Bora Öçal
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Bora Öçal has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Oğuzhan Kilim
Department of Cloud Computing Isparta Vacational School of Information Tehnologies, Isparta University of Applied Sciences, Isparta, Türkiye
2 shared publications - Oğuzhan Çarikçi
Süleyman Demirel Üniversitesi
2 shared publications - Ayhan Kuloğlu
Department of Accounting and Taxation, Nevşehir Vocational School, Nevşehir Hacı Bektaş Veli University, Nevşehir 50300, Turkey
1 shared publication - Canan Çitil Akyol
Cumhuriyet University
1 shared publication - Enes Açıkgözoğlu
Isparta University of Applied Sciences
1 shared publication - Erdal Dursun
International Science and Technology University, Warsaw, Poland
1 shared publication
Latest Publications
- 12 October 2026
- Published by Springer Nature in Soft Computing
- Vol. 30 (10) , 7181-7202
Blockchain-assisted shrimp freshness monitoring system using AI and IPFS in cold chain logistics
- 12 October 2026
- Published by Springer Nature in Soft Computing
- Vol. 30 (10) , 7181-7202
Blockchain-assisted shrimp freshness monitoring system using AI and IPFS in cold chain logistics
- 13 September 2026
- Published by Erzurum Kultur ve Egitim Vakfi in EKEV Akademi Dergisi
- No. 107,p. 369-394
FACTORS CONSTRAINING OPERATIONAL EFFICIENCY IN MARITIME TRANSPORTATION: A COMPARATIVE ANALYSIS OF QUANTITATIVE DECISION SUPPORT MODELS AND FIELD REALITIES
This study aims to identify the key risk factors that constrain operational efficiency in international maritime transport and to conduct a comparative analysis of the performance of the six continents addressed in line with these factors. The research is based on a hybrid research design that combines qualitative field observations with quantitative decision support models. Within the scope of the study, seven key criteria were considered: port congestion, bureaucratic barriers, security/piracy, technical and fuel issues, personnel issues, environmental conditions, and geopolitical risks. Based on these criteria, Europe, North America, South America, Asia, Africa, and Oceania were compared in terms of operational risks. The research working group consisted of three senior ship captains with a cumulative 60 years of sectoral experience. Semi-structured interviews and pairwise comparison matrices were used as data collection tools. In the analysis of the data, the Best-Worst Method (BWM) was applied for criterion weighting and the Simple Additive Weighting (SAW) method was applied for continent ranking, and the findings were validated using the Analytic Hierarchy Process (AHP) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) methods. According to the analysis results, bureaucratic barriers have been identified as the most dominant operational constraint in maritime trade. This finding indicates that the fundamental disruptions in the sector stem from the costs of informal transactions, expressed through concepts such as the "Marlboro Canal," rather than technical inadequacies. In regional analyses, Europe was found to be the continent with the highest operational performance, while Asia and Africa were identified as the regions with the highest risk intensity. In light of the research findings, it is recommended that "Single Window" digital declaration systems, which minimise the risk of corruption, be widely implemented, particularly in developing ports, and that security protocols be made more transparent.
- 13 September 2026
- Published by Erzurum Kultur ve Egitim Vakfi in EKEV Akademi Dergisi
- No. 107,p. 369-394
FACTORS CONSTRAINING OPERATIONAL EFFICIENCY IN MARITIME TRANSPORTATION: A COMPARATIVE ANALYSIS OF QUANTITATIVE DECISION SUPPORT MODELS AND FIELD REALITIES
This study aims to identify the key risk factors that constrain operational efficiency in international maritime transport and to conduct a comparative analysis of the performance of the six continents addressed in line with these factors. The research is based on a hybrid research design that combines qualitative field observations with quantitative decision support models. Within the scope of the study, seven key criteria were considered: port congestion, bureaucratic barriers, security/piracy, technical and fuel issues, personnel issues, environmental conditions, and geopolitical risks. Based on these criteria, Europe, North America, South America, Asia, Africa, and Oceania were compared in terms of operational risks. The research working group consisted of three senior ship captains with a cumulative 60 years of sectoral experience. Semi-structured interviews and pairwise comparison matrices were used as data collection tools. In the analysis of the data, the Best-Worst Method (BWM) was applied for criterion weighting and the Simple Additive Weighting (SAW) method was applied for continent ranking, and the findings were validated using the Analytic Hierarchy Process (AHP) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) methods. According to the analysis results, bureaucratic barriers have been identified as the most dominant operational constraint in maritime trade. This finding indicates that the fundamental disruptions in the sector stem from the costs of informal transactions, expressed through concepts such as the "Marlboro Canal," rather than technical inadequacies. In regional analyses, Europe was found to be the continent with the highest operational performance, while Asia and Africa were identified as the regions with the highest risk intensity. In light of the research findings, it is recommended that "Single Window" digital declaration systems, which minimise the risk of corruption, be widely implemented, particularly in developing ports, and that security protocols be made more transparent.
- Open Access
- 6 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (17) , 8861
ETA Prediction in Last-Mile Logistics Under Domain Shift: From Zero-Shot Failure to Few-Shot Recovery
Estimated time of arrival (ETA) models for last-mile delivery are commonly evaluated within the same data source, leaving their reliability under cross-dataset distribution shift insufficiently characterized. This study evaluates internal generalization, independent external transfer, limited target-domain supervision, support-set sensitivity, and uncertainty calibration using five LaDe-D cities as the source domain and an independent planned-versus-actual route dataset from two countries as the target domain. CatBoost, LightGBM, XGBoost, and an uncertainty-aware neural reference model (DG-UCETA) were evaluated under a harmonized 21-feature Common-Core representation. External zero-shot MAE reached 150.76–185.47 min, despite substantially lower internal errors. A predefined 1% target-support condition reduced MAE to 57.60–64.87 min, although five independent support-set selections revealed substantial instability in this ultra-low-data regime; performance became markedly more stable at 5–10% support. A matched target-only control further showed that source pretraining improved MAE in only 4 of 16 model-support combinations, indicating that much of the observed recovery resulted from exposure to labeled target-domain data rather than from source initialization itself. Grouped feature ablation also localized the Common-Extended negative-transfer effect primarily to speed-derived variables, with speed-history features increasing external MAE by 28.02 min relative to Common-Core. Conformal recalibration improved coverage but did not correct systematic point-prediction bias. These findings indicate that representative target-domain supervision, feature compatibility, and adaptation stability are more critical to reliable cross-domain ETA deployment than architectural complexity alone.
- 6 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (17) , 8861
Open AccessETA Prediction in Last-Mile Logistics Under Domain Shift: From Zero-Shot Failure to Few-Shot Recovery
Estimated time of arrival (ETA) models for last-mile delivery are commonly evaluated within the same data source, leaving their reliability under cross-dataset distribution shift insufficiently characterized. This study evaluates internal generalization, independent external transfer, limited target-domain supervision, support-set sensitivity, and uncertainty calibration using five LaDe-D cities as the source domain and an independent planned-versus-actual route dataset from two countries as the target domain. CatBoost, LightGBM, XGBoost, and an uncertainty-aware neural reference model (DG-UCETA) were evaluated under a harmonized 21-feature Common-Core representation. External zero-shot MAE reached 150.76–185.47 min, despite substantially lower internal errors. A predefined 1% target-support condition reduced MAE to 57.60–64.87 min, although five independent support-set selections revealed substantial instability in this ultra-low-data regime; performance became markedly more stable at 5–10% support. A matched target-only control further showed that source pretraining improved MAE in only 4 of 16 model-support combinations, indicating that much of the observed recovery resulted from exposure to labeled target-domain data rather than from source initialization itself. Grouped feature ablation also localized the Common-Extended negative-transfer effect primarily to speed-derived variables, with speed-history features increasing external MAE by 28.02 min relative to Common-Core. Conformal recalibration improved coverage but did not correct systematic point-prediction bias. These findings indicate that representative target-domain supervision, feature compatibility, and adaptation stability are more critical to reliable cross-domain ETA deployment than architectural complexity alone.
- 30 August 2026
- Published by Suleyman Demirel University Visionary Journal in Süleyman Demirel Üniversitesi Vizyoner Dergisi
- Vol. 17 (51) , 777-796
Performance Comparison of Machine Learning-Based Regression Models in Predicting Türkiye’s Exports
The study aims to identify the most suitable machine learning-based regression model that can be used to predict the future course of exports by analysing the macroeconomic indicators affecting Türkiye’s export performance and through variables with a high correlation with exports. The study utilises 12 different macroeconomic variables related to the Turkish and global economies, and the relationship between these variables and exports are examined using correlation analysis. For the variables showing a strong relationship with exports, the linear model LASSO is applied alongside four different ensemble-based machine learning algorithms, using the Python programming language. To obtain unbiased and robust predictive accuracy, model performances are evaluated using a cross-validation framework. The results demonstrate that all models achieve high predictive performance; however, LASSO, in particular, provides the strongest overall accuracy with near-perfect explanatory power and a low error rate. Among the ensemble methods, Gradient Boosting emerges as the approach with the best performance. The findings demonstrate that regression methods can effectively capture Türkiye’s export dynamics and provide a reliable foundation for export forecasts. The study contributes to the literature from both methodological and practical perspectives in understanding Türkiye’s export dynamics, whilst also supporting data-driven policy development for decision-makers.
- 30 August 2026
- Published by Suleyman Demirel University Visionary Journal in Süleyman Demirel Üniversitesi Vizyoner Dergisi
- Vol. 17 (51) , 777-796
Performance Comparison of Machine Learning-Based Regression Models in Predicting Türkiye’s Exports
The study aims to identify the most suitable machine learning-based regression model that can be used to predict the future course of exports by analysing the macroeconomic indicators affecting Türkiye’s export performance and through variables with a high correlation with exports. The study utilises 12 different macroeconomic variables related to the Turkish and global economies, and the relationship between these variables and exports are examined using correlation analysis. For the variables showing a strong relationship with exports, the linear model LASSO is applied alongside four different ensemble-based machine learning algorithms, using the Python programming language. To obtain unbiased and robust predictive accuracy, model performances are evaluated using a cross-validation framework. The results demonstrate that all models achieve high predictive performance; however, LASSO, in particular, provides the strongest overall accuracy with near-perfect explanatory power and a low error rate. Among the ensemble methods, Gradient Boosting emerges as the approach with the best performance. The findings demonstrate that regression methods can effectively capture Türkiye’s export dynamics and provide a reliable foundation for export forecasts. The study contributes to the literature from both methodological and practical perspectives in understanding Türkiye’s export dynamics, whilst also supporting data-driven policy development for decision-makers.
- 31 July 2026
- Published by International Journal of Economics and Administrative Studies in Uluslararası İktisadi ve İdari İncelemeler Dergisi
- No. 52,p. 165-182
A MACHINE LEARNING APPROACH BASED ON SYNTHETIC DATA FOR ESTIMATING CARBON FOOTPRINT IN LOGISTICS PROCESSES
This study aims to estimate the carbon footprint arising from logistics processes using machine learning methods based on synthetic data and to identify the most suitable model for this purpose. Due to data access limitations, a multidimensional synthetic dataset was generated using variables like transport distance, cargo weight, transport mode, fuel type, traffic density, weather, and vehicle characteristics. Carbon emissions were calculated via an activity-based approach. The study comparatively evaluated six algorithms: Linear Regression, Random Forest, Extra Trees, Gradient Boosting, Support Vector Regression, and XGBoost. Findings indicate that tree-based ensemble learning models outperformed classical methods in predicting emissions. Among all models, XGBoost delivered the highest performance with an R² value of 0.9945 and minimal error rates. The results demonstrate that synthetic data provides an effective alternative for estimating carbon footprints in logistics process where access to real-world data is limited, and that it can contribute to sustainable logistics decision-making processes.
- 31 July 2026
- Published by International Journal of Economics and Administrative Studies in Uluslararası İktisadi ve İdari İncelemeler Dergisi
- No. 52,p. 165-182
A MACHINE LEARNING APPROACH BASED ON SYNTHETIC DATA FOR ESTIMATING CARBON FOOTPRINT IN LOGISTICS PROCESSES
This study aims to estimate the carbon footprint arising from logistics processes using machine learning methods based on synthetic data and to identify the most suitable model for this purpose. Due to data access limitations, a multidimensional synthetic dataset was generated using variables like transport distance, cargo weight, transport mode, fuel type, traffic density, weather, and vehicle characteristics. Carbon emissions were calculated via an activity-based approach. The study comparatively evaluated six algorithms: Linear Regression, Random Forest, Extra Trees, Gradient Boosting, Support Vector Regression, and XGBoost. Findings indicate that tree-based ensemble learning models outperformed classical methods in predicting emissions. Among all models, XGBoost delivered the highest performance with an R² value of 0.9945 and minimal error rates. The results demonstrate that synthetic data provides an effective alternative for estimating carbon footprints in logistics process where access to real-world data is limited, and that it can contribute to sustainable logistics decision-making processes.
- Open Access
- 3 April 2026
- Published by Fiscaoeconomia in Fiscaoeconomia
- Vol. 10 (2) , 1-18
Evaluation of the Structural Competitiveness of Major Container Ports in Europe Using a Hybrid Multi-Criteria Decision-Making Approach (CRITIC-TOPSIS-SAW)
This study aims to evaluate the infrastructural competitiveness of Europe’s ten largest container ports using a quantitative approach and to identify the key infrastructure components that determine it. The study examines critical criteria such as quay length, maximum depth, number of cranes, terminal area, and annual capacity. Methodologically, a hybrid Multi-Criteria Decision Making (MCDM) approach was employed, incorporating CRITIC for the objective weighting of criteria and SAW and TOPSIS methods for ranking port performances. The findings revealed that the number of cranes (27.10%) and maximum depth (22.96%) were the most distinctive factors in the structural competitiveness of ports. According to the performance ranking, both SAW and TOPSIS results identified the ports of Antwerp-Bruges and Rotterdam as the top two ports with the strongest infrastructure in Europe. The high level of agreement obtained among different ranking methods indicates that the findings are consistent and robust in terms of sensitivity analysis. Moreover, this situation is also supported by the value of 0.9879 for the Spearman Rank Correlation Coefficient. Consequently, it is recommended that port authorities and decision-makers prioritize strategic investments not only in terms of physical space size but also in terms of crane capacity, which increases operational speed, and depth increases suitable for large vessels.
- 3 April 2026
- Published by Fiscaoeconomia in Fiscaoeconomia
- Vol. 10 (2) , 1-18
Open AccessEvaluation of the Structural Competitiveness of Major Container Ports in Europe Using a Hybrid Multi-Criteria Decision-Making Approach (CRITIC-TOPSIS-SAW)
This study aims to evaluate the infrastructural competitiveness of Europe’s ten largest container ports using a quantitative approach and to identify the key infrastructure components that determine it. The study examines critical criteria such as quay length, maximum depth, number of cranes, terminal area, and annual capacity. Methodologically, a hybrid Multi-Criteria Decision Making (MCDM) approach was employed, incorporating CRITIC for the objective weighting of criteria and SAW and TOPSIS methods for ranking port performances. The findings revealed that the number of cranes (27.10%) and maximum depth (22.96%) were the most distinctive factors in the structural competitiveness of ports. According to the performance ranking, both SAW and TOPSIS results identified the ports of Antwerp-Bruges and Rotterdam as the top two ports with the strongest infrastructure in Europe. The high level of agreement obtained among different ranking methods indicates that the findings are consistent and robust in terms of sensitivity analysis. Moreover, this situation is also supported by the value of 0.9879 for the Spearman Rank Correlation Coefficient. Consequently, it is recommended that port authorities and decision-makers prioritize strategic investments not only in terms of physical space size but also in terms of crane capacity, which increases operational speed, and depth increases suitable for large vessels.
- Open Access
- 28 January 2026
- Published by Electronic Journal of Social Sciences in Elektronik Sosyal Bilimler Dergisi
- Vol. 25 (1) , 73-91
Türkiye ve G8 Ülkelerinin İhracat Taşıma Maliyetlerinin Çok Kriterli Karar Verme Yöntemleri İle Analizi
Ülkelerin taşımacılık şekillerinin maliyet yapıları, küresel rekabet açısından kritik öneme sahiptir. Bu çalışmanın amacı, büyük ekonomilere sahip G8 ülkeleri ve gelişen bir ekonomiye sahip olan Türkiye’nin ihracat taşımalarında kullandıkları taşımacılık şekillerinin birim taşıma maliyetlerini, çok kriterli karar verme yöntemlerinden Entropi ve Gri İlişkisel Analiz yöntemleri ile analiz ederek, bu ülkeleri taşıma maliyetleri açısından değerlendirmektir. Çalışmada, ülkelerin taşıma şekillerine göre 2016-2021 yıllarına ait ihracat taşımalarının maliyet verileri kullanılmıştır. Çalışma kapsamında taşıma şekillerinin önem ağırlıkları, Entropi yöntemi ile analiz edilmiş ve elde edilen önem ağırlıklarına göre ülkeleri, taşıma maliyetleri açısından değerlendirmek için Gri ilişkisel Analiz yöntemi uygulanmıştır. Çalışma sonucunda kriter ağırlığı en yüksek olan taşımacılık şeklinin diğer modlar olduğu tespit edilmiştir. Gri İlişkisel Analiz yöntemi sonucunda ise taşıma maliyetleri açısından en başarılı ülkenin Rusya, en başarısız ülkenin ise Japonya olduğu tespit edilmiştir.
- 28 January 2026
- Published by Electronic Journal of Social Sciences in Elektronik Sosyal Bilimler Dergisi
- Vol. 25 (1) , 73-91
Open AccessTürkiye ve G8 Ülkelerinin İhracat Taşıma Maliyetlerinin Çok Kriterli Karar Verme Yöntemleri İle Analizi
Ülkelerin taşımacılık şekillerinin maliyet yapıları, küresel rekabet açısından kritik öneme sahiptir. Bu çalışmanın amacı, büyük ekonomilere sahip G8 ülkeleri ve gelişen bir ekonomiye sahip olan Türkiye’nin ihracat taşımalarında kullandıkları taşımacılık şekillerinin birim taşıma maliyetlerini, çok kriterli karar verme yöntemlerinden Entropi ve Gri İlişkisel Analiz yöntemleri ile analiz ederek, bu ülkeleri taşıma maliyetleri açısından değerlendirmektir. Çalışmada, ülkelerin taşıma şekillerine göre 2016-2021 yıllarına ait ihracat taşımalarının maliyet verileri kullanılmıştır. Çalışma kapsamında taşıma şekillerinin önem ağırlıkları, Entropi yöntemi ile analiz edilmiş ve elde edilen önem ağırlıklarına göre ülkeleri, taşıma maliyetleri açısından değerlendirmek için Gri ilişkisel Analiz yöntemi uygulanmıştır. Çalışma sonucunda kriter ağırlığı en yüksek olan taşımacılık şeklinin diğer modlar olduğu tespit edilmiştir. Gri İlişkisel Analiz yöntemi sonucunda ise taşıma maliyetleri açısından en başarılı ülkenin Rusya, en başarısız ülkenin ise Japonya olduğu tespit edilmiştir.
- Open Access
- 8 December 2025
- Published by International Journal of Engineering and Innovative Research in International Journal of Engineering and Innovative Research
- Vol. 7 (2) , 128-137
ENHANCING REVERSE LOGISTICS EFFICIENCY THROUGH AI-SUPPORTED PARCEL DAMAGE CLASSIFICATION
This study introduces an automated analysis method that uses AI and image processing to check the physical condition of boxes, aiming to support reverse logistics in cargo transport. The system processes images of cardboard boxes moving along a conveyor belt, using techniques like background removal, masking, and morphological operations to calculate damage scores. Based on these scores, it can accurately sort boxes into three categories: “Intact,” “Slightly Damaged,” and “Severely Damaged.” The low variance in the results shows the model is stable and consistent in its assessments. Compared to manual checks, this approach is faster, more reliable, and more structured—helping lower reverse logistics costs and improve customer satisfaction. Overall, the study shows how AI-driven image analysis can boost both efficiency and service quality in the logistics industry.
- 8 December 2025
- Published by International Journal of Engineering and Innovative Research in International Journal of Engineering and Innovative Research
- Vol. 7 (2) , 128-137
Open AccessENHANCING REVERSE LOGISTICS EFFICIENCY THROUGH AI-SUPPORTED PARCEL DAMAGE CLASSIFICATION
This study introduces an automated analysis method that uses AI and image processing to check the physical condition of boxes, aiming to support reverse logistics in cargo transport. The system processes images of cardboard boxes moving along a conveyor belt, using techniques like background removal, masking, and morphological operations to calculate damage scores. Based on these scores, it can accurately sort boxes into three categories: “Intact,” “Slightly Damaged,” and “Severely Damaged.” The low variance in the results shows the model is stable and consistent in its assessments. Compared to manual checks, this approach is faster, more reliable, and more structured—helping lower reverse logistics costs and improve customer satisfaction. Overall, the study shows how AI-driven image analysis can boost both efficiency and service quality in the logistics industry.
- 7 April 2023
- Published by Academician Publishing
- p. 81-98
Logistics Centre Location Selection Based on Logistics Costs: An Application in Isparta
The aim of this study is to select a logistics centre location in Isparta province within the borders of Turkey based on logistics costs. Analytical Hierarchy Process (AHP) method and TOPSIS method were used in the study. Firstly, 5 logistics costs that are thought to affect the logistics centre location selection were determined and the importance levels of logistics costs were calculated by AHP method. Afterwards, 3 possible logistics centre locations in Isparta province were determined and the most suitable logistics centre location was calculated by TOPSIS method. As a result of the study, it was determined that the most suitable logistics centre location in Isparta is Keçiborlu district.
- 7 April 2023
- Published by Academician Publishing
- p. 81-98
Logistics Centre Location Selection Based on Logistics Costs: An Application in Isparta
The aim of this study is to select a logistics centre location in Isparta province within the borders of Turkey based on logistics costs. Analytical Hierarchy Process (AHP) method and TOPSIS method were used in the study. Firstly, 5 logistics costs that are thought to affect the logistics centre location selection were determined and the importance levels of logistics costs were calculated by AHP method. Afterwards, 3 possible logistics centre locations in Isparta province were determined and the most suitable logistics centre location was calculated by TOPSIS method. As a result of the study, it was determined that the most suitable logistics centre location in Isparta is Keçiborlu district.
- 7 April 2023
- Published by Academician Publishing
Current Studies in Social Sciences VI