Yazar "Savas, Serkan" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • [ X ]
    Öğe
    Affecting Factors of Efficiency in Photovoltaic Energy Systems and Productivity-Enhancing Suggestions
    (Institute of Electrical and Electronics Engineers Inc., 2022) Ay, Ilker; Kademli, Murat; Karabulut, Sener; Savas, Serkan
    In recent years, hazardous gases emission from fossil fuels has attracted public concerns due to its worse effects on the ecosystem and living conditions not only mankind but also all creatures living on earth. That's why solar energy has a vital role in alternative energy resources. Solar energy sources will gain more importance in the future. As it is known, the most needed type of energy today is electrical energy. Thus, in this study, the necessary conditions for the photovoltaic (PV) systems used in solar energy production to operate at maximum performance and which parameters are required to control these conditions are examined. The results show that four parameters that we need to measure. These are: maximum operating current of a panel/cell (Impp), maximum operating voltage of a panel/cell (Vmpp), panel surface temperature and light intensity falling on the panel. Except for the panel surface temperature, the rest of the parameters can be measured directly. However, affecting the panel surface temperature; we must not ignore parameters such as ambient temperature, wind speed, humidity and light intensity. Therefore, while determining the panel surface temperature, these parameters should also be measured and a surface temperature should be determined accordingly. © 2022 IEEE.
  • [ X ]
    Öğe
    Enhancing Disease Classification with Deep Learning: a Two-Stage Optimization Approach for Monkeypox and Similar Skin Lesion Diseases
    (Springer, 2024) Savas, Serkan
    Monkeypox (MPox) is an infectious disease caused by the monkeypox virus, presenting challenges in accurate identification due to its resemblance to other diseases. This study introduces a deep learning-based method to distinguish visually similar diseases, specifically MPox, chickenpox, and measles, addressing the 2022 global MPox outbreak. A two-stage optimization approach was presented in the study. By analyzing pre-trained deep neural networks including 71 models, this study optimizes accuracy through transfer learning, fine-tuning, and ensemble learning techniques. ConvNeXtBase, Large, and XLarge models were identified achieving 97.5% accuracy in the first stage. Afterwards, some selection criteria were followed for the models identified in the first stage for use in ensemble learning technique within the optimization approach. The top-performing ensemble model, EM3 (composed of RegNetX160, ResNetRS101, and ResNet101), attains an AUC of 0.9971 in the second stage. Evaluation on unseen data ensures model robustness and enhances the study's overall validity and reliability. The design and implementation of the study have been optimized to address the limitations identified in the literature. This approach offers a rapid and highly accurate decision support system for timely MPox diagnosis, reducing human error, manual processes, and enhancing clinic efficiency. It aids in early MPox detection, addresses diverse disease challenges, and informs imaging device software development. The study's broad implications support global health efforts and showcase artificial intelligence potential in medical informatics for disease identification and diagnosis.
  • [ X ]
    Öğe
    Ensemble learning based lung and colon cancer classification with pre-trained deep neural networks
    (Springer Heidelberg, 2024) Savas, Serkan; Guler, Osman
    PurposeLung and colon cancer are among the most common cancer types with the highest mortality rates worldwide. In recent years, studies have been carried out on the early diagnosis and detection of lung cancer and colon cancer. Also, new treatment methods and options have been investigated. With the development of early diagnostic methods, the survival rate of patients has increased. Therefore, in this study, a transfer learning-based deep ensemble learning model is proposed for the classification of lung and colon cancer from histopathological images.MethodsExperiments were carried out on the LC25000 dataset with the proposed approach. DenseNet121, InceptionV3, MobileNet, ResNet50, ResNet101, VGG16, and Xception models were used for transfer learning. These models were implemented with different variations for ensemble learning.ResultsIt is seen that the most successful transfer learning model is the InceptionV3 model, and the ResNet101 model has the lowest performance. The DETL_V1 model, in which all models were used, was the most successful model with an accuracy rate of 99.78%.ConclusionBy focusing on top models and using ensemble learning to combine their predictions, better performance was obtained compared to any single model on its own. Obtaining a more robust and generalizable model was achieved by combining multiple models that are trained on different subsets of the data with different architectures. The results proved that the proposed approach is supportive for decision in clinical diagnosis processes.
  • [ X ]
    Öğe
    Transfer-learning-based classification of pathological brain magnetic resonance images
    (Wiley, 2024) Savas, Serkan; Damar, Cagri
    Different diseases occur in the brain. For instance, hereditary and progressive diseases affect and degenerate the white matter. Although addressing, diagnosing, and treating complex abnormalities in the brain is challenging, different strategies have been presented with significant advances in medical research. With state-of-art developments in artificial intelligence, new techniques are being applied to brain magnetic resonance images. Deep learning has been recently used for the segmentation and classification of brain images. In this study, we classified normal and pathological brain images using pretrained deep models through transfer learning. The EfficientNet-B5 model reached the highest accuracy of 98.39% on real data, 91.96% on augmented data, and 100% on pathological data. To verify the reliability of the model, fivefold cross-validation and a two-tier cross-test were applied. The results suggest that the proposed method performs reasonably on the classification of brain magnetic resonance images.