Uzbaş, Betül

Profile URL
https://hdl.handle.net/20.500.13091/11864
Name Variants
Uzbaş, B. Uzbas, Betul
Job Title
Email Address
buzbas@ktun.edu.tr
Main Affiliation
10.01. Department of Computer Engineering
Status
Current Staff
Website
ORCID ID
0000-0002-0255-5988
Scopus Author ID
57201915831
Turkish CoHE Profile ID
E52718094232E359
Google Scholar ID
D5G4R78AAAAJ
WoS Researcher ID
AAM-2345-2020

Research Topics

Domains
Health SciencesSocial SciencesLife Sciences
Fields
DentistryHealth ProfessionsArts and HumanitiesMedicineBiochemistry, Genetics and Molecular Biology
Subfields
Oral SurgeryHealth Information ManagementArcheologyRadiology, Nuclear Medicine and ImagingMolecular Biology
Specific Research Areas
Dental Radiography and Imaging
Artificial Intelligence in Healthcare
Forensic Anthropology and Bioarchaeology Studies
COVID-19 diagnosis using AI
dental development and anomalies

Sustainable Development Goals

NO POVERTY1
NO POVERTY
0
Research Products
ZERO HUNGER2
ZERO HUNGER
0
Research Products
GOOD HEALTH AND WELL-BEING3
GOOD HEALTH AND WELL-BEING
5
Research Products
QUALITY EDUCATION4
QUALITY EDUCATION
0
Research Products
GENDER EQUALITY5
GENDER EQUALITY
0
Research Products
CLEAN WATER AND SANITATION6
CLEAN WATER AND SANITATION
0
Research Products
AFFORDABLE AND CLEAN ENERGY7
AFFORDABLE AND CLEAN ENERGY
0
Research Products
DECENT WORK AND ECONOMIC GROWTH8
DECENT WORK AND ECONOMIC GROWTH
0
Research Products
INDUSTRY, INNOVATION AND INFRASTRUCTURE9
INDUSTRY, INNOVATION AND INFRASTRUCTURE
0
Research Products
REDUCED INEQUALITIES10
REDUCED INEQUALITIES
0
Research Products
SUSTAINABLE CITIES AND COMMUNITIES11
SUSTAINABLE CITIES AND COMMUNITIES
0
Research Products
RESPONSIBLE CONSUMPTION AND PRODUCTION12
RESPONSIBLE CONSUMPTION AND PRODUCTION
0
Research Products
CLIMATE ACTION13
CLIMATE ACTION
0
Research Products
LIFE BELOW WATER14
LIFE BELOW WATER
0
Research Products
LIFE ON LAND15
LIFE ON LAND
0
Research Products
PEACE, JUSTICE AND STRONG INSTITUTIONS16
PEACE, JUSTICE AND STRONG INSTITUTIONS
0
Research Products
PARTNERSHIPS FOR THE GOALS17
PARTNERSHIPS FOR THE GOALS
1
Research Products
Documents

12

Citations

48

h-index

3

Go to Scopus profile
Documents

12

Citations

39

Go to WoS profile

Publication Collaboration

Affiliation Name Count
Konya Technical University 13
Selçuk University 3
Tarsus University 2
Aselsan (Turkey) 2
Ankara University 1
1 / 2
Data obtained from OpenAlex
Scholarly Output

17

Articles

12

Views / Downloads

53/77

Supervised MSc Theses

3

Supervised PhD Theses

0

WoS Citation Count

14

Scopus Citation Count

21

Patents

0

Projects

0

WoS Citations per Publication

0.82

Scopus Citations per Publication

1.24

Open Access Source

12

Supervised Theses

3

JournalCount
ARTIFICIAL INTELLIGENCE AND APPLIED MATHEMATICS IN ENGINEERING PROBLEMS2
Avrupa Bilim ve Teknoloji Dergisi1
Concurrency and Computation-Practice & Experience1
Egyptian Informatics Journal1
European Journal of Science and Technology1
Current Page: 1 / 3

Scopus Quartile Distribution

Competency Cloud

GCRIS Competency Cloud

Filters

2020 - 202617

Settings

Author of Publication: search.filters.isAuthorOfPublication.b37a91b2-acda-4cb4-9cb2-12392200749f

Scholarly Output Search Results

Now showing 1 - 10 of 17
  • Article
    Detection of Covid-19 Severity and Mortality From Blood Parameters by Ensemble Learning Methods
    (2023-12-29) Erol, Doğan, Gizemnur; Uzbaş, Betül; Doğan, Gizemnur Erol
    COVID-19 is a pandemic that causes a high rate of spread and Acute Respiratory Distress Syndrome (ARDS). Severe pneumonia in infected individuals has resulted in too many patients being admitted to the Intensive Care Unit (ICU). This has placed unprecedented pressure on health systems by exceeding capacities. It is essential to detect the prognosis of this disease so that the health systems can remain active and the conditions of the patients who need to be hospitalized in the ICU do not become critical. In this study, COVID-19 prognosis was detected by using ICU admission (COVID-19 SEVERITY) and COVID-19 related death (COVID19 MORTALITY) datasets with Machine Learning (ML) methods. The missing data of the datasets were filled with K-Nearest Neighbor (KNN), and Min-Max normalization was performed. Datasets were divided three times into training and test sets, and the data were balanced with the Synthetic Minority Oversampling Technique (SMOTE). Then, classification was carried out using Ensemble Learning (EL) methods. For COVID-19 SEVERITY and COVID-19 MORTALITY, 89.54% and 97.25% accuracy were achieved with the Adaboost classifier, respectively. Successful and rapid COVID-19 prognosis detection with ML methods will help to use the ICU more efficiently and relieve the pressure on health systems.
  • Article
    LDA-Driven Classifiers and Stacking Ensembles for Efficient Human Activity Recognition
    (IEEE-Inst Electrical Electronics Engineers Inc, 2026) Uzbas, Betul
    Human Activity Recognition (HAR) is a core problem in ambient intelligence, aiming at the accurate classification of human movements using data acquired from wearable sensors. To ensure rigorous scientific validity, the methodology implements a leakage-free pipeline that adheres to the original subject-level separation between training and testing sets. This protocol ensures that participants are strictly partitioned, validating the model's performance on entirely unseen individuals to reflect realistic deployment scenarios. The proposed framework leverages Linear Discriminant Analysis (LDA) to transform the 561-dimensional raw sensor space into a high-utility, five-dimensional manifold, achieving a 99.1% reduction in feature dimensionality while preserving critical discriminative information. Classification performance was benchmarked across a spectrum of architectures, ranging from LDA-driven single classifiers to a complex LDA-augmented stacking ensemble (Stack579). In the Stack579 configuration, a meta-learner integrated diversified base model outputs with the original feature space to maximize spatial context. Empirical results demonstrate that while the Stack579_MetaMLP achieved the peak predictive accuracy of 96.64%, the LDA-SVM and LDA-LR variants followed closely with an accuracy of 96.50%. Critically, a pairwise McNemar test (p > 0.05) was conducted to evaluate the significance of these improvements. The analysis revealed no statistically significant difference between the complex ensemble and the streamlined LDA models. Furthermore, LDA-centric models exhibited an exceptional inference latency of approximately 0.0057 ms per sample, providing a decisive computational advantage. This study concludes that while stacking architectures offer maximum absolute precision, LDA-driven single classifiers represent a highly optimized framework for real-time edge computing and wearable applications by ensuring a superior balance between high-tier accuracy and extreme computational agility.
  • Master Thesis
    Panoramik Radyografilerde Veri Ön İşleme ve Derin Öğrenme Kullanarak Diş Segmentasyonu
    (2024) Kocakuş, Mehmet; Uzbaş, Betül
    Dental segmentasyon, dental radyografik görüntülerde dişlerin ve çevresindeki anatomik yapıların sınırlarının belirlenmesi sürecidir. Bu süreç, dental yapıları dijital görüntüler üzerinde ayrı sınırlara ayırarak analiz edilebilir hale getirir. Özellikle Yapay Zekâ (YZ) destekli sistemlerde, dental segmentasyon; diş tespiti, çürük analizi, periodontal hastalıkların belirlenmesi ve ortodontik planlamalar gibi birçok klinik uygulamanın temelini oluşturmaktadır. Segmentasyonun amacı, tanı ve tedavi süreçlerinde doğru, hızlı ve tekrarlanabilir analizler sunarak klinik karar verme süreçlerini desteklemektir. Bu bağlamda, özellikle uzman eksikliği yaşanan bölgelerde otomatik dental segmentasyon sistemlerinin geliştirilmesi önemli bir ihtiyaç haline gelmiştir. Bu çalışma, U-Net Derin Öğrenme (DÖ) modeli kullanılarak dental radyografilerde segmentasyon performansı üzerinde veri artırımı, ön işleme teknikleri ve dikkat bloklarının etkisini araştırmaktadır. Araştırmanın amacı, otomatik diş segmentasyonu için en etkili görüntü işleme filtreleri, veri artırımı stratejileri ve derin öğrenme mimarileri kombinasyonunu belirlemektir. Çalışmada, Tufts Üniversitesi tarafından sağlanan 1.000 dental radyografiden oluşan bir veri seti kullanılmıştır. Veri seti, %85 eğitim ve %15 test olmak üzere ikiye ayrılmıştır. Görüntü kontrastını artırmak ve gürültüyü azaltmak amacıyla Kontrast Sınırlamalı Uyarlanabilir Histogram Eşitleme (Contrast-Limited Adaptive Histogram Equalization, CLAHE) Otsu eşikleme gibi ön işleme teknikleri ve, segmentasyon odak bölgelerini yorumlamak için Grad-CAM tabanlı ısı haritaları uygulanmıştır. Ayrıca, modelin genelleme yeteneğini artırmak için aynalama, 5° ve 10° derecelik döndürmeler ve öteleme gibi veri artırımı yöntemleri kullanılmıştır. Önerilen U-Net modeli, Adam optimizasyon algoritması kullanılarak 100 epok boyunca eğitilmiştir. Model performansını değerlendirmek amacıyla Dice skoru, Birleşim Üzerinden Kesişim (Intersection over Union, IoU) ve Piksel Doğruluğu (Pixel Accuracy, PA) ölçütleri kullanılmıştır. Veri artırma uygulanmadan gerçekleştirilen deneylerde, CLAHE ön işleme ve dikkat blokları içeren Attention U-Net modeli ile %91,01 Dice, %83,51 IoU ve %97,86 PA en yüksek başarı elde edilmiştir. CLAHE ön işleme ile veri artırma uygulandığında ise, aynalama yöntemi ile artırılmış veriler kullanılarak eğitilen klasik U-Net modeli %91,02 Dice, %83,51 IoU ve %97,86 PA değerleri ile en yüksek başarıyı göstermiştir. Elde edilen bulgular, uygun veri artırımı, ön işleme teknikleri ve dikkat bloklarının uygulanmasının, özellikle veri setinin sınırlı olduğu durumlarda, modelin güvenilirliğini ve doğruluğunu anlamlı düzeyde artırdığını göstermektedir. Çalışmada, veri ön işleme yöntemleri ve dikkat bloklarıyla desteklenen derin öğrenme modellerinin, diş segmentasyonu ve tanısının otomatikleştirilmesi yoluyla sağlık profesyonellerine destek olması amaçlanmaktadır. Bu yaklaşım, özellikle uzman radyologlara erişimin kısıtlı olduğu uzak bölgelerdeki sağlık kuruluşları için önemli bir değer taşımaktadır.
  • Conference Object
    Citation - Scopus: 1
    Gender Determination From Teeth Images Via Hybrid Feature Extraction Method
    (SPRINGER INTERNATIONAL PUBLISHING AG, 2020) Uzbaş, Betül; Arslan, Ahmet; Kök, Hatice; Acılar, Ayşe Merve
    Teeth are a significant resource for determining the features of an unknown person, and gender is one of the important pieces of demographic information. For this reason, gender analysis from teeth is a current topic of research. Previous literature on gender determination have generally used values obtained through manual measurements of the teeth, gingiva, and lip area. However, such methods require extra effort and time. Furthermore, since sexual dimorphism varies among populations, it is necessary to know the optimum values for each population. This study uses a hybrid feature extraction method and a Support Vector Machine (SVM) for gender determination from teeth images. The study group was composed of 60 Turkish individuals (30 female, 30 male) between the ages of 19 and 27. Features were automatically extracted from the intraoral images through a hybrid method that combines two-dimensional Discrete Wavelet Transformation (DWT) and Principle Component Analysis (PCA). Classification was performed from these features through SVM. The system can be easily used on any population and can perform fast and low-cost gender determination without requiring any extra effort.
  • Master Thesis
    Sefalometrik Noktaların Derin Öğrenme Kullanarak Otomatik Tespiti
    (Konya Teknik Üniversitesi, 2022) Njikam, Mohamed Nourdine Mogham; Babalık, Ahmet; Uzbaş, Betül; Acılar, Ayşe Merve
    Günümüzde her sektörde bilgisayarlar kullanılarak büyük miktarda veriler toplanmaktadır. Sağlık, savunma sanayi, uzay ve siber güvenlik gibi alanlarda makine öğrenmesi yöntemleri kullanılarak, toplanan bu veri yığınları yüksek başarı oranlarıyla raporlanıp bunlardan anlamlı bilgiler çıkarılabilmektedir. Medikal görüntü analizi alanında yapılan araştırmalara ilgi artmasıyla birlikte uzmanlar, kritik tıbbi analiz problemlerini ele almak için ilginç ve etkili yöntemlere yönelmiştir. Bu alanlardan biri de sefalometrik analizdir. Sefalometrik işaretler hastalık teşhisleri, oral ve maksillofasiyal cerrahi alanlarında değerlendirme ve kraniyofasiyal büyüme tahmini, tedavi planı, küratif etkisini değerlendirme ve farklı olguları karşılaştırmak için kullanılmaktadır. Bu tez çalışmasında Evrişimsel Sinir Ağları (ESA) kullanılarak sefalometrik noktalarının otomatik tespitini yapan bir U-Net modeli geliştirilmiştir. 2015 IEEE Uluslararası Biyomedikal Görüntüleme Sempozyumu içinde Sefalometrik X-ray Görüntü Analizi Yarışması'nın himayesinde oluşturulmuş sefalometrik görüntüler kullanılmıştır. Toplam 19 Sefalometrik nokta otomatik tespit edilmiştir. 2 mm aralığında 74,0% Başarılı Algılama Oranı (BAO), 2,5 mm aralığında 81,4%, 3 mm aralığında 86,3% ve 4mm aralığında ise 92,2% BAO elde edilmiştir.
  • Article
    Early-Stage Diabetes Detection Using Age-Based Feature Selection and Machine Learning Methods
    (2025-12-31) Uzbaş, Betül
    Diabetes is spreading rapidly around the world, and there is an urgent need for governments to develop comprehensive strategies for diabetes detection. Early detection of diabetes is important for early initiation of treatment. In this paper, Data Mining (DM) and Machine Learning (ML) techniques are used to detect early diabetes by age from survey data. The dataset was divided into 3 groups (young, middle-aged, elderly), and a unique feature selection process was performed by averaging the feature importance obtained in Random Forest (RF), Gradient Boosting (GB), and eXtreme Gradient Boosting (XGBoost) algorithms for each group, and the features that should be considered in diabetes detection according to age groups were determined. Then, the features selected for each age group were classified using different ML methods. Accuracies of 96.77%, 98.10% and 99% were obtained for the young, middle-aged and elderly groups, respectively. The characteristics that should be taken into account in the assessment of diabetes according to age groups were also identified.
  • Article
    Veri Ön İşleme Tekniklerinin Sağlık Verilerinin Sınıflandırma Başarısına Etkisinin İncelenmesi
    (2024-12-31) Erdoğan, Feyza; Tongur, Vahit; Uzbaş, Betül
    Veri madenciliği sürecinin en temel adımlarından biri olan veri ön işleme teknikleri, literatürde sıklıkla başvurulan bir süreçtir. Bu çalışmada Hepatit hastalığına ait veri kümesi üzerinde sağlık alanında sık kullanılan veri ön işleme tekniklerinin etkinliği incelenmiştir. Sırasıyla eksik veri, dengesiz veri kümesi, aykırı veri, normalizasyon ve özellik seçimi işlemleri uygulanmıştır. Veri kümesinin her adımda elde edilen yeni versiyonu için literatürde sıklıkla kullanılan beş makine öğrenmesi yöntemi (KNN, LR, RF, SVM, ANN) ile sınıflandırma yapılmıştır. Elde edilen sonuçlar, doğru ve gerekli veri ön işleme tekniklerinin seçimi ile model başarısına olumlu katkısını desteklemektedir. Tüm aşama sonunda elde edilen model performansları %85 ve üzerinde olup, tüm performans belirleme ölçütleri bazında tutarlı sonuçlar göstermektedir. Her bir veri ön işleme model performansına kademeli olarak katkıda bulunmuş, en yüksek katkı ise son aşamada uygulanan özellik seçimi ile sağlanmıştır. Özellik seçimi, modelin performansını belirgin şekilde iyileştirerek sınıflandırma başarısına önemli ölçüde katkı sağlamıştır.
  • Article
    Arrhythmia Detection From 12-Lead ECG with 2-Phase Feature Extraction: By Presenting the Evaluation of Atrial Fibrillation
    (Springer London Ltd, 2025-11-17) Erol Dogan, Gizemnur; Tezel, Gulay; Solak, Fatma Zehra; Uzbas, Betul
    12-Lead Electrocardiography (ECG) is an essential diagnostic tool for detecting Cardiac Arrhythmias (CAs). In this study, Arrhythmia Detection (AD) was conducted using a 12-Lead ECG dataset. The dataset underwent specific preprocessing, and a hybrid 2-Phase Feature Extraction (2-PFE) method was proposed: (1) QRS detection using the Pan-Tompkins algorithm, and (2) P-Peak detection using windowing. The study specifically focused on analyzing Atrial Fibrillation (AFIB) separately from other arrhythmia types. This approach was evaluated through three classification models: SR and NON-SR, SR and NON-SR without AFIB, SR and AFIB.
  • Article
    Automatic Localization of Cephalometric Landmarks Using Convolutional Neural Networks
    (2021-12-03) Nourdine Mogham Njikam Mohamed; Uzbaş, Betül
    Experts have brought forward interesting and effective methods to address critical medical analysis problems. One of these fields of research is cephalometric analysis. During the analysis of tooth and the skeletal relationships of the human skull, cephalometric analysis plays an important role as it facilitates the interpretation of bone, tooth, and soft tissue structures of the patient. It is used during oral, craniofacial, and maxillofacial surgery and during treatments in orthodontic and orthopedic departments. The automatic localization of cephalometric landmarks reduces possible human errors and is time saving. To performed automatic localization of cephalometric landmarks, a deep learning model has been proposed inspired by the U-Net model. 19 cephalometric landmarks that are generally manually determined by experts are automatically obtained using this model. The cephalometric X-ray image dataset created under the context of IEEE 2015 International Symposium on Biomedical Imaging (ISBI 2015) is used and data augmentation is applied to it for this experiment. A Success Detection Rate SDR of 74% was achieved in the range of 2 mm, 81.4% in the range of 2.5mm, 86.3% in the range of 3mm, and 92.2% in the range of 4mm.
  • Article
    Fully Automated Pell & Gregory Classification on Panoramic Radiographs
    (Cairo Univ., Fac. Computers & Information, 2026-03-01) Uzbas, Betul; Dogan, Fatma Busra; Nourdine, Mogham Njikam Mohamed; Yucelbas, Sule; Yucelbas, Cuneyt; Arslan, Zeynep Betul; Yasar, Fusun; Mohamed Nourdine, Mogham Njikam
    This study proposes a fully automated deep learning system based on the U-Net architecture for classifying mandibular third molars using the Pell & Gregory method. Novel anatomical landmarks were introduced and automatically detected on panoramic radiographs by the model. These landmarks were then used to determine the classification through their spatial relationships. The system was trained and evaluated using panoramic radiographs collected from different patients. Two independent datasets were constructed according to the side of mandibular third molar impaction: 373 images for the left jaw (teeth 37-38) and 328 for the right jaw (teeth 47-48). For the Pell & Gregory classification, the proposed approach achieved a classification accuracy of 93.24% for the left jaw and 91.30% for the right jaw, demonstrating consistent and reliable performance across both datasets. The model effectively localized anatomical points and classified third molars without manual input. This automated approach enhances diagnostic consistency and reduces observer variability, offering practical utility in clinical environments. Overall, the study demonstrates the potential of artificial intelligence to improve diagnostic workflows by providing a reliable tool for the automated classification of impacted third molars according to the Pell & Gregory system.