Burak Gülmez
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Burak Gülmez has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Sinem Kulluk
Erciyes University
4 shared publications - Fatih Bahar
Erciyes Üniversitesi Mühendislik Fakültesi, Kayseri, Turkey
2 shared publications - Lale Özbakır
Erciyes University
2 shared publications Emrah Korhan
1 shared publication- Emrah Korhan
Department of Industrial Engineering, Kahramanmaraş İstiklal University, Kahramanmaraş, Türkiye
1 shared publication Güney Öztürk
Turkcell Technology, Istanbul, Turkey
1 shared publication
Latest Publications
- Open Access
- 23 August 2026
- Published by Elsevier in Borsa Istanbul Review
- Vol. 26 (6)
Asset clustering–driven risk–return trade-offs using AGE-MOEA in multi-objective portfolio optimization: Evidence from the EuroStoxx 50
- 23 August 2026
- Published by Elsevier in Borsa Istanbul Review
- Vol. 26 (6)
Open AccessAsset clustering–driven risk–return trade-offs using AGE-MOEA in multi-objective portfolio optimization: Evidence from the EuroStoxx 50
- Open Access
- 15 April 2026
- Published by Taylor & Francis in Drying Technology
- Vol. 44 (7) , 977-997
Dragon fruit drying method selection: A hybrid SWARA-EDAS-CoCoSo-MOORA MCDM approach
- 15 April 2026
- Published by Taylor & Francis in Drying Technology
- Vol. 44 (7) , 977-997
Open AccessDragon fruit drying method selection: A hybrid SWARA-EDAS-CoCoSo-MOORA MCDM approach
- Top Cited PapersOpen Access
- 12 April 2026
- Published by Elsevier in Energy Conversion and Management: X
- Vol. 30
Artificial intelligence-driven smart grid optimization: A comprehensive review of machine learning, renewable integration, and cybersecurity applications
- 12 April 2026
- Published by Elsevier in Energy Conversion and Management: X
- Vol. 30
Top Cited PapersOpen AccessArtificial intelligence-driven smart grid optimization: A comprehensive review of machine learning, renewable integration, and cybersecurity applications
- Open Access
- 10 April 2026
- Published by Springer Nature in Applied Intelligence
- Vol. 56 (6) , 200
Code generation with large language models: a survey from neural program synthesis to autonomous software development
Large language models have reshaped code generation, driving a transition from rule-based and statistical methods to transformer-based architectures pretrained on vast code corpora. This survey traces the intellectual lineage from classical program synthesis through pre-transformer neural approaches to contemporary large-scale models, examining code generation capabilities across model architectures, training strategies, task taxonomies, evaluation methodologies, security implications, and ethical considerations. Contemporary models show proficiency in function-level synthesis, program repair, and documentation generation, though performance varies across programming languages and task complexities. Models ranging from 125 M to hundreds of billions of parameters are analyzed (including CodeBERT, GraphCodeBERT, Codex, AlphaCode, CodeGen, StarCoder, CodeLlama, WizardCoder, DeepSeek-Coder-V2, Yi-Coder, and GPT-4) with pass@1 accuracies on HumanEval spanning a wide range across model generations; multi-agent approaches show promise on repository-level and complex benchmarks, though all figures require cautious interpretation given data contamination risks and evaluation protocol differences. Security concerns persist, as models consistently generate vulnerable code across a range of configurations, with vulnerability rates varying substantially depending on model generation, task type, and prompt design. The survey provides critical analysis of architectural design choices, scaling law behavior for code versus natural language, training data curation challenges including legal and ethical dimensions, and the gap between benchmark performance and real-world software engineering workflows. Critical gaps are identified in handling repository-level context, maintaining consistency across extended generation sessions, and providing reliability guarantees. Future trajectories point toward autonomous software engineering agents, hybrid neuro-symbolic verification approaches, and multi-faceted evaluation frameworks, though foundational challenges in correctness verification, security assurance, and trustworthy generation remain unresolved.
- 10 April 2026
- Published by Springer Nature in Applied Intelligence
- Vol. 56 (6) , 200
Open AccessCode generation with large language models: a survey from neural program synthesis to autonomous software development
Large language models have reshaped code generation, driving a transition from rule-based and statistical methods to transformer-based architectures pretrained on vast code corpora. This survey traces the intellectual lineage from classical program synthesis through pre-transformer neural approaches to contemporary large-scale models, examining code generation capabilities across model architectures, training strategies, task taxonomies, evaluation methodologies, security implications, and ethical considerations. Contemporary models show proficiency in function-level synthesis, program repair, and documentation generation, though performance varies across programming languages and task complexities. Models ranging from 125 M to hundreds of billions of parameters are analyzed (including CodeBERT, GraphCodeBERT, Codex, AlphaCode, CodeGen, StarCoder, CodeLlama, WizardCoder, DeepSeek-Coder-V2, Yi-Coder, and GPT-4) with pass@1 accuracies on HumanEval spanning a wide range across model generations; multi-agent approaches show promise on repository-level and complex benchmarks, though all figures require cautious interpretation given data contamination risks and evaluation protocol differences. Security concerns persist, as models consistently generate vulnerable code across a range of configurations, with vulnerability rates varying substantially depending on model generation, task type, and prompt design. The survey provides critical analysis of architectural design choices, scaling law behavior for code versus natural language, training data curation challenges including legal and ethical dimensions, and the gap between benchmark performance and real-world software engineering workflows. Critical gaps are identified in handling repository-level context, maintaining consistency across extended generation sessions, and providing reliability guarantees. Future trajectories point toward autonomous software engineering agents, hybrid neuro-symbolic verification approaches, and multi-faceted evaluation frameworks, though foundational challenges in correctness verification, security assurance, and trustworthy generation remain unresolved.
- Open Access
- 14 March 2026
- Published by Springer Nature in Applied Intelligence
- Vol. 56 (5) , 153
A hybrid decision tree-Markowitz framework for intelligent trading portfolio optimization
Predicting stock returns is difficult due to numerous dynamic and interrelated factors such as interest rates, exchange rates, economic conditions, corporate policies, investor behavior, and political developments. This study proposes a hybrid trading strategy that integrates the Decision Tree (DT) algorithm with the Markowitz Mean-Variance (MV) portfolio optimization model to improve prediction accuracy and optimize investment returns. Using data from 94 companies continuously listed on the NASDAQ 100 (NDX100) index between 2015 and 2024, the model uses technical analysis indicators as input for the DT to predict short-term stock returns and then applies MV optimization to allocate weights within dynamically generated portfolios. The empirical analysis includes 64 portfolio variations derived from different parameter settings and is evaluated using the Sharpe ratio, Sortino ratio, maximum drawdown, total return, and turnover ratios. The results show that portfolios created with higher trading target ratios and moderate MV optimization significantly outperform the NDX100 index, providing superior risk-adjusted returns and better stability. These findings highlight the effectiveness of combining machine learning-based regressor with classical optimization for dynamic portfolio creation and underscore its practical potential for improving trading decisions in volatile markets.
- 14 March 2026
- Published by Springer Nature in Applied Intelligence
- Vol. 56 (5) , 153
Open AccessA hybrid decision tree-Markowitz framework for intelligent trading portfolio optimization
Predicting stock returns is difficult due to numerous dynamic and interrelated factors such as interest rates, exchange rates, economic conditions, corporate policies, investor behavior, and political developments. This study proposes a hybrid trading strategy that integrates the Decision Tree (DT) algorithm with the Markowitz Mean-Variance (MV) portfolio optimization model to improve prediction accuracy and optimize investment returns. Using data from 94 companies continuously listed on the NASDAQ 100 (NDX100) index between 2015 and 2024, the model uses technical analysis indicators as input for the DT to predict short-term stock returns and then applies MV optimization to allocate weights within dynamically generated portfolios. The empirical analysis includes 64 portfolio variations derived from different parameter settings and is evaluated using the Sharpe ratio, Sortino ratio, maximum drawdown, total return, and turnover ratios. The results show that portfolios created with higher trading target ratios and moderate MV optimization significantly outperform the NDX100 index, providing superior risk-adjusted returns and better stability. These findings highlight the effectiveness of combining machine learning-based regressor with classical optimization for dynamic portfolio creation and underscore its practical potential for improving trading decisions in volatile markets.
- Top Cited PapersOpen Access
- 3 March 2026
- Published by Elsevier in European Journal of Radiology Open
- Vol. 16, 100741
Convolutional neural networks for prostate cancer detection, classification, and segmentation: A systematic review and bibliometric analysis
- 3 March 2026
- Published by Elsevier in European Journal of Radiology Open
- Vol. 16, 100741
Top Cited PapersOpen AccessConvolutional neural networks for prostate cancer detection, classification, and segmentation: A systematic review and bibliometric analysis
- Top Cited PapersOpen Access
- 14 January 2026
- Published by Elsevier in Critical Reviews in Oncology/Hematology
- Vol. 219, 105126
Artificial intelligence applications in ovarian cancer detection: A systematic literature review of deep learning approaches and clinical translation challenges
- 14 January 2026
- Published by Elsevier in Critical Reviews in Oncology/Hematology
- Vol. 219, 105126
Top Cited PapersOpen AccessArtificial intelligence applications in ovarian cancer detection: A systematic literature review of deep learning approaches and clinical translation challenges
- Open Access
- 1 January 2026
- Published by Wiley in Journal of Food Processing and Preservation
- Vol. 2026 (1) , 1973243
Banana Drying Method Selection: A Hybrid Multi‐Criteria Decision Making Approach Integrating SWARA Weighting With MOORA, MARCOS, and PSI Ranking Methods
Banana, a tropical fruit with high initial moisture content and high oxidation susceptibility, requires careful drying method selection to preserve quality attributes. This study applied a hybrid multicriteria decision making (MCDM) framework integrating Step‐wise Weight Assessment Ratio Analysis (SWARA) for criteria weighting with three ranking methods: Multi‐Objective Optimization on the basis of Ratio Analysis (MOORA), Measurement of Alternatives and Ranking according to Compromise Solution (MARCOS), and Preference Selection Index (PSI). Twelve evaluation criteria covering quality, operational, and economic dimensions were evaluated across eight drying alternatives. SWARA weighting identified aroma preservation (10.69%) and nutritional retention (10.69%) as paramount criteria. All three MCDM methods produced identical rankings (Spearman correlation = 1.0, Kendall tau = 1.0), establishing freeze drying as the optimal method (100.00%), followed by vacuum drying (83.81%), heat pump drying (72.19%), dehydrator drying (61.52%), hot air drying (58.55%), microwave drying (53.81%), solar cabinet drying (24.82%), and sun drying (0.00%). Sensitivity analysis across 72 perturbation scenarios revealed zero rank changes, confirming ranking stability. The perfect intermethod consensus strengthens confidence in the recommended technology hierarchy for banana drying applications.
- 1 January 2026
- Published by Wiley in Journal of Food Processing and Preservation
- Vol. 2026 (1) , 1973243
Open AccessBanana Drying Method Selection: A Hybrid Multi‐Criteria Decision Making Approach Integrating SWARA Weighting With MOORA, MARCOS, and PSI Ranking Methods
Banana, a tropical fruit with high initial moisture content and high oxidation susceptibility, requires careful drying method selection to preserve quality attributes. This study applied a hybrid multicriteria decision making (MCDM) framework integrating Step‐wise Weight Assessment Ratio Analysis (SWARA) for criteria weighting with three ranking methods: Multi‐Objective Optimization on the basis of Ratio Analysis (MOORA), Measurement of Alternatives and Ranking according to Compromise Solution (MARCOS), and Preference Selection Index (PSI). Twelve evaluation criteria covering quality, operational, and economic dimensions were evaluated across eight drying alternatives. SWARA weighting identified aroma preservation (10.69%) and nutritional retention (10.69%) as paramount criteria. All three MCDM methods produced identical rankings (Spearman correlation = 1.0, Kendall tau = 1.0), establishing freeze drying as the optimal method (100.00%), followed by vacuum drying (83.81%), heat pump drying (72.19%), dehydrator drying (61.52%), hot air drying (58.55%), microwave drying (53.81%), solar cabinet drying (24.82%), and sun drying (0.00%). Sensitivity analysis across 72 perturbation scenarios revealed zero rank changes, confirming ranking stability. The perfect intermethod consensus strengthens confidence in the recommended technology hierarchy for banana drying applications.
- 17 June 2025
- Published by Elsevier in Clinical Imaging
- Vol. 125, 110542
Deep learning based colorectal cancer detection in medical images: A comprehensive analysis of datasets, methods, and future directions
- 17 June 2025
- Published by Elsevier in Clinical Imaging
- Vol. 125, 110542
Deep learning based colorectal cancer detection in medical images: A comprehensive analysis of datasets, methods, and future directions