Journal of Construction Engineering, Management & Innovation

Merve Kuru Erdem Osman Gökalp Gülben Çalış

Predicting the thermal comfort of building occupants is of paramount importance in the operation of smart buildings, providing a data-driven approach to control Heating, Ventilation, and Air Conditioning (HVAC) systems for managing occupant thermal comfort and energy use, which aligns with modern sustainability and efficiency goals. Recently, ensemble machine learning (ML)-based thermal comfort prediction models have been proposed to provide more accurate estimation of thermal comfort; however, these efforts often lack a systematic and comprehensive evaluation across a wide range of ML models within a single study. To address this gap, this study presents a systematic comparative analysis of four ensemble ML frameworks (bagging, boosting, stacking, and voting) with six basic ML algorithms (Logistic Regression, K-Nearest Neighbors, Support Vector Machine, Decision Tree, Multilayer Perceptron, and Multinomial Naïve Bayes) and six advanced ensemble ML algorithms (Random Forest, Rotation Forest, Extra Trees, Gradient Boosting Classifier, Histogram Gradient Boosting Classifier, and Extreme Gradient Boosting). The analysis is conducted using the widely recognized ASHRAE Global Thermal Comfort Database II, providing both 3-point and 7-point Thermal Sensation Vote (TSV) predictions. Accuracy, precision, recall and F1 metrics are used for evaluation and 10-fold cross validation is applied for further comparison. The results demonstrate the Histogram Gradient Boosting (HGB) algorithm achieved the highest F1 score (0.638) for 7-point TSV prediction whereas the Random Forest (RF) algorithm provided the highest F1 score (0.549) for 7-point TSV prediction. In practice, these findings suggest that integrating RF and HGB models into Building Management Systems or IoT-based HVAC platforms can support real-time adaptive control, helping practitioners to reduce energy use while maintaining occupant comfort.

https://doi.org/10.31462/jcemi.2025.04346379

Merve Tuna Kayılı Bahar Sultan Qurraie

Achieving Net-Zero Energy Building (NZEB) performance requires a comprehensive approach that integrates both passive and active energy strategies. This study investigates the standalone impact of various passive design measures on reducing heating and lighting energy demands in an existing educational facility located in Safranbolu, Türkiye, a region characterized by a continental climate with mild summers and cold winters. Utilizing dynamic energy simulations conducted via DesignBuilder and the EnergyPlus engine, the research evaluates a range of envelope retrofit strategies, including optimized window-to-wall ratios (WWR), high-performance glazing systems, double-skin façades (DSFs), and advanced insulation materials. The results indicate that while passive envelope enhancements can significantly improve thermal performance, the most effective configuration identified in this case study, combining a cavity wall with aerogel insulation and triple-pane argon-filled low-emissivity glazing, achieved a 34.9% reduction in heating demand under the specific conditions of the building and climate analyzed. While passive strategies effectively reduce energy losses, they are insufficient on their own to eliminate dependence on external energy sources. To overcome this limitation, the integration of active renewable energy systems, such as photovoltaic (PV) panels and solar thermal collectors, is essential. Furthermore, incorporating energy storage technologies and smart energy management systems can enhance system reliability and efficiency. This study underscores that a hybrid approach, combining passive design with active solar technologies, offers the most viable path to NZEB achievement. Notably, the research provides an original and detailed multi-scenario evaluation of passive-only retrofit strategies, quantifying their individual and combined potential prior to the introduction of active energy systems.

https://doi.org/10.31462/jcemi.2025.04380402

Deribe Assefa Aga Berhanu Belayneh Beyene Niels Noorderhaven

Individual job performance is an under-explored issue in the project management literature. This study examines the relationship between work motivation and job performance in a mega hydropower project context. Drawing on self-determination theory, we theorize that work motivation positively affects job performance, and that this relationship is positively moderated by megaproject internal social responsibility (ISR), which refers to voluntary actions of a megaproject organization that target improving the physical and psychological working environment, which in turn aims at enhancing the wellbeing of employees. Following an explanatory and quantitative research design, a questionnaire survey was administered to project employees who worked on a mega hydropower project in Ethiopia. Using a field survey with valid responses from 200 project employees selected on the basis of a simple random sampling technique, the findings of our study, based on Partial Least Squares Structural Equation Modeling (PLS-SEM) using SmartPLS 4 software, reveal that ISR as perceived by project employees enhances the positive association between motivation and job performance. The study, however, did not find a direct relationship between the perceptions of ISR and job performance. The results of the present study are vital for understanding the nuanced boundary conditions under which employee motivation is more associated with job performance in a megaproject context, a topic which is not well addressed empirically in the project management literature. The paper discusses the theoretical and practical implications of these findings.

https://doi.org/10.31462/jcemi.2025.04403423

Gizem Can Sehnaz Cenani

Sustainability reveals the importance of efficiently managing building life cycle processes within the scope of contemporary solutions like the circular and green economies. These solutions take a wider perspective, also caring for ecosystem resilience and human well-being. Hospitals, which include large and diverse groups of end-users, must consider human welfare, a core green economy goal, alongside strict green building requirements. It is believed that designing truly sustainable and healthy hospitals requires prioritizing end-users’ health and wellbeing. This study investigates end-user perceptions of sustainability criteria within hospitals. It evaluates feedback from hospital end-users through two case studies. Data was collected from a total of 208 participants via a survey based on LEED v4 BD+C: Healthcare requirements, targeting long-term and short-term end-users in medium and large-scale hospitals. To calculate the average importance score for each statement according to the total number of responses, the index value based ranking method was used. The findings reveal that while both long-term and short-term hospital end-users prioritized criteria related to Indoor Environmental Quality (IEQ), their specific expectations varied according to the scale of the hospitals. When considering the opinions of short-term and long-term hospital users, it was found that short-term users prioritized the IEQ and Energy and Atmosphere (EA) categories, while long-term users focused more on the IEQ, Sustainable Sites (SS), and Material and Resources (MR) categories. These findings suggest that sustainable hospital designs should consider both end-user perspective and hospital scales. The findings aim to support the design of healthier healthcare buildings and contribute to the ongoing refinement of green building certification standards.

https://doi.org/10.31462/jcemi.2025.04424437

Ahmet Esat Keser Şirin Şevval Uçak Murat Kuruoğlu Onur Behzat Tokdemir

Labor productivity is a critical factor that directly affects project performance in terms of time, cost, and quality. However, accurately predicting this productivity is challenging due to variability in construction site conditions, individual characteristics of the workforce, and environmental factors. In this study, a total of 18 different regression algorithms, including ensemble methods, tree-based structures, linear regression models, support vector regressions, and artificial neural networks, were systematically evaluated to predict productivity. In the modeling process, a multi-source dataset from large-scale energy infrastructure projects was utilized. The data includes attributes such as environmental conditions, team experience, task complexity, and daily production output for six different activity types. All models are trained within a robust framework, featuring a 70% training and 30% testing separation, 10-fold cross-validation, and hyperparameter optimization using GridSearchCV. Performance evaluation is based on metrics such as R², RMSE, and MAE. The results of the comparative analysis revealed that the ensemble models, particularly CatBoost, XGBoost, and Bagging, outperformed the others in almost all activity types, achieving higher generalization accuracy and lower prediction error. Beyond model accuracy, attribute importance analyses also provided estimates of the determinants of productivity. Variables such as task complexity, temperature, and team experience were among the prominent factors. These findings demonstrate that data-driven models can also be applied to identify variables that influence productivity, thereby supporting planning processes. The study contributes to the literature by providing a comprehensive model comparison framework and offering practical implications for productivity management in construction projects.

https://doi.org/10.31462/jcemi.2025.04438476

Beliz Özorhon Uğur İbrahim Yurttutan

The construction industry underpins global development but continues to face challenges such as complexity, fragmentation, and stakeholder misalignment. While project management is critical to improving outcomes, limited empirical research explores how standardized knowledge areas affect success in complex real-world contexts. Despite the widespread adoption of project management practices, their integrated application within Engineering, Procurement, and Construction Management (EPCM) environments remains underexplored. This study addresses this gap by examining how standardized PMBOK® knowledge areas influence project performance in a large-scale EPCM project. This case study evaluates the twelve Project Management Body of Knowledge (PMBOK®) areas, including the Construction Extension, within a major EPCM project—an international airport delivered under a government-funded contract. A mixed-methods design was employed, integrating document analysis, field observation, and interviews with senior personnel. Performance was assessed using a multi-criteria framework based on the Simple Multi-Attribute Rating Technique (SMART), examining both the importance and execution of each knowledge area. Results show cost, schedule, and quality management as the strongest contributors to success, while risk, stakeholder, and procurement management underperformed relative to their strategic importance. Integration and Health, Safety, Security, and Environmental (HSSE) management were moderately effective, supported by Enterprise Resource Planning (ERP) systems and structured planning. The study underscores the critical role of experienced managers in coordinating interdependencies and driving performance. Contributions include a structured evaluation framework, practitioner-focused recommendations to strengthen underperforming areas, and insights for aligning project management practices with performance objectives in complex project environments.

https://doi.org/10.31462/jcemi.2025.04477500

Yasemin Ezgi Akyildiz Emel Sadikoglu Sevilay Demirkesen Chengyi Zhang Harun Turkoglu Atilla Damcı Deniz Besiktepe Uttam Kumar Pal

The construction industry is fragmented and complex. The involvement of multiple stakeholders can lead to disputes that result in serious time and cost burdens. Developing effective strategies to best address the conflicts is significant for the successful completion of projects. Even though there are studies selecting Dispute Resolution Methods (DRMs), the literature lacks a step-by-step methodology for the proper selection of DRMs for contractual and relational conflicts. To address the gap, this study utilizes the Choosing-by-Advantages (CBA) method to select among the DRMs based on a set of identified construction risks. According to the CBA method, alternatives, factors, criteria, attributes, and advantages are determined. The study proposes several factors, including “claims management”, “design management”, “construction management”, “contract”, and “coordination and relationship”. The alternatives are considered as negotiation, mediation, arbitration, and litigation. Thirteen interviews were conducted with industry experts. The findings implied that “negotiation” was the best option regarding the highest Importance of Advantages with the lowest cost. This study contributes to the literature by systematically implementing CBA in dispute resolution to guide industry practitioners in managing conflicts. This study presents a novel application of the CBA method in the context of DRM selection, extending its application beyond the traditional selection problems, such as designer and subcontractor selection. Moreover, the study helps practitioners, mediators, and policymakers assess existing DRMs and select the most suitable option using the CBA framework.

https://doi.org/10.31462/jcemi.2025.04501520

Ebru Kılıç Bakırhan Merve Tuna Kayılı

Fit-out waste generated during building refurbishments has significant environmental consequences, accounting for substantial portions of construction and demolition waste. Over a 50-year lifespan, the total waste generated by a rentable office was found to be approximately four times higher than that of a standard office, while implementing open-plan layouts and movable partitions reduced embodied energy by up to 61.3% and embodied energy loss by 84.3%, respectively. This study investigates the effectiveness of flexible interior strategies—open-plan layouts and movable partition systems—in mitigating the environmental impacts associated with fit-out waste in rentable offices. The analysis, structured around three hypotheses and four office typologies, covers the production, replacement, and refurbishment stages of the building life cycle and evaluates total waste, life cycle embodied energy (LCEE), and embodied carbon (EC). The findings highlight that flexibility-oriented design strategies can significantly reduce material turnover and resource inefficiency in the building sector. However, strategies such as recycling, reuse, and the economic aspects of the interventions are excluded from the scope of this study.

https://doi.org/10.31462/jcemi.2025.04521541