A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Bagging vs. Boosting: A Comparative Study on Predicting the Compressive Strength of Geopolymer Concrete
Economical and social transformation are significantly required to face climate challenges, it is crucial to adopt innovative approaches to minimize the carbon footprint of building materials. Geopolymer concrete is a promising alternative to traditional Portland cement-based concrete, as it emits significantly lower amounts of carbon dioxide. However, there is still a need for further research to standardize the production and usage of Geopolymer concrete. With the increasing use of Artificial Intelligence in various fields, there is a need to leverage this technology to improve the accuracy and efficiency in materials science. This paper focuses on the application of Ensemble methods in understanding Geopolymer concrete using Artificial Intelligence (AI), a comparative study of Bagging and Boosting algorithms is presented here for predicting the compressive strength of Geopolymer concrete mixture; in specific Random Forest and Gradient Boost models respectively. The study evaluates the performance of these two approaches on a dataset of different mix compositions, comparing their accuracy and efficiency. The results show that the Boosting algorithm outperforms the Bagging algorithm, achieving an accuracy rate of 92%.
Bagging vs. Boosting: A Comparative Study on Predicting the Compressive Strength of Geopolymer Concrete
Economical and social transformation are significantly required to face climate challenges, it is crucial to adopt innovative approaches to minimize the carbon footprint of building materials. Geopolymer concrete is a promising alternative to traditional Portland cement-based concrete, as it emits significantly lower amounts of carbon dioxide. However, there is still a need for further research to standardize the production and usage of Geopolymer concrete. With the increasing use of Artificial Intelligence in various fields, there is a need to leverage this technology to improve the accuracy and efficiency in materials science. This paper focuses on the application of Ensemble methods in understanding Geopolymer concrete using Artificial Intelligence (AI), a comparative study of Bagging and Boosting algorithms is presented here for predicting the compressive strength of Geopolymer concrete mixture; in specific Random Forest and Gradient Boost models respectively. The study evaluates the performance of these two approaches on a dataset of different mix compositions, comparing their accuracy and efficiency. The results show that the Boosting algorithm outperforms the Bagging algorithm, achieving an accuracy rate of 92%.
Bagging vs. Boosting: A Comparative Study on Predicting the Compressive Strength of Geopolymer Concrete
Belal, Aya (author) / El-Tair, A. Maher (author) / Mashaly, Maggie Ahmed (author)
2023-10-22
440228 byte
Conference paper
Electronic Resource
English
Predicting compressive strength of geopolymer concrete using NDT techniques
| Springer Verlag | 2018
Predicting compressive strength of geopolymer concrete using NDT techniques
| Online Contents | 2018
Machine learning based models for predicting compressive strength of geopolymer concrete
| Springer Verlag | 2024