Güngör, Burcu
Loading...
Profile URL
Name Variants
Bakir Gungor, Burcu
Bakir-Gungor, Burcu
Bakir-Güngör, Burcu
Bakir-gungor, Burcu
Burcu Güngör
Gungor, Burcu Bakir
Bakir-Güngör, B.
Bakir-Gungor, Burcu
Bakir-Güngör, Burcu
Bakir-gungor, Burcu
Burcu Güngör
Gungor, Burcu Bakir
Bakir-Güngör, B.
Job Title
Doç. Dr.
Email Address
burcu.gungor@agu.edu.tr
Main Affiliation
02. 04. Bilgisayar Mühendisliği
02. Mühendislik Fakültesi
01. Abdullah Gül University
02. Mühendislik Fakültesi
01. Abdullah Gül University
Status
Current Staff
Website
ORCID ID
Scopus Author ID
Turkish CoHE Profile ID
Google Scholar ID
WoS Researcher ID
Sustainable Development Goals
13
CLIMATE ACTION
0
Research Products
17
PARTNERSHIPS FOR THE GOALS
0
Research Products
8
DECENT WORK AND ECONOMIC GROWTH
0
Research Products
9
INDUSTRY, INNOVATION AND INFRASTRUCTURE
1
Research Products
12
RESPONSIBLE CONSUMPTION AND PRODUCTION
0
Research Products
16
PEACE, JUSTICE AND STRONG INSTITUTIONS
0
Research Products
11
SUSTAINABLE CITIES AND COMMUNITIES
0
Research Products
1
NO POVERTY
0
Research Products
6
CLEAN WATER AND SANITATION
0
Research Products
10
REDUCED INEQUALITIES
0
Research Products
14
LIFE BELOW WATER
2
Research Products
15
LIFE ON LAND
2
Research Products
5
GENDER EQUALITY
0
Research Products
4
QUALITY EDUCATION
0
Research Products
7
AFFORDABLE AND CLEAN ENERGY
1
Research Products
3
GOOD HEALTH AND WELL-BEING
51
Research Products
2
ZERO HUNGER
1
Research Products
Documents
101
Citations
1091
h-index
20
Documents
146
Citations
8923
Scholarly Output
123
Articles
55
Views / Downloads
2657/1872
Supervised MSc Theses
9
Supervised PhD Theses
7
WoS Citation Count
628
Scopus Citation Count
858
WoS h-index
16
Scopus h-index
19
Patents
0
Projects
2
WoS Citations per Publication
5.11
Scopus Citations per Publication
6.98
Open Access Source
56
Supervised Theses
16
| Journal | Count |
|---|---|
| Frontiers in Genetics | 7 |
| PeerJ Computer Science | 6 |
| -- 3rd International Conference on Computer Science and Engineering, UBMK 2018 -- Sarajevo -- 143560 | 5 |
| Applied Sciences-Basel | 5 |
| PeerJ | 5 |
Current Page: 1 / 11
Scopus Quartile Distribution
Competency Cloud
123 results
Scholarly Output Search Results
Now showing 1 - 10 of 123
Article Citation - WoS: 44Citation - Scopus: 58Review of Feature Selection Approaches Based on Grouping of Features(PeerJ Inc, 2023) Kuzudisli, Cihan; Bakir-Gungor, Burcu; Bulut, Nurten; Qaqish, Bahjat; Yousef, MalikWith the rapid development in technology, large amounts of high-dimensional data have been generated. This high dimensionality including redundancy and irrelevancy poses a great challenge in data analysis and decision making. Feature selection (FS) is an effective way to reduce dimensionality by eliminating redundant and irrelevant data. Most traditional FS approaches score and rank each feature individually; and then perform FS either by eliminating lower ranked features or by retaining highly -ranked features. In this review, we discuss an emerging approach to FS that is based on initially grouping features, then scoring groups of features rather than scoring individual features. Despite the presence of reviews on clustering and FS algorithms, to the best of our knowledge, this is the first review focusing on FS techniques based on grouping. The typical idea behind FS through grouping is to generate groups of similar features with dissimilarity between groups, then select representative features from each cluster. Approaches under supervised, unsupervised, semi supervised and integrative frameworks are explored. The comparison of experimental results indicates the effectiveness of sequential, optimization-based (i.e., fuzzy or evolutionary), hybrid and multi-method approaches. When it comes to biological data, the involvement of external biological sources can improve analysis results. We hope this work's findings can guide effective design of new FS approaches using feature grouping.Conference Object Citation - Scopus: 1A Federated Learning Framework for Classifying the Images in Ultrasonic Nondestructive Testing(Institute of Electrical and Electronics Engineers Inc., 2024) Gulsen, Abdulkadir; Hacilar, Hilal; Kolukisa, Burak; Bakir-Güngör, BurcuUltrasonic inspection is a critical technique in non-destructive testing that ensures the safety and integrity of the material by detecting internal defects. Defect classification within this context is vital for preventing failures and extending the lifespan of materials. However, the advancement of ultrasonic testing technology is hindered by a scarcity of publicly available, realistic datasets, which are essential for developing accurate models. To address these challenges, this paper introduces a Federated Learning (FL) framework employing a Convolutional Neural Network (CNN) model for defect classification using ultrasonic inspection images. This innovative approach allows for the decentralized training of models on private datasets without the need for data exchange, thus preserving data privacy. Our comparative analysis demonstrates that the FL achieves performance comparable to traditional methods while maintaining the confidentiality of sensitive information. The framework also proves to be robust and scalable with an increase in the number of participating clients. This pioneering study highlights the potential of FL in transforming ultrasonic defect classification and suggests possibilities for its application in other areas of non-destructive testing where publicly available datasets are scarce. These findings would encourage researchers to develop a federated platform for enhanced collaboration and explore advanced CNN architectures to improve training efficiency. © 2025 Elsevier B.V., All rights reserved.Article Topological Feature Generation for Link Prediction in Biological Networks(PeerJ Inc, 2023) Temiz, Mustafa; Bakir-Gungor, Burcu; Sahan, Pinar Guner; Coskun, MustafaGraph or network embedding is a powerful method for extracting missing or potential information from interactions between nodes in biological networks. Graph embedding methods learn representations of nodes and interactions in a graph with low-dimensional vectors, which facilitates research to predict potential interactions in networks. However, most graph embedding methods suffer from high computational costs in the form of high computational complexity of the embedding methods and learning times of the classifier, as well as the high dimensionality of complex biological networks. To address these challenges, in this study, we use the Chopper algorithm as an alternative approach to graph embedding, which accelerates the iterative processes and thus reduces the running time of the iterative algorithms for three different (nervous system, blood, heart) undirected protein-protein interaction (PPI) networks. Due to the high dimensionality of the matrix obtained after the embedding process, the data are transformed into a smaller representation by applying feature regularization techniques. We evaluated the performance of the proposed method by comparing it with state-of-the-art methods. Extensive experiments demonstrate that the proposed approach reduces the learning time of the classifier and performs better in link prediction. We have also shown that the proposed embedding method is faster than state-of-the-art methods on three different PPI datasets.Article Citation - WoS: 11Citation - Scopus: 10Clinical and Molecular Evaluation of MEFV Gene Variants in the Turkish Population: A Study by the National Genetics Consortium(Springer Heidelberg, 2022) Dundar, Munis; Fahrioglu, Umut; Yildiz, Saliha Handan; Bakir-Gungor, Burcu; Temel, Sehime Gulsun; Akin, Haluk; Erdem, LeventFamilial Mediterranean fever (FMF) is a monogenic autoinflammatory disorder with recurrent fever, abdominal pain, serositis, articular manifestations, erysipelas-like erythema, and renal complications as its main features. Caused by the mutations in the MEditerranean FeVer (MEFV) gene, it mainly affects people of Mediterranean descent with a higher incidence in the Turkish, Jewish, Arabic, and Armenian populations. As our understanding of FMF improves, it becomes clearer that we are facing with a more complex picture of FMF with respect to its pathogenesis, penetrance, variant type (gain-of-function vs. loss-of-function), and inheritance. In this study, MEFV gene analysis results and clinical findings of 27,504 patients from 35 universities and institutions in Turkey and Northern Cyprus are combined in an effort to provide a better insight into the genotype-phenotype correlation and how a specific variant contributes to certain clinical findings in FMF patients. Our results may help better understand this complex disease and how the genotype may sometimes contribute to phenotype. Unlike many studies in the literature, our study investigated a broader symptomatic spectrum and the relationship between the genotype and phenotype data. In this sense, we aimed to guide all clinicians and academicians who work in this field to better establish a comprehensive data set for the patients. One of the biggest messages of our study is that lack of uniformity in some clinical and demographic data of participants may become an obstacle in approaching FMF patients and understanding this complex disease.Conference Object Papiller Tiroid Karsinom Oluşumunda Etkili Moleküler Mekanizmaların İn Siliko Yöntemlerle Tespit Edilmesi(Institute of Electrical and Electronics Engineers Inc., 2019) Ersöz, Nur Sebnem; Guzel, Yasin; Bakir-Güngör, BurcuRepresenting approximately 70% to 80% of thyroid cancers, papillary thyroid cancer (PTC) is the most common type of thyroid cancers. PTC is seen in all age groups, but it is seen more frequently in women than in men. Detection of biomarker proteins of papillary thyroid cancinoma plays an important role in the diagnosis of the disease. In this study, we aim to find target genes and pathways that are associated with papillar thyroid carcinoma, by integrating different bioinformatics methods. For this purpose, usingin-silico methodologies, candidate genes and pathways that could explain disease development mechanisms are identified. Throughout this study, firstly we identified differentially expressed genes as the amount of their protein product differ between patient and healthy groups. Secondly, by using active subnetworks search algorithms, topologic analyses and functional enrichment tests, candidate proteins,which could be thought as PTC biomarkers, and affected pathways are identified. © 2020 Elsevier B.V., All rights reserved.Conference Object The Effect of Different Classifiers on Recursive Cluster Elimination in the Analysis of Transcriptomic Data(Institute of Electrical and Electronics Engineers Inc., 2023) Bulut, Nurten; Bakir-Güngör, Burcu; Qaqish, Bahjat F.; Yousef, MalikGene expression data with limited sample size and a large number of genes are frequently encountered in genetic studies. In such high-dimensional data, identification of genes that distinguish between disease states is a challenging task. Feature selection (FS) is a useful approach in dealing with high dimensionality. Support Vector Machines Recursive Cluster Elimination (SVM-RCE) is a technique for FS in high-dimensional data. The SVM-RCE approach has been utilized for identification of clusters of genes whose expression levels correlate with pathological state. A key step in SVM-RCE is the use of an SVM classifier to assign an area under the curve (AUC) score to each gene cluster based on its ability to predict class labels. In this study, we investigate the use of alternative classifiers in the cluster-scoring step. Specifically, we compare Support Vector Machines, Random Forest, XgBoost, Naive Bayes, and linear logistic regression. In addition to AUC score performance evaluation, the algorithms are compared in terms of the number of selected genes at different levels of clustering and in terms of the running time. © 2023 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 1TextNetTopics_TIS: Enhancing Textnettopics With Random Forest-Based Topic Importance Scoring(Institute of Electrical and Electronics Engineers Inc., 2024) Voskergian, Daniel; Bakir-Güngör, Burcu; Yousef, MalikTextNetTopics is an innovative Latent Dirichlet Allocation-based topic selection method for training text classification models. One main limitation is its computationally intensive scoring mechanism, especially when applied to many topics. This scoring mechanism involves training a machine learning model (i.e., Random Forest) on each topic using the Monte-Carlo Cross-Validation approach and assigning a score value based on a specific performance metric (e.g., accuracy or F1-score). Moreover, the measured score does not account for the interactions between all features residing in all topics. This paper presents a new topic-scoring mechanism called Topic Importance Scoring. This computationally efficient approach trains a Random Forest model on all topics simultaneously and leverages the extracted feature importance values to give each topic a score reflecting its classification potential. The experiments on three diverse datasets confirm that the proposed method's performance is superior to the Topic Performance Scoring, which was used in the original TextNetTopics method. © 2024 Elsevier B.V., All rights reserved.Master Thesis İstatistiksel Ön Puanlama Bileşeni ile Gruplama Puanlama Modellemesi (GSM) Yaklaşımın Geliştirilmesi: Yüksek Boyutlu Transkriptomik Veri Analizi için Bir Vaka Çalışması(Abdullah Gül Üniversitesi / Sosyal Bilimler Enstitüsü, 2024) Khokhar, Maham; Güngör, BurcuRapid advancements in transcriptomic technologies have significantly increased the volume of data available for analysis, which presents challenges in terms of efficiency and computational demand. This thesis introduces a Pre-Scoring component to the Grouping-Scoring-Modeling (G-S-M) framework to address inefficiencies caused by the excessive number of gene groups generated by traditional GSM. By selectively prioritizing gene groups based on their statistical significance, this innovation aims to reduce the computational demands associated with scoring these groups using machine learning models, thereby streamlining the analysis process. Assessed across nine diverse Gene Expression datasets, the Pre-Scoring G-S-M framework not only maintained accuracy comparable to the traditional approach but did so with significantly fewer genes. This refinement conserves resources while maintaining the robustness and reliability of the data analysis, crucial for advancing research in personalized medicine and therapeutic strategies. The findings suggest that the modified G-S-M framework serves as a valuable tool in bioinformatics, offering a more efficient approach to handling large-scale genomic datasets. Future work will focus on adapting this enhanced framework to incorporate diverse types of omics knowledge, such as proteomics and metabolomics, further optimizing its performance to broaden its applicability in both clinical and research settingsMaster Thesis Enhancing Breast Cancer Detection With a Hybrid Machine Learning Approach(2024) Etcil, Mustafa; Güngör, Burcu; Güngör, V. CagriDünya Sağlık Örgütü (WHO) tarafından belirlendiği üzere, göğüs kanseri, son beş yılda 7.8 milyon yeni vakayla en yaygın kanser türlerinden biri olarak ön plana çıkmaktadır. Bu çarpıcı istatistik, gelişmiş tanı yöntemlerine olan acil ihtiyacı vurgulamaktadır. Bu bağlamda, mevcut çalışma, göğüs kanseri tespiti için lojistik regresyon modeli eğitim sürecini iyileştirmek amacıyla klonal seçim algoritması (CSA) ile parçacık sürü optimizasyonunu (PSO) yenilikçi bir şekilde birleştiren CSA-PSO-LR sınıflandırıcısını önermektedir. Bu araştırma, geniş çapta tanınan iki veri seti olan Wisconsin Diagnostik Göğüs Kanseri (WDBC) ve Wisconsin Göğüs Kanseri Veritabanı (WBCD) kullanılarak, performans değerlendirmesi için 10 kat çapraz doğrulama ve Bayes hiperparametre optimizasyonunu içeren katı bir değerlendirme protokolü uygulamaktadır. Ayrıca, çalışma, model eğitim süresini önemli ölçüde kısaltmayı amaçlayan CPU paralelleştirme stratejilerini tanıtmaktadır. Karar ağaçları, aşırı gradyan artırma, en yakın komşular, lojistik regresyon, rastgele ormanlar ve destek vektör makineleri gibi makine öğrenimi algoritmalarına karşı yapılan karşılaştırmalı analizler, CSA-PSO-LR sınıflandırıcısının tespit doğruluğu ve F1-ölçütü açısından üstün performans sergilediğini göstermektedir. Bu araştırma, göğüs kanserinin erken tespitine yönelik yenilikçi bir yaklaşım sunarak, daha etkili tedavi planlarının kolaylaştırılmasına ve hastaların hayatta kalma beklentilerinin artırılmasına katkıda bulunmaktadır.Conference Object Citation - Scopus: 1Integrative Analyses in Omics Data: Machine Learning Perspective(Deutsche Gesellschaft fur Medizinische Informatik, Biometrie und Epidemiologie e.V., 2023) Ünlü Yazici, Miray; Bakir-Güngör, Burcu; Yousef, MalikDevelopments in the high throughput technologies have enabled the production of an immense amount of knowledge at the multi-omics level. Considering complex diseases which are affected by multi-factors, single omics datasets might not be sufficient to unveil the molecular mechanisms of heterogeneous diseases. Providing a comprehensive and systematic overview to explain disease hallmarks in significant depth is critical. Utilizing multi-omics datasets has led to the development of a variety of tools and platforms. Machine learning models are utilized in a wide variety of tools to tackle the complexity of disorders and to identify new biomolecular signatures and potential markers. Underlying aspects of these approaches are based on training the models for making predictions and classification of the given data. In this review, we describe current machine learning-based approaches and available implementations. Challenges in the enlightenment of disease mechanisms of onset and progression and future development of the field of medicine will be discussed. The prominence of biological interpretation of model output with corresponding biological knowledge will be also covered in this review. © 2023 Elsevier B.V., All rights reserved.
