Yazar "Kocak, Burak" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Efficient machine learning models for estimation of compressive strengths of zeolite and diatomite substituting concrete in sodium chloride solution
    (Springer Heidelberg, 2024) Ozcan, Giyasettin; Kocak, Burak; Gulbandilar, Eyyup; Kocak, Yilmaz
    This study implements a set of machine learning algorithms to building material science, which predict the compressive strength of zeolite and diatomite substituting concrete mixes in sodium chloride solution. Particularly, Random Forest, Support Vector Machine, Extreme Gradient Boosting, Light Gradient Boosting, and Categorical Boosting algorithms are exploited and their optimal parameters are tuned. In the training and testing of these models, 28 day, 56 day, and 90 day compressive strength observations of 63 samples of 7 different concrete mixtures substituting Portland cement, zeolite, diatomite, zeolite + diatomite were used. Consequently, compressive strength experimentation results and machine learning predictions were compared through statistical methods such as RMSE, MAPE, and R 2. Results denote that the prediction performance of machine learning is improving with tuned models. Particularly, RMSE, MAPE, R 2 scores of Categorical Boosting are, respectively, 1.15, 1.45%, and 98.03% after parameter tuning design. The results denote that presented machine learning model can provide an advantage in the cost and duration of the compressive strength experiments.
  • Küçük Resim Yok
    Öğe
    Prediction of compressive strengths of pumice-and diatomite-containing cement mortars with artificial intelligence-based applications
    (Elsevier Sci Ltd, 2023) Kocak, Burak; Pinarci, Brahim; Guvenc, Ugur; Kocak, Yilmaz
    In this study, two different Artificial neural networks (ANN) and two different adaptive network-based fuzzy inference systems (ANFIS) models were constructed to predict the compressive strength of 7 different cement mortar samples with or without pumice and/or diatomite on different days. Five parameters including day, PC, pumice, diatomite and water were employed as the inputs, and the compressive strength was used as the output variable. The compressive strengths used in the model construction were obtained from laboratory experiments accounting for a total of 168 data. Statistical methods such as R2, RMS and MAPE preferred in the literature were used to compare the four different models. According to the test results obtained from R2, RMS and MAPE, ANN and ANFIS models were able to make very good predictions performance. For this reason, it can be said that these cement mortars' compressive strength can be estimated with a very small error and in a short time with both ANN and ANFIS models.