| People | Locations | Statistics |
|---|---|---|
| Naji, M. |
| |
| Motta, Antonella |
| |
| Aletan, Dirar |
| |
| Mohamed, Tarek |
| |
| Ertürk, Emre |
| |
| Taccardi, Nicola |
| |
| Kononenko, Denys |
| |
| Petrov, R. H. | Madrid |
|
| Alshaaer, Mazen | Brussels |
|
| Bih, L. |
| |
| Casati, R. |
| |
| Muller, Hermance |
| |
| Kočí, Jan | Prague |
|
| Šuljagić, Marija |
| |
| Kalteremidou, Kalliopi-Artemi | Brussels |
|
| Azam, Siraj |
| |
| Ospanova, Alyiya |
| |
| Blanpain, Bart |
| |
| Ali, M. A. |
| |
| Popa, V. |
| |
| Rančić, M. |
| |
| Ollier, Nadège |
| |
| Azevedo, Nuno Monteiro |
| |
| Landes, Michael |
| |
| Rignanese, Gian-Marco |
|
Alyami, Mana
in Cooperation with on an Cooperation-Score of 37%
Topics
Publications (3/3 displayed)
- 2024Estimating Compressive Strength of Concrete Containing Rice Husk Ash Using Interpretable Machine Learning-based Models
- 2023Influence of Heat–Cool Cyclic Exposure on the Performance of Fiber-Reinforced High-Strength Concretecitations
- 2023Prediction of compressive strength of two-stage (preplaced aggregate) concrete using gene expression programming and random forest
Places of action
| Organizations | Location | People |
|---|
document
Estimating Compressive Strength of Concrete Containing Rice Husk Ash Using Interpretable Machine Learning-based Models
Abstract
The construction sector is a major contributor to global greenhouse gas emissions. Using recycled and waste materials in concrete is a practical solution to address environmental challenges. Currently, agricultural waste is widely used as a substitute for cement in the production of eco-friendly concrete. However, traditional methods for assessing the strength of such materials are both expensive and time-consuming. Therefore, this study uses machine learning techniques to develop prediction models for the compressive strength (CS) of rice husk ash (RHA) concrete. The ML techniques used in the present study include random forest (RF), light gradient boosting machine (LightGBM), ridge regression, and extreme gradient boosting (XGBoost). A total of 348 values of CS were collected from the experimental studies, and five characteristics of RHA concrete were taken as input variables. For the performance assessment of the models, multiple statistical metrics were used. During the training phase, the correlation coefficients (R) obtained for ridge regression, RF, XGBoost, and LightGBM were 0.943, 0.981, 0.985, and 0.996, respectively. In the testing set, these values demonstrated even higher performance, with correlation coefficients of 0.971, 0.993, 0.992, and 0.998 for ridge regression, RF, XGBoost, and LightGBM, respectively. The statistical analysis revealed that the LightGBM model outperformed other models, whereas the ridge regression model exhibited comparatively lower accuracy. SHapley Additive exPlanation (SHAP) method was employed for the interpretability of the developed model. The SHAP analysis revealed that water-to-cement is a controlling parameter in estimating the CS of RHA concrete. In conclusion, this study provides valuable guidance for builders and researchers to estimate the CS of RHA concrete. However, it is suggested that more input variables be incorporated and hybrid models utilized to further enhance the reliability and precision of the models.