads can vary depending on parameters such as structural geometry, foundation soil system characteristics, and earthquake characteristics. Due to the fact that near-fault movements contain higher accelerations and higher velocity components compared to far-fault movements, high-rise structures may exhibit relatively more sensitive behavior under such loads and may be negatively affected by these earthquake contents. In this context, the aim of this study is to investigate the dynamic behavior of a 12-story building system under near-fault and far-fault ground motions, taking into account different soil properties. To this end, three-dimensional finite element models were first created for the 12-story building system, considering both fixed and flexible foundation conditions. Modal analyses were performed using finite element models created with ANSYS software, and the obtained mode periods were compared with those obtained from analytical models. Subsequently, the dynamic behavior of the 12-story building system was investigated using relative displacement, stress, and acceleration responses obtained from time-domain analyses conducted for different soil systems and fixed foundation conditions. Comparisons of the dynamic responses showed that the structural dynamic responses could be influenced not only by the soil-structure interaction system but also by nearby and distant fault earthquakes.

    İncele
  • BildiriYalnız künye2026
    Advancing Digital Wallet Security Through Multi-Factor Authentication and Homomorphic Encryption-Based Privacy Preservation

    Genemo, Musa Dima; Kumar, Kotha Anil; Sadat, Quazi Taif; Santosh, Kathari; Sreeram, G.; Raj, I. Infant; Dash, R.; Rautray, R.; Mishra, S.K.

    Digital wallets have been provided by FinTech businesses thus reengineering the financial services but nonetheless there is a possibility of keyloggers, bogus personas and assaults of the server with conventional systems using PIN authentication. The current multi-factor authentication configuration usually leaves sensitive biometric information exposed as the logins are processed. To address these security issues, the paper proposes the MHESecAuth that employs Multi-Factor Homomorphic Encryption and Smart Contracts to authenticate. The permission to make transactions is secure since the system operates with PINs, OTPs and no one can view the biometrics. As per experimental research, the system can be accurate at 96.4 percent, false acceptance rate is 0.08 percent, false rejection rate is 0.6 percent and encryption consumes 160ms. The framework optimizes security, privacy and performance against both MFA, encryption-only and combined solutions and is therefore suitable in the development of quantum-secure digital wallets and still blockchain-based audit and transparency.

    İncele
  • BildiriYalnız künye2025Scopus SJRQ2
    Investigation of antioxidant and antidiabetic activities of propolis obtained from different locations of artvin

    Turan, I.; Gultekin, D. Canbolat; Akmese, O.; Gultekin, E.; Demir, S.; Aliyazicioglu, Y.

    İncele
  • BildiriYalnız künye2025Scopus SJRQ2
    Investigation of antioxidant and antidiabetic activities of different extracts of Vitis labrusca fruit peels

    Güntekin, D. Canbolat; Akmese, O.; Gültekin, E.; Bak, F. Ersen; Özkan, A. I.; Turan, I.; Demir, S.; Aliyazicioglu, Y.

    İncele
  • BildiriYalnız künye2025
    Multi Objective Reinforcement Tuning for Responsible Generative AI in Automated Financial Advisory Systems

    Bhandarkar, Vishakha D; Genemo, Musa Dima; Muda, Iskandar; Murugan, Rekha; Sreeram, G.; Dharani, N.

    Generative AI in a financial context poses risks to the areas of regulatory compliance, accuracy in the content being delivered, and appropriateness in terms of emotion. This research proposes ReFiGen, a framework that can be used to create compliant financial content that is compliant with the regulatory framework and the sentiment of the users. Following domain-specific fine-tuning, ReFiGen blends sentiment alignment with reinforcement learning to optimize on compliance. It demonstrates better performance than baseline models with a high data accuracy rate of 98.35 percent and can generate a fluent output that is emotionally congruent, and regulation-minded. The results of experiments indicate that ReFiGen is both clear and coherent and exactly follows financial guidelines. This practice affirms that the combination of unstructured compliance modeling and affective control is a successful aspect of LLMs. ReFiGen is one of the milestones on the journey of trustworthy and ethically aligned AI in the financial advisory market.

    İncele
  • BildiriYalnız künye2025
    Depth Estimation Based Automatic Pose Correction in Hand Images

    Sünnetci Koşmaz, Betül; Bingöl, Özkan; Gedikli, Eyüp; Ekinci, Murat

    In palm biometric recognition systems, the hand being at different angles and positions relative to the camera presents a critical challenge in terms of accuracy and reliability. Especially in images captured in free environments, hand misalignment can negatively affect recognition performance by making it difficult to extract biometric attributes. Perspective distortions due to camera position change the geometric structure of the hand, compromising biometric data integrity. While 3D imaging systems can offer successful solutions for pose normalization, performing a similar transformation for 2D images poses a major technical challenge. In this study, depth estimation supported plane fitting is used to remove perspective distortions in 2D images and pose normalization of the hand is obtained. The proposed method uses the information obtained from depth estimation to realign the hand image as if it were standing directly in front of the camera, improving geometric consistency. This will make the extraction of biometric features more reliable and contribute to improving the accuracy of palm recognition systems.

    AtıfScopus1OpenAlex1
    İncele
  • BildiriYalnız künye2025
    Improving Skin Lesion Classification with Pretrained Deep Learning Models

    Almasani, Heba; Ture, Hayati

    Skin cancer is the most common type of cancer. Cancer can be defined as a disease characterized by the uncontrolled division and spread of cells. As with other types of cancer, early diagnosis and treatment play a crucial role in combating skin cancer. Since diagnosis is made through visual examination, factors such as the level of expertise and image artifacts negatively affect diagnostic accuracy and slow down the process.Computer-aided applications used to analyze such images provide faster and more accurate results. Additionally, these methods eliminate factors that reduce diagnostic accuracy during the classification and segmentation of skin lesions.This study classifies skin cancer to benign or malignant using deep learning and machine learning methods. In particular, Convolutional Neural Networks (CNNs) have shown promising results in medical image classification. The study evaluates six pre-trained CNN models - VGG16, EfficientNetB7, EfficientNetV2L, DenseNet, ConvNeXtBase and MobileNet - for binary skin lesion classification using the ISIC 2019 dataset. The study first preprocesses and balances the data to enhance performance. The results indicate that the ConvNeXtBase model achieved the highest success with accuracy rate of 84.63% after balancing the data that we have.

    • SDG 3 · Sağlık ve Kaliteli Yaşam
    AtıfScopus5WoS1OpenAlex5
    İncele
  • BildiriYalnız künye2025
    Hybrid CNN-LSTM Framework for Automated Detection of Pediatric Heart Murmurs

    Al-Taib, Asmaa Abduh; Ture, Hayati; Aslan, Muhammed Emin

    This study presents a comprehensive deep learning framework for automated heart murmur detection from phonocardiogram (PCG) signals to address the subjective limitations of cardiac auscultation. Using the CirCor DigiScope dataset of 5,272 pediatric heart sound recordings from 1,568 subjects, we systematically evaluated multiple approaches including traditional machine learning models (Logistic Regression, SVM, KNN, Decision Tree, AdaBoost), basic deep learning architectures (standalone CNN and LSTM), and advanced transfer learning models (DenseNet121, EfficientNet B0/B1/B2, ResNet 50/101, MobileNet V2/V3, GhostNet, AttentionCNN). Our hybrid CNN-LSTM architecture combines mel-spectrogram spatial feature extraction with temporal sequence modeling using 128 traditional audio features and comprehensive preprocessing with data augmentation. The CNN-LSTM model achieved superior performance with 84.6% accuracy, 0.84 F1-score, 0.748 precision, and 0.800 recall, significantly outperforming traditional methods (best SVM: 0.716 F1-score) and advanced architectures (best DenseNet121: 0.72 F1-score), demonstrating robust classification with 0.879 AUC. Results indicate that hybrid deep learning architectures effectively automate cardiac auscultation, providing objective diagnostic tools with potential for improved healthcare accessibility and clinical decision-making.

    • SDG 3 · Sağlık ve Kaliteli Yaşam
    İncele
  • BildiriYalnız künye2025
    Tumor Classification via Subregion Combinations of Cortical L5PC6 Pyramidal Neurons

    Ozcan, Zubeyir; Bozkir, Ilknur Kayikcioglu; Kayikcioglu, Temel

    In this study, it was aimed to classify benign and malignant tumor samples by utilizing different subregions of a cortical L5PC6 pyramidal neuron. A spike-based learning method was applied to a real dataset, and a decision mechanism based on action potential generation was established by training a separate neuron for each class. During the training process, various types of synaptic connections and spike encoding schemes were evaluated and intensity coding yielded the highest performance for the pyramidal neuron. Regional analyses revealed that the basilar region particularly stood out in terms of classification success. The results demonstrate that the morphological and biophysical diversity of pyramidal neurons provides a significant advantage in classification tasks.

    • SDG 3 · Sağlık ve Kaliteli Yaşam
    İncele
  • BildiriAçık Erişim2025
    Comparative Analysis of Vision Foundation Models For Building Segmentation in Aerial Imagery

    Akbulut, Zeynep; Özdemir, Samed; Karslı, Fevzi; Sefercik, U.G.

    Visual Foundation Models (VFMs) demonstrate impressive generalization capabilities for image segmentation and classification tasks, leading to their increasing adoption in the remote sensing field. This study investigates the performance of VFMs in zero-shot building segmentation from aerial imagery using two model pipelines: Grounded-SAM and SAM+CLIP. Grounded-SAM integrates the Grounding DINO backbone with a Segment Anything Model (SAM) while SAM+CLIP first employs SAM for generating masks followed by Contrastive Language Image Pretraining (CLIP) for classification. The evaluation, performed on the WHU building dataset using Precision, Recall, F1 score, and intersection over union (IoU) metrics, revealed that Grounded-SAM achieved F1-score of 0.83 and IoU of 0.71. SAM+CLIP achieved F1-score of 0.65 and IoU of 0.49. While Grounded-SAM excelled at accurately delineating partially occluded and irregularly shaped buildings, SAM+CLIP was able to segment larger buildings but struggled with delineating smaller ones. Given the impressive performance of VFMs in zero-shot building segmentation, future efforts aimed at refining these models through fine-tuning or few-shot learning could significantly expand their application in remote sensing.

    AtıfScopus4WoS4OpenAlex4
    İncele
  • BildiriYalnız künye2025Scopus SJRQ4
    A Novel BPA Derivation Method Using Linguistic Fuzzy Sets in Dempster-Shafer Theory

    Başkan, Elif; Şahin, Rıdvan; Kahraman, C.; Oztaysi, B.; Cebi, S.; Cevik Onar, S.; Tolga, C.; Ucal Sari, I.; Otay, I.

    In this study, we present a new method for developing Basic Probability Assignment (BPA) using Linguistic Fuzzy Sets (LFS). Dempster-Shafer Theory (DST) is used to efficiently combine different data sources. The use of LFS provides a robust structure for managing uncertainty in decision making by representing knowledge in linguistic terms. However, effectively integrating multiple uncertain sources requires a strong probabilistic approach. To overcome this challenge, we propose a method to derive BPA values directly from linguistic terms, ensuring compatibility with the DST fusion rule. We then use the Dempster-Shafer combination rule to combine information from various sources, thereby improving the reliability of the decision-making process.

    İncele
  • BildiriAçık Erişim2024
    Experimental Demonstration of an Optic-DAC Based Transmitter Structure

    Baser, Oguzhan; Küçük, Mehmet Ali; Albayrak, Cenk; Türk, Kadir

    In this paper, an optical-DAC (ODAC) based transmitter design is proposed for indoor visible light communication (VLC) applications. The proposed design is practically realized and the communication performance of the experimental VLC system is investigated. In the ODAC transmitter, multilevel communication signal can be generated optically by independently switching light emitting diode (LED) groups with different powers. In this way, multilevel modulation techniques in VLC systems can be realized through a simple transmitter structure that can be digitally driven. In the proposed transmitter design, unlike the existing ODAC-based VLC transmitters in the literature, metal oxide semiconductor field effect transistors (MOSFET) are used as switching elements in order to drive high-power LED for ambient illumination and communication. In the experimental studies, an offline VLC system using the designed ODAC-based transmitter with a power of approximately 10 W is tested at different switching speeds and distances. The results show that by implementing 8 PAM modulation in the proposed transmitter design, a data transmission rate of 6.264 Mbps is successfully achieved.

    İncele
  • BildiriAçık Erişim2024
    Reconfigurable Optical Filter Based Receiver Structure For Visible Light Communication

    Küçük, Mehmet Ali; Albayrak, Cenk; Türk, Kadir

    In this paper, a novel receiver structure is proposed to mitigate the inter-channel interference (ICI) effects that limit the data rate in multi-color visible light communication (MC-VLC) systems. Reconfigurable optical filters (ROFs) are used at the receiver side of MC-VLC systems to enable the separation of color channels. ROFs are optical elements that have the ability to electrically change their transmission spectrum. Utilizing this feature of ROFs, a receiver structure is developed that, unlike traditional receiver structures, can adaptively adjust the transmit spectrum based on channel state information. This adaptive adjustment is aimed at maximizing communication performance by effectively separating color channels in MC-VLC systems. The obtained results demonstrate that the proposed receiver structure achieves higher communication performance compared to traditional receivers.

    İncele
  • BildiriAçık Erişim2024
    Cross-view Gait Recognition Based on Fine-Tuned Deep Networks

    Yaprak, Busranur; Gedikli, Eyup; Bingöl, Ozkan; Dogan, Ramazan Ozgur

    Gait recognition is a biometrics-based computer vision process used to identify people based on their walking styles. Compared to other types of biometrics, gait offers a more advantageous recognition process as it does not require high-resolution and close-range images and obtains without contact. But besides this, gait biometrics is highly affected by cross-view variation, and under this variation recognition performance decreases significantly. In this study, performance evaluations of fine-tuned VGG-16 and ResNet-50 deep CNN networks on the cross-view gait recognition problem are performed. For this purpose, Gait energy images (GEI) and Silhouettes obtained from CASIA-B, the most comprehensive data set in gait recognition, are given as input to the networks. The experimental results showed that the VGG-16 network achieved higher recognition rates in cross-view gait recognition.

    İncele
  • BildiriAçık Erişim2024
    A Study on the Segmentation and Classification of Diabetic Retinopathy Images Using the K-Means Clustering Method

    Incir, Ramazan; Bozkurt, Ferhat

    Diabetic Retinopathy (DR) is a retinal disease caused by diabetes, representing one of the most prevalent causes of vision loss affecting millions of people worldwide. Swift detection and treatment of this condition are crucial for preventing the disease. Various deep learning and machine learning algorithms have been employed for disease detection and classification, often overlooking the data preprocessing stage. In the data preprocessing phase of this study, segmentation of important lesions, such as hard exudates, was conducted using the K-Means clustering method. The identified lesions were highlighted on the original images. The resulting dataset was then classified using pre-trained architectures, namely EfficientNetV2-M, ResNet50, MobileNet, and DenseNet121. After training on the APTOS dataset, the EfficientNetV2-M model achieved an accuracy of 95.16%. The classification results indicated the contribution of the lesion highlighting process during data preprocessing to the overall classification accuracy.

    • SDG 3 · Sağlık ve Kaliteli Yaşam
    AtıfWoS1OpenAlex3
    İncele
  • BildiriAçık Erişim2024
    In Different Scenarios MobileNet-V1 for Cross-view Gait Recognition

    Yaprak, Busranur; Gedikli, Eyup; Badica, C.; Ivanovic, M.; Koprinkova-Hristova, P.; Leon, F.; Manolopoulos, Y.; Yildirim, T.; Ucar, A.

    Gait recognition aims to identify people from a distance by analyzing their walking style. Nevertheless, the efficacy of recognition drops significantly under cross-view and, appearance-based variations such as carrying and clothing. In this study, the performance of the MobileNet-V1 deep network is evaluated in various scenarios to address the cross-view gait recognition problem. In the first scenario, the fine-tuned MobileNet-V1 is evaluated on Gait Energy Images (GEI) as input data, while in the second scenario, the fine-tuned MobileNet-V1 is assessed with Optical Flows and masked RGB frames input data. In the last scenario, the first two scenarios are combined over a single fused deep network based on finetuned MobileNet-V1, and a single recognition process is performed using two different fused features data; GEI features with Optical Flow features, and GEI features with masked RGB frame features. In the evaluation process, a comprehensive data set for the cross-view gait recognition problem, CASIA-B is used for the experiments. The obtained results demonstrate that in the last scenario, the contribution of masked RGB frame features to the recognition rate of GEI is more significant.

    İncele
  • BildiriAçık Erişim2024
    High-Accuracy Hand Segmentation for Palmprint Biometric Systems Improving Auto-Encoder Techniques

    Yalcin, Kadir; Dogan, Ramazan Ozgur; Dogan, Hulya; Bingol, Ozkan

    Biometric technologies have been widely adopted in various commercial products, ranging from security systems to personal devices, due to their exceptional reliability and user-friendliness. Among these, palmprint biometrics has gained increasing attention for its advantages, such as ease of use, a larger surface area, and the ability to capture more features compared to other biometric methods. A typical palmprint biometric system involves five key stages: (a) Image Acquisition, (b) Hand Segmentation, (c) Pattern Generation, (d) Feature Extraction, and (e) Verification/Identification. The overall success of the system depends on the effectiveness of each stage, with hand segmentation being crucial for identifying the most relevant features for accurate verification. This study aims to achieve high-accuracy biometric recognition by segmenting hands from images captured in uncontrolled environments with complex backgrounds. Accuracy (ACC), Intersection over Union (IoU), F1-Score, and Dice Coefficient are the four critical metrics used to assess the performance of segmentation techniques. The findings demonstrate that the U-Net + ViT and MA-Net + ResNet34 techniques outperform traditional auto-encoder methods in both quantitative performance metrics and visual analysis, leading to significantly improved hand segmentation for biometric systems.

    İncele
  • BildiriAçık Erişim2024
    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.

    AtıfScopus4OpenAlex3
    İncele