Yazar "Yalcin, Sercan" seçeneğine göre listele

Listeleniyor 1 - 5 / 5
  • Küçük Resim Yok
    Öğe
    Advanced convolutional neural network modeling for fuel cell system optimization and efficiency in methane, methanol, and diesel reforming
    (Peerj Inc, 2024) Yalcin, Sercan; Yildirim, Muhammed; Alatas, Bilal
    Fuel cell systems (FCSs) have been widely used for niche applications in the market. Furthermore, the research community has worked on using FCSs for different sectors, such as transportation, stationary power generation, marine and maritime, aerospace, military and defense, telecommunications, and material handling. The reformation of various fuels, such as methanol, methane, and diesel can be utilized to generate hydrogen for FCSs. This study introduces an advanced convolutional neural network (CNN) model designed to accurately forecast hydrogen yield and carbon monoxide volume percentages during the reformation processes of methane, methanol, and diesel. Moreover, the CNN model has been tailored to accurately estimate methane conversion rates in methane reforming processes. The proposed CNN models are created by combining the 3D-CNN and 2D-CNN models. The Keras Tuner approach in Python is employed in this study to find the ideal values for different hyperparameters such as batch size, learning rate, time steps, and optimization method selection. The accuracy of the proposed CNN model is evaluated by using the root mean square error (RMSE), mean absolute percentage error (MAE), mean absolute error (MAE), and R2. The results indicate that the proposed CNN model is better than other artificial intelligence (AI) techniques and standard CNN for performance estimation of reforming processes of methane, diesel, and methanol. The results also show that the suggested CNN model can be used to accurately estimate critical output parameters for reforming various fuels. The proposed method performs better in CO prediction than the support vector machine (SVM), with an R2 of 0.9989 against 0.9827. This novel methodology not only improves performance estimation for reforming processes but also provides a valuable tool for accurately estimating output parameters across various fuel types.
  • Küçük Resim Yok
    Öğe
    Automatic Diagnosis, Classification, and Segmentation of Abdominal Aortic Aneurysm and Dissection from Computed Tomography Images
    (Mdpi, 2025) Baltaci, Hakan; Yalcin, Sercan; Yildirim, Muhammed; Bingol, Harun
    Background/Objectives: Diagnosis of abdominal aortic aneurysm and abdominal aortic dissection (AAA and AAD) is of strategic importance as cardiovascular disease has fatal implications worldwide. This study presents a novel deep learning-based approach for the accurate and efficient diagnosis of abdominal aortic aneurysms (AAAs) and aortic dissections (AADs) from CT images. Methods: Our proposed convolutional neural network (CNN) architecture effectively extracts relevant features from CT scans and classifies regions as normal or diseased. Additionally, the model accurately delineates the boundaries of detected aneurysms and dissections, aiding in clinical decision-making. A pyramid scene parsing network has been built in a hybrid method. The layer block after the classification layer is divided into two groups: whether there is an AAA or AAD region in the abdominal CT image, and determination of the borders of the detected diseased region in the medical image. Results: In this sense, both detection and segmentation are performed in AAA and AAD diseases. Python programming has been used to assess the accuracy and performance results of the proposed strategy. From the results, average accuracy rates of 83.48%, 86.9%, 88.25%, and 89.64% were achieved using ResDenseUNet, INet, C-Net, and the proposed strategy, respectively. Also, intersection over union (IoU) of 79.24%, 81.63%, 82.48%, and 83.76% have been achieved using ResDenseUNet, INet, C-Net, and the proposed method. Conclusions: The proposed strategy is a promising technique for automatically diagnosing AAA and AAD, thereby reducing the workload of cardiovascular surgeons.
  • Küçük Resim Yok
    Öğe
    Content-Based Brain Magnetic Resonance Image Retrieval and Classification With the Proposed Deep Learning and Tissue-Based System
    (Ieee-Inst Electrical Electronics Engineers Inc, 2025) Dogan, Bedriye; Burak Mutlu, Hursit; Yildirim, Muhammed; Yalcin, Sercan; Aslan, Serpil; Sampathila, Niranjana; Rajendra Acharya, U.
    The exponential growth in the size of databases due to technological advancements has led to challenges in locating and accessing specific components of the data. While deep learning and other machine learning architectures have shown promise in retrieving data components, their efficacy is more pronounced when addressing disease cohorts. Contrarily, this effectiveness diminishes when accessing large datasets. This study focuses on the analysis of brain magnetic resonance imaging (MRI) images and, specifically, to differentiate between benign and malignant lesions associated with Alzheimer's disease, multiple sclerosis (MS), and intracranial regions, all of which are medically significant with distinct treatment modalities. A hybrid model was first devised to facilitate image retrieval by employing a pre-trained EfficientNet-b0 and local binary pattern (LBP) for feature extraction. These extracted features were then amalgamated to encompass diverse aspects of each image. To improve model performance, redundant features were pruned using the minimum redundancy maximum relevance (mRMR) technique. As a result, the proposed model demonstrated efficacy in analyzing a diverse dataset encompassing three distinct diseases and eight unique classes. Notably, existing machine architectures already published in the literature have struggled to achieve comparable success rates in discerning such closely related yet distinct disease groups. Our study underscores the challenge posed by increasing class diversity on the performance of deep learning architectures and obtained an accuracy of 98.9% in classifying three diseases and eight unique classes. As a result, the same model was used as the base in both the classification and CBIR processes for MRI detection, yielding competitive results when compared with the literature and other models.
  • Küçük Resim Yok
    Öğe
    Multi-task advanced convolutional neural network for robust lymphoblastic leukemia diagnosis, classification, and segmentation
    (Peerj Inc, 2025) Yalcin, Sercan; Yalcin, Zuhal Cetin; Yildirim, Muhammed; Alatas, Bilal
    Acute lymphoblastic leukemia (ALL), a hematologic malignancy characterized by the overproduction of immature lymphocytes, a type of white blood cell. Accurate and timely diagnosis of ALL is crucial for effective management. This article introduces a novel multi-task advanced convolutional neural network (MTA-CNN) framework for ALL detection in medical imaging data by simultaneously performing, expression classification, and disease detection. The MTA-CNN is based on a deep learning architecture that can handle multiple tasks simultaneously, allowing it to learn more comprehensive and generalizable features. With, expression classification, and disease detection tasks, the MTA-CNN effectively leverages the complementary information from each task to improve overall performance. The proposed framework employs CNNs to extract informative features from medical images. These features capture the spatial and temporal characteristics of the data, which are essential for accurate ALL diagnosis. The cascaded structure of the MTA-CNN allows the model to learn features at different levels of abstraction, from low-level to high-level, enabling it to capture both fine-grained and coarse-grained information. To ensure the reliability of the detection results, non-maximum suppression is employed to eliminate redundant detections, focusing only on the most likely candidates. Additionally, the MTA-CNN's ability to accurately localize key facial landmarks provides valuable information for further analysis, including identifying abnormal structures or changes in anatomical features associated with ALL. Experimental results on a comprehensive dataset of medical images demonstrate the superiority of the MTA-CNN over other learning methods. The proposed framework achieved an accuracy of 0.978, precision of 0.979, recall of 0.967, F1-score of 0.973, specificity of 0.991, Cohen's kappa of 0.979, and negative predictive value (NPV) of 0.990. These metrics significantly outperform baseline models, highlighting the MTA-CNN's ability to accurately identify and classify ALL cases. The MTA-CNN offers a promising approach for improving the efficiency and accuracy of ALL diagnosis.
  • Küçük Resim Yok
    Öğe
    Optimal control strategy to charging and discharging techniques for electric vehicle battery pack optimization based on genetic algorithm and machine learning
    (Elsevier, 2026) Yalcin, Sercan; Yildirim, Muhammed; Khan, Muhammad Attique; Li, Yang; Alabdullah, Bayan; Cho, Yongwon; Nam, Yunyoung
    This paper investigates optimal control strategies for charging and discharging battery packs, aiming to maximize lifespan and performance. The focus is on developing efficient techniques based on Genetic Algorithms (GAs) and machine learning (ML) to optimize battery pack operation. This study uses a proposed GA as a global search engine for optimal control parameters, while integrating Support Vector Machine (SVM) to improve the prediction accuracy of the battery state affected by these parameters. Furthermore, the Deep Reinforcement Learning (DRL) agent is trained in a physics-based simulation environment, such as PyBaMM, directly learning physics-informed, dynamic charging current profiles, unlike traditional DRL studies.The research explores various control parameters, including charging/discharging rates, current profiles, and temperature management, to minimize degradation and maximize energy efficiency. This approach effectively searches the vast solution space to identify optimal control strategies that balance immediate energy demands with long-term battery health. Simulation results demonstrate the effectiveness of the proposed GA-based optimization framework in achieving significant improvements in battery pack lifespan, energy efficiency, and overall performance compared to conventional control methods.