Browsing by Author "Uzel, H."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Article
    Citation - Scopus: 1
    Alzheimer’s Classification with a MaxViT-Based Deep Learning Model Using Magnetic Resonance Imaging
    (Interdisciplinary Publishing Academia, 2025) Demirtaş Alpsalaz, S.; Aslan, E.; Özüpak, Y.; Alpsalaz, F.; Uzel, H.
    Alzheimer’s disease (AD), a progressive neurodegenerative disorder, poses significant challenges for early diagnosis due to subtle symptom onset and overlap with normal aging. This study aims to develop an effective deep learning model for classifying four AD stages (Non-Demented, Very Mild Demented, Mild Demented, Moderate Demented) using brain MRI scans. We propose a Multi-Axis Vision Transformer (MaxViT)-based framework, leveraging transfer learning and robust data augmentation on the Kaggle Alzheimer’s MRI Dataset to address class imbalance and enhance generalization. The model employs MaxViT’s multi-axis attention mechanisms to capture both local and global patterns in MRI images. Our approach achieved a classification accuracy of 99.60%, with precision of 99.0%, recall of 98.1%, and F1-score of 98.51%. These results highlight MaxViT’s superior ability to differentiate AD stages, particularly in distinguishing challenging early stages. The proposed model offers a reliable tool for early AD diagnosis, laying a strong foundation for future clinical applications and interdisciplinary research in neurodegenerative disease detection. Future work should explore larger, more diverse datasets and additional biomarkers to further validate and enhance model performance. © 2025 Elsevier B.V., All rights reserved.
  • Thumbnail Image
    Article
    Hybrid Machine Learning Approach for Enhanced Fault Detection and Power Estimation in Photovoltaic Systems
    (John Wiley and Sons Inc, 2026) Alpsalaz, F.; Özüpak, Y.; Aslan, E.; Uzel, H.
    Accurate power prediction and fault detection in photovoltaic (PV) systems are essential for improving energy efficiency and enabling predictive maintenance. This study proposes a novel hybrid regression model based on a stacking ensemble architecture, which integrates multiple machine learning algorithms: histogram-based gradient boosting (HGB), k-nearest neighbors (k-NN), decision tree (DT), random forest (RF), and LightGBM as base learners and employs Ridge regression as the meta-learner. The model was designed to detect complex fault conditions such as partial shading and module-level failures using SCADA-type input features. The performance of the proposed model was evaluated using standard regression metrics (R2, RMSE, MAE), achieving superior results with an R2 of 0.9939, RMSE of 12.0184, and MAE of 8.0544. Paired t-tests confirmed the statistical significance of performance improvements over baseline models (p < 0.05). To ensure transparency, explainability analyses were conducted using SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanations (LIME), which revealed that fault-related features had the greatest influence on model predictions. Comparative evaluation with recent state-of-the-art approaches demonstrated that the proposed hybrid model is scalable, computationally efficient, and robust under varying environmental and operational conditions. The findings suggest that the model can serve as a reliable and interpretable solution for real-time power forecasting and fault detection in PV systems. © 2026 The Author(s). IET Renewable Power Generation published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.