Yazar "Isikdag, Umit" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • [ X ]
    Öğe
    Cooling load prediction of a double-story terrace house using ensemble learning techniques and genetic programming with SHAP approach
    (Elsevier Science Sa, 2024) Cakiroglu, Celal; Aydin, Yaren; Bekdas, Gebrail; Isikdag, Umit; Sadeghifam, Aidin Nobahar; Abualigah, Laith
    Since the cooling systems used in buildings in hot climates account for a significant portion of the energy consumption, it is very important for both economy and environment to accurately predict the cooling load and consider it in building designs. This study aimed to maximize energy efficiency by appropriately selecting the features of a building that affect its cooling load. To this end, data-driven, accurate, and accessible tools were developed that enable the prediction of the cooling load of a building by practitioners. The study involves simulating the energy consumption of a mid-rise, double-story terrace house in Malaysia using building information modeling (BIM) and estimating the cooling load using ensemble machine learning models and genetic programming. Categorical Boosting (CatBoost), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Random Forest (RF) models have been developed and made available as an online interactive graphical user interface on the Streamlit platform. Furthermore, the symbolic regression technique has been utilized to obtain a closed-form equation that predicts the cooling load. The dataset used for training the predictive models comprised 94,310 data points with 10 input variables and the cooling load as the output variable. Performance metrics such as the coefficient of determination (R2), root mean squared error (RMSE), and mean absolute error (MAE) were used to measure the predictive model performances. The results of the machine learning models indicated successful prediction, with the CatBoost model achieving the highest score (R2 = 0.9990) among the four ensemble models and the predictive equation. The SHAP analysis determined the aspect ratio of the building as the most impactful feature of the building.
  • [ X ]
    Öğe
    Explainable machine learning models for predicting the axial compression capacity of concrete filled steel tubular columns
    (Elsevier Sci Ltd, 2022) Cakiroglu, Celal; Islam, Kamrul; Bekdas, Gebrail; Isikdag, Umit; Mangalathu, Sujith
    Concrete-filled steel tubular (CFST) columns have been popular in the construction industry due to enhanced mechanical properties such as higher strength and ductility, higher seismic resistance, and aesthetics. Extensive experimental, numerical and analytical studies have been conducted in the past few decades to assess the structural response of CFST columns under various loading conditions. However, there is still uncertainty in predicting the capacity of CFST columns, and most of the current codes are conservative. In this paper, data-driven machine learning (ML) models have been developed to predict the axial compression capacity of rectangular CFST columns. An extensive database of 719 experiments was collected from literature and is randomly used to train, test, and validate the ML models. Seven ML models, namely lasso regression, random forest, Adaptive Boosting (AdaBoost), Gradient Boosting Machine (GBM), Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), and Categorical Gradient Boosting (CatBoost), are evaluated to predict the compression capacity of CFST stub columns under axial load. The performance of the different ML models in predicting the compressive strength of CFST columns is compared by different code equations prevalent in different parts of the world. It is found that LightGBM and CatBoost models performed better with an accuracy of 97.9% and 98.3%, respectively, compared to the existing design codes in predicting the capacity of CFST columns. Feature importance analyses and SHapley Additive explanations (SHAP) explain the ML model performances and make the developed models interpretable. Resistance factor is determined using the best performing ML model for compressive strength prediction of CFST stub columns following AISC 360-16 code provision.