Yazar "Togacar, Mesut" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    A Hybrid Artificial Intelligence Approach for Down Syndrome Risk Prediction in First Trimester Screening
    (Mdpi, 2025) Yalcin, Emre; Aslan, Serpil; Togacar, Mesut; Demir, Suleyman Cansun
    Background/Objectives: The aim of this study is to develop a hybrid artificial intelligence (AI) approach to improve the accuracy, efficiency, and reliability of Down Syndrome (DS) risk prediction during first trimester prenatal screening. The proposed method transforms one-dimensional (1D) patient data-including features such as nuchal translucency (NT), human chorionic gonadotropin (hCG), and pregnancy-associated plasma protein A (PAPP-A)-into two-dimensional (2D) Aztec barcode images, enabling advanced feature extraction using transformer-based deep learning models. Methods: The dataset consists of 958 anonymous patient records. Each record includes four first trimester screening markers, hCG, PAPP-A, and NT, expressed as multiples of the median. The DS risk outcome was categorized into three classes: high, medium, and low. Three transformer architectures-DeiT3, MaxViT, and Swin-are employed to extract high-level features from the generated barcodes. The extracted features are combined into a unified set, and dimensionality reduction is performed using two feature selection techniques: minimum Redundancy Maximum Relevance (mRMR) and RelieF. Intersecting features from both selectors are retained to form a compact and informative feature subset. The final features are classified using machine learning algorithms, including Bagged Trees and Naive Bayes. Results: The proposed approach achieved up to 100% classification accuracy using the Naive Bayes classifier with 1250 features selected by RelieF and 527 intersecting features from mRMR. By selecting a smaller but more informative subset of features, the system significantly reduced hardware and processing demands while maintaining strong predictive performance. Conclusions: The results suggest that the proposed hybrid AI method offers a promising and resource-efficient solution for DS risk assessment in first trimester screening. However, further comparative studies are recommended to validate its performance in broader clinical contexts.
  • Küçük Resim Yok
    Öğe
    Experimental and artificial intelligence approaches to measuring the wear behavior of DIN St28 steel boronized by the box boronizing method using a mechanically alloyed powder source
    (Pergamon-Elsevier Science Ltd, 2023) Albayrak, Muhammet Gokhan; Evin, Ertan; Yigit, Oktay; Togacar, Mesut; Ergen, Burhan
    Wear in moving materials in contact with each other is an inevitable cause of damage. To prevent this damage, various processes are applied to the material surfaces. The most widely used method is the surface hardening method. This study aims to examine the wear properties of the samples by forming a hard boride layer on the surface of low-carbon steel such as St28 with experimental and artificial intelligence approaches. In this context, it is aimed to obtain the boride layer at relatively low temperatures by pre-processing the powder mixture to be used as a boron source, such as Mechanical Alloying (MA). The boronizing process was carried out using the box boronizing technique. The wear behavior of the obtained samples was investigated by the block-on-disk method. In artificial intelligence approaches; The dataset is divided into three categories as 10N, 20N, and 40N. There are 39 sample types and attributes in each category. In this study, feature selection algorithms such as linear regression (LR), ridge, recursive feature elimination (RFE), f-regression, and multiple inclusion criterion (MIC) were used to select the most efficient samples. Then the best samples were classified according to their force types. Ensemble learning methods, machine learning methods, and Bayesian neural networks were used in the classification processes. Thanks to the proposed approach and feature selection algorithm, the best performance has been shown up to 10 feature selection. By ignoring 29 inefficient features, classification was performed with 10 efficient features. In the classification process, 100% overall accuracy was achieved.
  • Küçük Resim Yok
    Öğe
    Transformer-Based Emotion and Conflict Analysis of Disaster-Related Social Media: An Actor-Aware Decision Support Framework
    (Mdpi, 2026) Togacar, Mesut; Aslan, Serpil; Meydanoglu, Ayse; Denizyol, Emirhan; Ekidi, Abdurrezzak; Karateke, Tuncay; Saylan, Enes
    Social media platforms have become critical communication environments during disasters, where individuals express emotions, share information, and engage in public discourse. These platforms also reflect heterogeneous communication patterns shaped by different actor groups. However, existing studies predominantly focus on emotion classification and often overlook the combined role of actor identity and conflict dynamics. To address this gap, this study proposes an integrated AI-based analytical framework for actor-aware emotion and conflict analysis in post-disaster social media. An expert-annotated Turkish tweet dataset was constructed based on Ekman's emotion model, including anger, fear, sadness, happiness, and surprise, along with an additional irrelevant/off-topic category and conflict-level labels. A Transformer-based model (BERTurk) was fine-tuned for multi-class emotion classification. Experimental results show that the proposed model achieves strong classification performance, with an accuracy of 0.931 and an F1-score of 0.912, outperforming conventional machine learning and deep learning baselines. Actor-based analysis reveals systematic differences in emotional and conflict patterns across groups. Scientists, journalists, and individual users exhibit higher levels of conflict and more pronounced negative emotional expressions, whereas institutionally oriented actors display comparatively balanced and supportive communication patterns. In addition, a web-based decision support system was developed to enable interactive visualization and actor-level exploration of emotional and conflict dynamics. Overall, the proposed framework provides a scalable, analytically robust approach to understanding social media discourse in disaster contexts and offers practical implications for AI-driven crisis communication and decision-support systems.