Profile URL: https://hdl.handle.net/20.500.13091/11843
Job Title:Dr. Öğr. Üyesi
Email Address:vtongur@ktun.edu.tr
Main Affiliation:10.02. Department of Software Engineering
Status: Current Staff
ORCID:
0000-0001-5419-7839
0000-0001-5419-7839Scopus ID:
57191242912
57191242912YÖK Akademik: 983293343A984503
Google Scholar:
RPA6MEsAAAAJ
RPA6MEsAAAAJWeb of Science ID:
AAO-4296-2020
AAO-4296-202012 results
Scholarly Output Search Results
Now showing 1 - 10 of 12
Article Interpreter and Interface Design for a Special PLC Based on Atmega(2020) Tongur Vahit; Kahramanlı ŞirzatArticle A Review on Measurement of Particle Sizes by Image Processing Techniques(2023) Karakoyun, Murat; Batibay, Ahmet Burçin; Tongur, VahitThis review is based on how to measure particle sizes with different image processing techniques. In addition to this, particle size significantly affects the mechanical properties of the material. In material science, structure of the material is analyzed to understand that a material can provide certain standards, such as toughness and durability. Therefore, it is a great importance to make this measurement carefully and accurately. The segmentation approach, which is frequently used in image processing, aims to isolate objects in an image from the background. In this sense, the separation of particles from the background can be considered as a problem of the image processing. In image processing applications, there are different approaches used in segmentation such as histogram-based, clustering-based, region amplification, separation and merging. In this review, a comparative analysis was made by examining recent studies on particle size measurement.Article Combining Machine Learning and Metaheuristics Optimizing for 3PLs’ Daily Payment Schedules in Logistics(Elsevier - Division Reed Elsevier India Pvt Ltd, 2026-08-01) Uymaz, Sait Ali; Kaya, Ersin; Gerz, Serkan; Bardiz, Ahmet; Tongur, VahitIn today's competitive business environment, logistics processes that encompass critical stages from procurement to customer delivery play a central role in supply chain management. Effective supplier management is crucial for gaining a competitive advantage, enhancing quality, and ensuring customer satisfaction. This study proposes an artificial intelligence-based model for generating daily payment schedules for third-party logistics providers (3PLs), which are a key component of logistics operations. The proposed model consists of two stages. In the first stage, 3PLs are scored based on their logistical capabilities and operational data using machine learning methods. In the second stage, daily payment schedules are automatically generated using a metaheuristic approach based on these scores and financial data from the payment system. The machine learning and metaheuristic methods used in the construction of the model were determined using logistical operational and financial data from Alışan Logistic for the period 2021-2023. The results showed that CatBoost Regression was the most successful method for scoring 3PLs, while the Genetic Algorithm was the most effective for generating payment schedules.Article Citation - WoS: 10Citation - Scopus: 9Land Reallocation Model With Simulated Annealing Algorithm(TAYLOR & FRANCIS LTD, 2020) Ertunç, Ela; Uyan, Mevlüt; Tongur, VahitLand consolidation project has many stages. Land reallocation is the most considerable stage in which many factors play a role and forms the basis of this project. In this study, a new optimisation-based reallocation model has been developed to realise block reallocation by evaluating the requests of landowners. The reallocation according to the developed method also reset the block spaces automatically. The most powerful aspect of the method is that while the reallocation phase in land consolidation projects takes weeks and months, this method can be done in minutes. This method contributes to projects in terms of time and cost.Article Citation - WoS: 28Citation - Scopus: 28Use of the Migrating Birds Optimization (mbo) Algorithm in Solving Land Distribution Problem(ELSEVIER SCI LTD, 2020) Tongur, Vahit; Ertunç, Ela; Uyan, MevlütLand distribution is an important process in Land Consolidation (LC) projects where agricultural parcels are reallocated to predetermined blocks. Land distribution is a process that takes a long time, requires high operating costs, and conflicts between landowners occur frequently. The parcels are tried to be placed in the best and most appropriate place of the existing blocks by considering many parameters in the distribution stage. Therefore, the placement of new parcels in blocks is seen as an optimization process. In LC projects, this process is carried out manually by technical staff using a software and thus it becomes a process that takes weeks and even months. Various methods have been developed to solve this important stage of the LC projects. It is required to find the best solution, since this issue is an optimization problem. This study aims to develop a new land distribution method. For this purpose, land distribution were carried out by use Migrating Birds Optimization (MBO) Algorithm. Used land distribution method in practice and the results of the new developed method were compared and thus the usability of the method that developed by us was tested. With this study, it has developed a new and successful distribution method according to the preference of land owners.Article Citation - WoS: 28Citation - Scopus: 34Solving a Big-Scaled Hospital Facility Layout Problem With Meta-Heuristics Algorithms(ELSEVIER - DIVISION REED ELSEVIER INDIA PVT LTD, 2019) Tongur, Vahit; Hacıbeyoğlu, Mehmet; Ülker, ErkanThe main objective of the hospital facility layout problem is to place the polyclinics, laboratories and radiology units within the predefined boundaries in such way that minimize the movement cost of patients and healthcare staff. Especially in big-scaled hospitals including several different specialized departments, it is important in terms of hospital efficiency that interacting units are placed closely. Nowadays meta-heuristic algorithms are often used to solve optimization problems such as facility layout. In this study; polyclinic, laboratory and radiology units' layout of a big-scaled university hospital was organized using three meta-heuristic algorithms which are migrating bird optimization (MBO), tabu search (TS) and simulated annealing (SA). The results were compared with the existing clinic layout. Consequently MBO and SA meta-heuristic algorithms have given the same best results improving the existing clinic layout efficiency approximately by 58%. (C) 2019 Karabuk University. Publishing services by Elsevier B.V.Master Thesis Evrişimli sinir ağları için hibrit bir iyileştirici geliştirilmesi(2026) Aksekili, İbrahim Çağrı; Tongur, VahitThe success of deep learning models depends not only on architectural design but also on the effectiveness of optimization algorithms responsible for updating model parameters. Although the Adam optimization algorithm, which has become an industry standard, provides high computational efficiency and fast convergence, it suffers from several structural limitations, including limited generalization capability, variance instability in the early stages of training, and excessive sensitivity to noisy gradients. To address these limitations and to ensure a more stable and robust learning process, this thesis proposes a novel hybrid optimization algorithm named Self-Confident RadaBelief (SCRB). The proposed method integrates the variance rectification mechanism of the RAdam algorithm with the precise gradient estimation strategy of AdaBelief. In addition, an L1-based variance smoothing term, which has not been previously explored in adaptive optimization methods, is introduced to enhance robustness against sudden and erroneous gradient fluctuations. This design enables the optimizer to achieve more reliable parameter updates, particularly in noise-sensitive training scenarios. The performance of the proposed algorithm was evaluated on multiple benchmark datasets representing varying levels of complexity, including CIFAR-10, CIFAR-100, Caltech-101, STL-10, and Fashion MNIST. All experiments were conducted using a Deep Convolutional Neural Network (Deep CNN) architecture enhanced with modern techniques such as Swish activation functions and Batch Normalization. Experimental results demonstrate that the SCRB algorithm outperforms widely used optimization methods such as Adam and RMSprop, particularly on high-complexity datasets. On the CIFAR-100 dataset, SCRB achieved an accuracy of 79.66%, surpassing Adam (78.72%) and RMSprop (77.19%). Furthermore, on the Caltech-101 dataset, which is characterized by an imbalanced data distribution, the proposed method exhibited superior computational efficiency by converging faster, reaching optimal performance at the 184th epoch. These findings indicate that SCRB provides a stable optimization process while significantly improving the generalization capability of deep learning models, making it an effective alternative for noise-sensitive image classification tasks.Article Citation - WoS: 20Citation - Scopus: 18Comparison of Different Optimization Based Land Reallocation Models(ELSEVIER SCI LTD, 2020) Uyan, Mevlüt; Tongur, Vahit; Ertunç, ElaLand reallocation, which is an optimization problem in the field of engineering, is the process of reallocating parcels to pre-determined blocks according to the preferences of landowners. In practice, this is done manually and takes weeks or even months. The elongation of this process affects both the cost of the project and the project's acceptability by the landowners and thus the success of the project. Because the success of land consolidation projects is determined by the satisfaction of the landowners. For these reasons, the optimization-based land reallocation studies have been extensively carried out recently. However, these methods in the literature are not used in practice and the reallocation is still done manually. Therefore, for the first time in this study, two new reallocation models were developed to solve this problem by using Migration Birds and Simulated Annealing Algorithms and the results of these methods in a real project area were compared. Additionally, the results were compared to the conventional reallocation method (manual reallocation) to evaluate the performance of the methods developed. Both proposed methods provided a successful and practicable reallocation plan in a very short time with respect to the conventional one.Article Veri Ön İşleme Tekniklerinin Sağlık Verilerinin Sınıflandırma Başarısına Etkisinin İncelenmesi(2024-12-31) Erdoğan, Feyza; Tongur, Vahit; Uzbaş, BetülVeri 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.Master Thesis Veri Madenciliği Teknikleri ile Kitap Öneri Sistemi(2025) Can, Mustafa; Tongur, VahitGünümüzde artan kitap sayısıyla birlikte okuyucular kitap seçmekte zorlanmaktadırlar. E-ticaretin gelişmesi birçok ürün gibi farklı türden kitaba da ulaşımı oldukça kolaylaştırmıştır. Bu kolaylığın yanında okuyucunun doğru kitabı bulabilmesi oldukça önemlidir. E-ticaret sitelerinde fiziksel bir kitap satış mağazasında bulunan kitap sayısından daha fazla sayıda kitap bulunabilmektedir. Bu da beraberinde kitap seçimini zorlaştırmaktadır. E-ticaret sitelerinin önemli avantajlarından birisi de kullanıcıların kitaplar hakkındaki değerlendirmelere ulaşılabilmesidir. Bu çalışmada kitap öneri sistemi oluşturmak amacıyla 1000kitap.com platformundan kitaplara ait çeşitli bilgiler toplanmıştır. Elde edilen kitap özetlerine metin ön işlem adımları uygulanmıştır. Ön işlemden geçen kitap özetlerinden KeyBERT tekniği ile anahtar kelimeler elde edilip, Zeyrek kütüphanesi ile kelime kökleri bulunmuştur. Ayrıca benzerlik hesaplamasını iyileştirmek adına BERT derin öğrenme modeli ile bir model eğitilerek roman türündeki kitaplar için yeni alt tür tahminleri yapılmıştır. Çalışmadaki temel amaç kullanıcının seçmiş olduğu bir kitabın anahtar kelimelerinden yararlanarak veri setindeki diğer kitapların anahtar kelimeleri ile benzerliklerini hesaplayıp, okuyucuya benzer içerikli farklı kitapları önermektir.
Research Topics
Domains
Physical SciencesLife Sciences
Fields
EngineeringAgricultural and Biological SciencesComputer Science
Subfields
Industrial and Manufacturing EngineeringSoil ScienceArtificial Intelligence
Specific Research Areas
Advanced Manufacturing and Logistics Optimization
Land Rights and Reforms
Optimization and Packing Problems
Metaheuristic Optimization Algorithms Research
Scheduling and Optimization Algorithms
Vehicle Routing Optimization Methods
Sustainable Development Goals
11SUSTAINABLE CITIES AND COMMUNITIES
1
Research Products
3GOOD HEALTH AND WELL-BEING
1
Research Products
Documents
10
Citations
166
h-index
7
Documents
12
Citations
180
Publication Collaboration
| Affiliation Name | Count |
|---|---|
| Necmettin Erbakan University | 12 |
| Konya Technical University | 8 |
| Selçuk University | 6 |
| Türkisch-Deutsche Universität | 1 |
| Turkish Society of Cardiology | 1 |
1 / 1
Data obtained from OpenAlex
| Journal | Count |
|---|---|
| Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi | 1 |
| COMPUTERS AND ELECTRONICS IN AGRICULTURE | 1 |
| Engineering Science and Technology, an International Journal | 1 |
| ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH | 1 |
| International Journal of Engineering Science and Computing | 1 |
Current Page: 1 / 2
Scholarly Output
12
Articles
9
Views / Downloads
18/13
Supervised MSc Theses
3
Supervised PhD Theses
0
WoS Citation Count
86
Scopus Citation Count
89
Patents
0
Projects
0
WoS Citations per Publication
7.17
Scopus Citations per Publication
7.42
Open Access Source
5
Supervised Theses
3
Scopus Quartile Distribution
Competency Cloud
