Ali Berkay Avci
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
Ali Berkay Avci has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Özge Deniz Toköz
İzmir Institute of Technology
2 shared publications - Gamze Akyol
Department of Interior Architecture and Environmental Design, Faculty of Fine Arts and Architecture, Antalya Bilim University, Akdeniz Bulvari No:290 A, 07190 Dösemealti, Antalya, Türkiye
1 shared publication - Gorkem Aybars Balci
Department of Coaching Education, Faculty of Sport Sciences Ege University Izmir Turkey
1 shared publication Görkem Aybars Balci
Department of Coaching Education, Faculty of Sport Sciences, Ege University, Bornova, Izmir, Türkiye
1 shared publicationHasan Engin Duran
Izmir Institute of Technology, Department of City and Regional Planning, Gülbahçe Campus Urla-İzmir, Turkey
1 shared publication- Muzaffer Colakoglu
Department of Coaching Education, Ege University, Faculty of Sport Sciences, Izmir, Turkey
1 shared publication
Latest Publications
- 15 March 2026
- Published by Politeknik Dergisi in Journal of Polytechnic
- Vol. 29 (2) , 1
A Full Factorial Analysis of Albedo, Window-to-Wall Ratio, and Ventilation on Energy Use and CO2 Concentration in a Mediterranean Apartment
This study investigates the combined impact of wall albedo, window-to-wall ratio, and natural ventilation duration on heating and cooling energy demand and indoor CO2 concentration in a naturally ventilated, well-insulated apartment in Izmir, Türkiye. A validated building energy model was developed using DesignBuilder and calibrated with real indoor and outdoor measurements collected over a three-month period. A full factorial 33 design was applied to evaluate 27 combinations of the three variables. Statistical analyses, including ANOVA and regression, were conducted to determine the significance and direction of each factor’s effects. Results revealed that natural ventilation duration was the most influential parameter, explaining over 94% of the variance in CO2 concentration and having the largest effect on energy demand. Window-to-wall ratio showed significant but seasonally opposing impacts on heating and cooling loads, while wall albedo affected energy demand but had no statistical effect on indoor CO2. The findings highlight the importance of considering design-operational interactions in passive residential strategies. The study offers practical recommendations for energy-efficient and health-conscious retrofits in Mediterranean housing, particularly where mechanical ventilation is absent, and supports the use of factorial simulations for informed decision-making in climate-sensitive design contexts.
- 15 March 2026
- Published by Politeknik Dergisi in Journal of Polytechnic
- Vol. 29 (2) , 1
A Full Factorial Analysis of Albedo, Window-to-Wall Ratio, and Ventilation on Energy Use and CO2 Concentration in a Mediterranean Apartment
This study investigates the combined impact of wall albedo, window-to-wall ratio, and natural ventilation duration on heating and cooling energy demand and indoor CO2 concentration in a naturally ventilated, well-insulated apartment in Izmir, Türkiye. A validated building energy model was developed using DesignBuilder and calibrated with real indoor and outdoor measurements collected over a three-month period. A full factorial 33 design was applied to evaluate 27 combinations of the three variables. Statistical analyses, including ANOVA and regression, were conducted to determine the significance and direction of each factor’s effects. Results revealed that natural ventilation duration was the most influential parameter, explaining over 94% of the variance in CO2 concentration and having the largest effect on energy demand. Window-to-wall ratio showed significant but seasonally opposing impacts on heating and cooling loads, while wall albedo affected energy demand but had no statistical effect on indoor CO2. The findings highlight the importance of considering design-operational interactions in passive residential strategies. The study offers practical recommendations for energy-efficient and health-conscious retrofits in Mediterranean housing, particularly where mechanical ventilation is absent, and supports the use of factorial simulations for informed decision-making in climate-sensitive design contexts.
- Open Access
- 1 January 2026
- Published by Wiley in Indoor Air
- Vol. 2026 (1)
Benchmarking Classical Machine Learning and Hybrid Quantum Approaches for Indoor Thermal Sensation Prediction
Reliable prediction of thermal sensation plays a critical role in enabling energy‐efficient and occupant‐oriented building operation. However, existing approaches remain limited under real‐world conditions. This study establishes a comprehensive and methodologically consistent framework to evaluate the predictive performance of thermal sensation vote (TSV) models by integrating a broad set of classical machine learning algorithms with a hybrid quantum–classical approach. The analysis is based on a dataset of 19,291 observations from naturally ventilated environments, including both environmental and personal variables. A total of 14 regression models were benchmarked using a unified fivefold cross‐validation protocol, followed by hyperparameter optimization of the best‐performing model and a structured feature ablation analysis. In parallel, a hybrid quantum–classical model was developed using parameterized quantum circuits and evaluated under the same experimental conditions to ensure direct comparability. The results show that ensemble‐based classical models outperform all other approaches, with tuned XGBoost achieving the highest predictive performance ( R 2 : 0.386 and RMSE: 0.983). However, improvements from hyperparameter optimization remain marginal, indicating a practical predictive ceiling. The feature ablation analysis reveals that personal variables provide the most significant contribution to prediction accuracy, while derived thermal indicators such as operative temperature offer no additional benefit when their constituent variables are included. The hybrid quantum model demonstrates stable training behavior but significantly lower predictive performance ( R 2 : 0.246 and RMSE: 1.085) and early convergence, suggesting limited representational capacity for tabular and noisy thermal comfort data. The findings indicate that TSV prediction is fundamentally constrained by data characteristics and human variability rather than model complexity. The study highlights the critical importance of occupant‐related variables, identifies diminishing returns from conventional feature engineering, and demonstrates that current quantum machine learning approaches are not yet competitive for this problem domain. These results provide a robust benchmark and emphasize the need for data‐centric and human‐centric modeling strategies to advance thermal comfort prediction.
- 1 January 2026
- Published by Wiley in Indoor Air
- Vol. 2026 (1)
Open AccessBenchmarking Classical Machine Learning and Hybrid Quantum Approaches for Indoor Thermal Sensation Prediction
Reliable prediction of thermal sensation plays a critical role in enabling energy‐efficient and occupant‐oriented building operation. However, existing approaches remain limited under real‐world conditions. This study establishes a comprehensive and methodologically consistent framework to evaluate the predictive performance of thermal sensation vote (TSV) models by integrating a broad set of classical machine learning algorithms with a hybrid quantum–classical approach. The analysis is based on a dataset of 19,291 observations from naturally ventilated environments, including both environmental and personal variables. A total of 14 regression models were benchmarked using a unified fivefold cross‐validation protocol, followed by hyperparameter optimization of the best‐performing model and a structured feature ablation analysis. In parallel, a hybrid quantum–classical model was developed using parameterized quantum circuits and evaluated under the same experimental conditions to ensure direct comparability. The results show that ensemble‐based classical models outperform all other approaches, with tuned XGBoost achieving the highest predictive performance ( R 2 : 0.386 and RMSE: 0.983). However, improvements from hyperparameter optimization remain marginal, indicating a practical predictive ceiling. The feature ablation analysis reveals that personal variables provide the most significant contribution to prediction accuracy, while derived thermal indicators such as operative temperature offer no additional benefit when their constituent variables are included. The hybrid quantum model demonstrates stable training behavior but significantly lower predictive performance ( R 2 : 0.246 and RMSE: 1.085) and early convergence, suggesting limited representational capacity for tabular and noisy thermal comfort data. The findings indicate that TSV prediction is fundamentally constrained by data characteristics and human variability rather than model complexity. The study highlights the critical importance of occupant‐related variables, identifies diminishing returns from conventional feature engineering, and demonstrates that current quantum machine learning approaches are not yet competitive for this problem domain. These results provide a robust benchmark and emphasize the need for data‐centric and human‐centric modeling strategies to advance thermal comfort prediction.
- 13 December 2025
- Published by Taylor & Francis in Architectural Science Review
- p. 1-22
Office layout design factors for enhanced thermal comfort: a CFD-based optimization study using orthogonal arrays
- 13 December 2025
- Published by Taylor & Francis in Architectural Science Review
- p. 1-22
Office layout design factors for enhanced thermal comfort: a CFD-based optimization study using orthogonal arrays
- Open Access
- 10 November 2025
- Published by Periodica Polytechnica Budapest University of Technology and Economics in Periodica Polytechnica Architecture
Digital Twins in Heritage Conservation and Visitor Engagement: Comparative Case Studies from Four Historic Sites
This study explores the application of digital twin technologies in heritage conservation and visitor engagement, focusing on their practical use in preserving and enhancing access to culturally significant sites. Digital twins, which are virtual replicas of physical environments, enable real-time monitoring and simulation, offering innovative tools for conservation management and experiential interpretation. Through a systematic literature review and comparative analysis of four case studies, Pompeii, Notre-Dame, the Colosseum, and Hagia Sophia, this research examines how digital twins are implemented across varying contexts. The findings reveal that digital twins support predictive maintenance, structural monitoring, and restoration planning while also enabling immersive experiences through virtual and augmented reality. These technologies provide remote access, interactive storytelling, and tailored tours, fostering a deeper connection with heritage. In terms of conservation, digital twins support predictive maintenance, structural monitoring, and evidence-based decision-making. The structured comparison highlights how digital twin systems balance preservation needs with modern engagement demands. While challenges such as data accuracy, cultural sensitivity, and technological infrastructure remain, the study concludes that digital twins represent a valuable model for integrating conservation and visitor experience in heritage site management. Future developments in immersive technologies and broader adoption of digital twins could further enhance the management and appreciation of cultural heritage worldwide.
- 10 November 2025
- Published by Periodica Polytechnica Budapest University of Technology and Economics in Periodica Polytechnica Architecture
Open AccessDigital Twins in Heritage Conservation and Visitor Engagement: Comparative Case Studies from Four Historic Sites
This study explores the application of digital twin technologies in heritage conservation and visitor engagement, focusing on their practical use in preserving and enhancing access to culturally significant sites. Digital twins, which are virtual replicas of physical environments, enable real-time monitoring and simulation, offering innovative tools for conservation management and experiential interpretation. Through a systematic literature review and comparative analysis of four case studies, Pompeii, Notre-Dame, the Colosseum, and Hagia Sophia, this research examines how digital twins are implemented across varying contexts. The findings reveal that digital twins support predictive maintenance, structural monitoring, and restoration planning while also enabling immersive experiences through virtual and augmented reality. These technologies provide remote access, interactive storytelling, and tailored tours, fostering a deeper connection with heritage. In terms of conservation, digital twins support predictive maintenance, structural monitoring, and evidence-based decision-making. The structured comparison highlights how digital twin systems balance preservation needs with modern engagement demands. While challenges such as data accuracy, cultural sensitivity, and technological infrastructure remain, the study concludes that digital twins represent a valuable model for integrating conservation and visitor experience in heritage site management. Future developments in immersive technologies and broader adoption of digital twins could further enhance the management and appreciation of cultural heritage worldwide.
- 25 October 2025
- Published by Elsevier in Journal of Building Engineering
- Vol. 114
Federated machine learning for indoor thermal comfort: Real-time zone-based personalization and HVAC control
- 25 October 2025
- Published by Elsevier in Journal of Building Engineering
- Vol. 114
Federated machine learning for indoor thermal comfort: Real-time zone-based personalization and HVAC control
- 15 February 2025
- Published by Taylor & Francis in Building Research & Information
- Vol. 54 (1) , 100-117
Machine learning-based prediction of thermal comfort: exploring building types, climate, ventilation strategies, and seasonal variations
- 15 February 2025
- Published by Taylor & Francis in Building Research & Information
- Vol. 54 (1) , 100-117
Machine learning-based prediction of thermal comfort: exploring building types, climate, ventilation strategies, and seasonal variations