Yazar "Gorecki, Jaroslaw" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • [ X ]
    Öğe
    Comparison of Nature-Inspired Optimization Models and Robust Machine-Learning Approaches in Predicting the Sustainable Building Energy Consumption: Case of Multivariate Energy Performance Dataset
    (MDPI, 2025) Keles, Mumine Kaya; Keles, Abdullah Emre; Kavak, Elif; Gorecki, Jaroslaw
    Accurate prediction of building energy loads is essential for smart buildings and sustainable energy management. While machine learning (ML) approaches outperform traditional statistical models at capturing nonlinear relationships, most studies primarily optimize prediction accuracy, overlooking the importance of computational efficiency and feature compactness, which are critical in real-time, resource-constrained environments. This study aims to evaluate whether hybrid nature-inspired feature-selection techniques can enhance the accuracy and computational efficiency of ML-based building energy load prediction. Using the UCI Energy Efficiency dataset, eight ML models (LightGBM, CatBoost, XGBoost, Decision Tree, Random Forest, Extra Trees, Linear Regression, Support Vector Regression) were trained under feature subsets obtained from the Butterfly Optimization Algorithm (BOA), Grey Wolf Optimization Algorithm (GWO), and a hybrid BOA-GWO approach. Model performance was evaluated using three metrics (MAE, RMSE, and R2), along with training time, prediction time, and the number of selected features. The results show that gradient-boosting models consistently yield the highest accuracy, with CatBoost achieving an R2 of 0.99 or higher. The proposed hybrid BOA-GWO method achieved competitive accuracy with fewer features and reduced training time, demonstrating its suitability for efficient ML deployment in smart building environments. Rather than proposing a new metaheuristic algorithm, this study contributes by adapting a hybrid BOA-GWO feature-selection strategy to the building energy domain and evaluating its benefits under a multi-criteria performance framework. The findings support the practical adoption of hybrid feature-selection-supported ML pipelines for intelligent building systems, energy management platforms, and IoT-based real-time applications.
  • [ X ]
    Öğe
    Determination of Green Building Awareness: A Study in Turkey
    (Mdpi, 2022) Keles, Abdullah Emre; Onen, Ecem; Gorecki, Jaroslaw
    The building sector is the world's most significant energy consumer. In addition to that, water consumption and increased waste are some of the most significant issues. Owing to the need to find a solution to this problem, the concept of green buildings has emerged. Green buildings are building types that consume less energy and are constructed with recyclable materials, in harmony with nature. The adoption of the concept of green building in societies is very important in this regard. This study aimed to understand the awareness level of people about green buildings. Its scope was to determine the level of awareness of people living in buildings with and without an energy identity certificate in Adana. The results were created in Microsoft Excel, and the survey questions were measured using SPSS. Data analysis was performed by the WEKA tool using the association rule mining method. According to the result, most of the participants did not have sufficient information about the subjects. The results show that nowadays, most people do not understand this building type and what it means to the next generation.
  • [ X ]
    Öğe
    Make saving crucial again: building energy efficiency awareness of people living in urban areas
    (Taylor & Francis Ltd, 2022) Keles, Abdullah Emre; Onen, Ecem; Gorecki, Jaroslaw
    Construction is one of the most energy-intensive sectors in the world. To scale down the energy demand of the building sector, some changes must be made. Formal exemplifications of this need can be seen in recent changes in the law in different countries. The energy identity/performance certificate contains requirements about buildings' energy consumption in Turkey, and the Energy Performance Regulation in Buildings is mandatory from 01.01.2020. Moreover, it aimed to measure the level of awareness of individuals in saving energy. Face-to-face surveys were conducted with the use of a questionnaire with individuals residing in Adana's pilot region on the awareness of similar issues such as green buildings and energy efficiency, especially energy identity/performance certificate. The survey results were prepared in Microsoft Excel, and the reliability of the survey questions was measured with the help of the SPSS (Statistical Package for the Social Sciences) program. The analysis of the data was obtained from WEKA (Waikato Environment for Knowledge Analysis). Association rule extraction, which is one of the data mining methods, was used in the analysis. Based on the findings, it was seen that most of the individuals did not have enough information about the topics in the survey.
  • [ X ]
    Öğe
    Use of Project Management Knowledge Areas in Civil Infrastructure Projects: Implications for Sustainability Assessment and Risk Analysis
    (MDPI, 2025) Keles, Abdullah Emre; Gulek, Gizem Gorkem; Gorecki, Jaroslaw
    The success of civil infrastructure projects hinges on effective project management. Building on the PMBOK (R) Guide framework, this study investigates how project management knowledge areas are used in practice and how their use relates to the integration of sustainability and risk-management principles. 272 construction professionals in T & uuml;rkiye were surveyed and their responses were analyzed using reliability testing, normality checks, and a combination of non-parametric tests (Mann-Whitney U, Kruskal-Wallis) and ANOVA. There were found significant differences in perceived use of knowledge areas by education level, project role, project profile, and prior project-management training; in applied practice, company profile explains variation, whereas project type does not. The results indicate that wider, more systematic adoption-particularly in integration, schedule/time, quality, and risk-supports transparent, traceable processes aligned with sustainability objectives. These behavioral determinants were interpreted as enablers of life-cycle sustainability assessment and risk-informed decision making across civil-infrastructure contexts. There were discussed managerial and policy implications for asset owners and contractors, identifying leverage points for training and capability building, and outlining how standardized use of PMBOK knowledge areas can accelerate sustainability assessment and risk analysis in practice.