Yazar "Karaduman, Mucahit" seçeneğine göre listele
Listeleniyor 1 - 14 / 14
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A hybrid CNN-ViT based framework for automatic traffic actions detection in smart cities(Public Library Science, 2026) Karaduman, Mucahit; Han, Neunggyu; Karaduman, Gulsah; Yildirim, Muhammed; Cho, Yongwon; Nam, YunyoungIt is crucial to automatically detect traffic accidents and hazardous situations in a timely and accurate manner. In this way, both individual security will be ensured and significant contributions will be made to economic efficiency and sustainable urban life. Millions of people die in traffic accidents every year. This situation also places an additional burden on health systems and will lead to many undesirable consequences. Early detection of events such as traffic density, accidents, and road closures accelerates emergency response processes, regulates traffic flow, and prevents secondary accidents. Therefore, artificial intelligence-supported automatic systems stand out as a key component of smart cities. This study aims to detect traffic accidents and traffic situations automatically. For this purpose, feature extraction was performed with five Convolutional Neural Network (CNN) and five Vision Transformer (ViT) based models. Then, the features obtained from these models were evaluated in different classifiers. The ViT model and the CNN model, which yielded the most successful results, served as the base for the proposed model. The features obtained from the best ViT model and CNN model were combined to bring together different features of the same image. Then, these features were classified into eight different categories using various classifiers. It was observed that the proposed model produced more successful results than the ten models whose preliminary results were obtained in the study. The accuracy value of the proposed model was 96.88%. This value is promising for future studies and plays a strategic role in terms of sustainability and enhancing the quality of life in smart cities.Öğe A Hybrid Model with Quantum Feature Map Based on CNN and Vision Transformer for Clinical Support in Diagnosis of Acute Appendicitis(Mdpi, 2026) Ogut, Zeki; Karaduman, Mucahit; Bozdag, Pinar Gundogan; Karakose, Mehmet; Yildirim, MuhammedBackground/Objectives: Rapid and accurate diagnosis of acute appendicitis is crucial for patient health and management, and the diagnostic process can be prolonged due to varying clinical symptoms and limitations of diagnostic tools. This study aims to shorten the timeframe for these vital processes and increase accuracy by developing a quantum-inspired hybrid model to identify appendicitis types. Methods: The developed model initially selects the two most performing architectures using four convolutional neural networks (CNNs) and two Transformers (ViTs). Feature extraction is then performed from these architectures. Phase-based trigonometric embedding, low-order interactions, and norm-preserving principles are used to generate a Quantum Feature Map (QFM) from these extracted features. The generated feature map is then passed to the Multiple Head Attention (MHA) layer after undergoing Hadamard fusion. At the end of this stage, classification is performed using a multilayer perceptron (MLP) with a ReLU activation function, which allows for the identification of acute appendicitis types. The developed quantum-inspired hybrid model is also compared with six different CNN and ViT architectures recognized in the literature. Results: The proposed quantum-inspired hybrid model outperformed the other models used in the study for acute appendicitis detection. The accuracy achieved in the proposed model was 97.96%. Conclusions: While the performance metrics obtained from the quantum-inspired model will form the basis of deep learning architectures for quantum technologies in the future, it is thought that if 6G technology is used in medical remote interventions, it will form the basis for real-time medical interventions by taking advantage of quantum speed.Öğe A novel approach in diagnosing knee osteoarthritis for content based image retrieval in big data analytics and medical images(Nature Portfolio, 2025) Bozdag, Pinar Gundogan; Mutlu, Hursit Burak; Karaduman, Mucahit; Yildirim, Muhammed; Khan, M. Attique; Alsenan, Shrooq; Nam, YunyoungThe rapid growth in database size due to technological advances has led to difficulties in locating and accessing specific data components. While deep learning and other machine learning architectures are promising in retrieving data components, their effectiveness is more pronounced when addressing groups of diseases. On the contrary, this effectiveness decreases when large data sets are accessed. Content-based Image retrieval (CBIR) methods are used in large data sets. In this study, knee osteoarthritis detection was performed using a developed hybrid CBIR-based system. Knee Osteoarthritis is the wear and tear of the cartilage in the knee joint. Knee osteoarthritis is a disease whose incidence increases, especially after a certain age. In this study, CBIR techniques were preferred to detect knee osteoarthritis. In the proposed method, feature extraction was performed using DarkNet53, Histogram of Oriented Gradients (HOG), and Local Binary Patterns (LBP). These features are combined to leverage the benefits of different aspects of the same image. To enhance the proposed model's speed and effectiveness, a hybrid model was developed utilizing the Neighborhood Component Analysis (NCA) method. Seven different distance measurement metrics were used in the developed CBIR model. Current deep learning architectures published in the literature struggle to achieve comparable success rates in distinguishing between closely related but distinct disease groups. The study highlights the challenges that increasing class diversity poses for the performance of deep learning architectures. In addition, the developed system aims to overcome the limitations of existing deep learning models in distinguishing similar disease groups.Öğe A novel feature fusion and mountain gazelle optimizer based framework for the recognition of jute pests in sustainable agriculture(Nature Portfolio, 2025) Kiziloluk, Soner; Karaduman, Mucahit; Aslan, Serpil; Yildirim, Muhammed; Khan, Muhammad Attique; Alhayan, Fatimah; Nam, YunyoungSustainable agriculture is an approach that involves adopting and developing agricultural practices to increase efficiency and preserve resources, both environmentally and economically. Jute is one of the primary sources of income grown in many countries. At this stage, increasing efficiency in jute production and protecting it from pests is essential. Detecting jute pests at an early stage will not only improve crop yield but also provide more income. In this paper, an artificial intelligence-based model was suggested to detect jute pests at an early stage. In this developed model, two different pre-trained models were used for feature extraction. To improve the performance of the developed model, the features obtained using the DarkNet-53 and DenseNet-201 models were combined. After this stage, the metaheuristic Mountain Gazelle Optimizer (MGO) was used, allowing the developed model to work faster and achieve more successful results. Feature selection was carried out using MGO; thus, more successful results were obtained with fewer, more compelling features. The proposed model was compared with six different models and five different classifiers accepted in the literature. In the developed model, 17 different jute pests were detected with 96.779% accuracy. The accuracy value achieved in the developed model is promising in successfully detecting jute pests.Öğe Artificial Intelligence and Decision Support Applications in Liver Hydatid Disease: Detection, Classification, and Complication Prediction(Springer Science+Business Media, 2025) Karaduman, Mucahit; Yildirim, Muhammed; Akbulut, SamiHydatid disease, caused by Echinococcus spp., is a parasitic infection commonly observed in endemic regions such as the Middle East, South America, and Central Asia. Imaging modalities like ultrasonography, computed tomography, and magnetic resonance imaging play a crucial role in diagnosing and managing this disease. However, these techniques have some limitations, particularly concerning diagnostic accuracy, operator dependency, and the inability to predict complications in advance. This chapter comprehensively addresses the use of artificial intelligence (AI) and clinical decision support systems in managing liver hydatid disease within this context. Since the disease most commonly affects the liver, the chapter specifically focuses on liver hydatid disease. AI-based technologies are increasingly utilized to overcome these challenges and optimize diagnostic processes. Deep learning algorithms (e.g., CNN, U-Net) have demonstrated high accuracy in analyzing imaging data. These algorithms enable the automated staging of liver hydatid cysts and predict the risk of complications. Notably, the automation of staging systems accelerates clinical decision-making and reduces discrepancies among expert opinions. Furthermore, surgical clinical decision support systems and complication prediction models not only enhance diagnostic processes but also make treatment planning more reliable. Despite the promising potential of AI models, their widespread clinical adoption faces obstacles such as the lack of high-quality data sets and the challenge of making model decisions interpretable. Therefore, multicenter studies and model validations based on extensive data sets are essential for integrating AI more effectively into clinical practice. In conclusion, AI-powered clinical decision support systems hold significant potential for standardizing and expediting the diagnostic and therapeutic processes in liver hydatid disease. However, further research is necessary to ensure their seamless integration into clinical practice. © 2025 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.Öğe CLASSIFICATION OF MALICIOUS NETWORK DATASET WITH RESIDUAL CNN(2025) Karaduman, Mucahit; YALÇIN, Sercan; YILDIRIM, MuhammedThis paper proposes a Residual Convolutional Neural Network (CNN) based model for malicious traffic detection. Network security is becoming increasingly important every day as the digital world develops. It aims to classify the data labeled as benign and malicious in the ready dataset. In the proposed model, first of all, all the information in the dataset is digitized. Then, it is normalized to the range of 0-1 and made ready as an input to the proposed architecture. It is aimed to classify the information in this two-class dataset with the proposed Residual Convolutional Neural Network (CNN) architecture. The accuracy rate obtained after the training and testing stages of the model is 94.9%. This accuracy rate shows that the proposed model successfully results in the detection of malicious packets in network attacks and can be used for network security.Öğe Clinically Focused Computer-Aided Diagnosis for Breast Cancer Using SE and CBAM with Multi-Head Attention(Mdpi, 2025) Ogut, Zeki; Karaduman, Mucahit; Yildirim, MuhammedBackground/Objectives: Breast cancer is one of the most common malignancies in women worldwide. Early diagnosis and accurate classification in breast cancer detection are among the most critical factors determining treatment success and patient survival. In this study, a deep learning-based model was developed that can classify benign, malignant, and normal breast tissues from ultrasound images with high accuracy and achieve better results than the methods commonly used in the literature. Methods: The proposed model was trained on a dataset of breast ultrasound images, and its classification performance was evaluated. The model is designed to effectively learn both local textural features and global contextual relationships by combining Squeeze-and-Excitation (SE) blocks, which emphasize channel-level feature importance, and Convolutional Block Attention Module (CBAM) attention mechanisms, which focus on spatial information, with the MHA structure. The model's performance is compared with three commonly used convolutional neural networks (CNNs) and three Vision Transformer (ViT) architectures. Results: The developed model achieved an accuracy rate of 96.03% in experimental analyses, outperforming both the six compared models and similar studies in the literature. Additionally, the proposed model was tested on a second dataset consisting of histopathological images and achieved an average accuracy of 99.55%. The results demonstrate that the model can effectively learn meaningful spatial and contextual information from ultrasound data and distinguish different tissue types with high accuracy. Conclusions: This study demonstrates the potential of deep learning-based approaches in breast ultrasound-based computer-aided diagnostic systems, providing a reliable, fast, and accurate decision support tool for early diagnosis. The results obtained with the proposed model suggest that it can significantly contribute to patient management by improving diagnostic accuracy in clinical applications.Öğe Deep and Statistical Features Classification Model for Electroencephalography Signals(Int Information & Engineering Technology Assoc, 2022) Karaduman, Mucahit; Karci, AliPeople strive to make sense of the complex electroencephalography (EEG) data generated by the brain. This study uses a prepared dataset to examine how easily people with alcohol use disorder (AUD) could be distinguished from healthy people. The signals from each electrode are connected to one another and are first represented as a single signal. The signal is then denoised through variation mode decomposition (VMD) during the preprocessing stage. The statistical and deep feature extraction phases are the two subsequent phases. The crucial step in the suggested strategy is to classify data using a combination of these two unique qualities. Deep and statistical feature performance was evaluated independently. Then, using the eigenvectors created by merging all of the collected features, classification was carried out using our DSFC (Deep - Statistical Features Classification) model. Although the classification accuracy rate using only statistical features was 81.2 percent and the classification accuracy rate using only deep learning was 95.71 percent, the classification accuracy rate utilizing hybrid features created using the suggested DSFC technique was 99.2%. Therefore, it can be proven that combining statistical and deep features can produce beneficial results.Öğe Detection of Gallbladder Disease Types Using a Feature Engineering-Based Developed CBIR System(Mdpi, 2025) Bozdag, Ahmet; Yildirim, Muhammed; Karaduman, Mucahit; Mutlu, Hursit Burak; Karaduman, Gulsah; Aksoy, AzizBackground/Objectives: Early detection and diagnosis are important when treating gallbladder (GB) diseases. Poorer clinical outcomes and increased patient symptoms may result from any error or delay in diagnosis. Many signs and symptoms, especially those related to GB diseases with similar symptoms, may be unclear. Therefore, highly qualified medical professionals should interpret and understand ultrasound images. Considering that diagnosis via ultrasound imaging can be time- and labor-consuming, it may be challenging to finance and benefit from this service in remote locations. Methods: Today, artificial intelligence (AI) techniques ranging from machine learning (ML) to deep learning (DL), especially in large datasets, can help analysts using Content-Based Image Retrieval (CBIR) systems with the early diagnosis, treatment, and recognition of diseases, and then provide effective methods for a medical diagnosis. Results: The developed model is compared with two different textural and six different Convolutional Neural Network (CNN) models accepted in the literature-the developed model combines features obtained from three different pre-trained architectures for feature extraction. The cosine method was preferred as the similarity measurement metric. Conclusions: Our proposed CBIR model achieved successful results from six other different models. The AP value obtained in the proposed model is 0.94. This value shows that our CBIR-based model can be used to detect GB diseases.Öğe Determining the Demands of Disabled People by Artificial Intelligence Methods(Ali KARCI, 2021) Karaduman, Mucahit; Karci, AliAnalysis of brain activities and remote control are among the current issues that are being studied. Analysis of signals arising during brain functions is electroencephalography (EEG). EEG signals have intellectual, visual stimulation, and motion resultant forms. Especially, EEG signals generated by visual stimulus are within the scope of this study. In this study, research was carried out on the classification of EEG signals formed in a person looking at visual figures. For these studies, first of all, EEG signals from the brain were recorded with images and filtered to remove noise. Then, the features were extracted from the signals. In this study, Moment 5 feature was also used in addition to the features used in many studies such as mean, median, standard deviation and entropy. Then, classification was made using Support Vector Machine (SVM), k Nearest Neighbor (KNN), and Decision Tree (DT) algorithms. Classification was made for 4 different visual shapes used, since these shapes are square, circle, triangle, and star, and the same categorical names were used in the classification stage. As a result of the classification of EEG signals; SVM and KNN algorithms have determined which shape is viewed with 99.99% accuracy. These results show that different signals are produced in the brain according to the structure of the shape viewed. This situation shows that it can be used as a method to give patients the opportunity to express their requests just by looking or thinking.Öğe Early detection of colorectal cancer using a hybrid model with enhanced image quality and optimized classification(Springer, 2025) Bozdag, Ahmet; Karaduman, Mucahit; Kiziloluk, Soner; Karaduman, Gulsah; Yildirim, Muhammed; Yildirim, Ozal; Acharya, U. RajendraColorectal cancer starts in the large intestine and rectum. It develops when small, usually harmless growths called polyps become cancerous over time. Early diagnosis increases the chances of successfully treating colorectal cancer. A new hybrid model was developed to detect colorectal tissue types. In the first step of the model, the quality of the images was increased using Denoising Convolutional Neural Network (DNCNN) networks. The feature maps of the images were then obtained using DarkNet53 and shrunk using the Gorilla Troops Optimization Algorithm (GTO) to speed up the proposed model's performance and boost the performance. Finally, a support vector machine (SVM) classifier was used to classify the feature maps. The proposed model obtained an accuracy of 95.5% in classifying eight tissue types in colorectal cancer histopathology specimens (Adipose, Complex, Debris, Empty, Lympho, Mucosa, Stroma, and Tumor). To make the developed model more generalizable, robust, and accurate, it needs to be tested with a huge dataset collected from various centers and races.Öğe Evaluation of Maxillary Sinus Membrane Morphology Using a Novel Hybrid CNN-ViT-Based Deep Learning Model: An Automated Classification Study(Mdpi, 2026) Duger, Nurullah; Talo, Furkan; Tekin, Gulucag Giray; Dagtekin, Burak; Karaduman, Mucahit; Yildirim, Muhammed; Yildirim, Tuba TaloObjectives: This study aimed to develop and validate a hybrid deep learning model combining Convolutional Neural Networks (CNN) and Vision Transformers (ViT) to automatically classify maxillary sinus membrane morphologies on Cone-Beam Computed Tomography (CBCT) images, distinguishing between Normal, Flat, Polypoid, and Obstruction types. Methods: A dataset of 959 CBCT images was collected and categorized into four morphological classes: Normal, Flat, Polypoid and Obstruction. A custom hybrid model was developed, integrating a lightweight residual CNN for local feature extraction, learnable weighted feature fusion with a bidirectional feature pyramid network and a Transformer encoder for global context modeling. The performance of proposed model was compared against six different architectures, including ResNet50, MobileNetV3L and standard ViT models, using accuracy, precision, recall and F1-score metrics. Results: The proposed hybrid model achieved the highest overall accuracy of 98.44%, outperforming six strong CNN and ViT models including ResNet50 (97.92%) and ViT-B16 (86.46%) models. In class-wise analysis, the model demonstrated superior diagnostic capability, particularly for the Obstruction class, achieving 100% accuracy. High discrimination was also observed for Flat (98.21%) and Polypoid (98.04%) morphologies, confirming the model's sensitivity to shape-based features. Conclusions: The proposed hybrid CNN-ViT model successfully classifies maxillary sinus membrane morphologies with high accuracy, effectively overcoming the limitations of standard ViT models on limited datasets. Detection of membrane morphology is vital for predicting surgical risks like membrane perforation and post-operative sinusitis. This model serves as a reliable clinical decision support tool, enabling clinicians to objectively assess specific risk factors before implant surgery and sinus floor elevation.Öğe Evaluation of the Risk of Urinary System Stone Recurrence Using Anthropometric Measurements and Lifestyle Behaviors in a Developed Artificial Intelligence Model(Mdpi, 2025) Yasar, Hikmet; Yildirim, Kadir; Karaduman, Mucahit; Kolcu, Bayram; Ezer, Mehmet; Suceken, Ferhat Yakup; Sarica, KemalBackground/Objectives: Urinary system stone disease is an important health problem both clinically and economically due to its high recurrence rates. In this study, an innovative hybrid approach based on deep learning is proposed to predict the recurrence risk of stone disease. Methods: Patient data were divided into three subsets: anthropometric measurements (Part A), derived body composition indices (Part B), and other clinical and demographic information (Part C). Each data subset was processed with autoencoder models, and low-dimensional, meaningful features were extracted. The obtained features were combined, and the classification process was performed using four different machine learning algorithms: Extreme Gradient Boosting (XGBoost), Cubic Support Vector Machines (Cubic SVM), k-Nearest Neighbor algorithm (KNN), and Decision Tree (DT). Results: According to the experimental results, the highest classification performance was obtained with the XGBoost algorithm. The suggested approach adds to the literature by offering a novel solution that makes early risk calculation for stone disease recurrence easier. It also shows how well structural feature engineering and deep representation can be integrated in clinical prediction issues. Conclusions: Prediction of the stone recurrence risk in advance is of great importance both in terms of improving the quality of life of patients and reducing the unnecessary diagnostic evaluations along with lowering treatment costs.Öğe Performance of Transformer-Based Methods on Restaurant Reviews Analysis(2025) Karaduman, Mucahit; BAYDEMİR, Muhammed Bedir; YILDIRIM, MuhammedSentiment analysis provides important data in various areas, from customer feedback to social media posts, by determining the text's emotional tones. In this study, sentiment analysis was performed using restaurant reviews with a transformer-based model. The attention mechanism underlying these models dynamically learns the contextual relationships of words in the text and better captures the meaning of the language. The model was trained and tested using a dataset from a vast information source. First, tokenization and padding operations of the dataset were performed; then, the model was trained, and test results were obtained. The training accuracy of the model was calculated as 90.81% and the test accuracy as 85.79%. When other performance metrics were also considered, the model, which achieved high success for negative and positive classes, showed lower success for the neutral class. In terms of general evaluation, it is seen that the model exhibited good performance when the accuracy rate was taken into account. This shows that transformer-based approaches are suitable for natural language processing and usability in this area.
