A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Prediction of compressive strength of GGBFS and Flyash-based geopolymer composite by linear regression, lasso regression, and ridge regression
This study aims to propose an efficient technique for improving the compressive strength of geopolymer concrete using Flyash and GGBS. Various regression models, including linear regression, lasso regression, and ridge regression, were compared to predict the compressive strength. The research holds significance in understanding the strengths and limitations of these regression techniques for real-world data scenarios, aiding data scientists and promoting advancements in machine learning. The outcomes can have practical implications in various domains, enhancing knowledge and comprehension of regression techniques and their applications. The dataset consisted of 147 samples with 11 independent variables and 1 dependent variable, and statistical measurements, such as MSE, MAE, and RMSE, were used to evaluate the accuracy of the models. These findings underscore the importance of selecting the appropriate regression model tailored to the specific dataset to ensure accurate predictions and reliable insights. Based on these findings, it can be concluded that the Linear Regression model is the most suitable for predicting compressive strength based on the given dataset. However, further research and analysis may be required to explore additional factors that could improve the accuracy of the models and enhance the understanding of the relationship between the independent variables and compressive strength.
Prediction of compressive strength of GGBFS and Flyash-based geopolymer composite by linear regression, lasso regression, and ridge regression
This study aims to propose an efficient technique for improving the compressive strength of geopolymer concrete using Flyash and GGBS. Various regression models, including linear regression, lasso regression, and ridge regression, were compared to predict the compressive strength. The research holds significance in understanding the strengths and limitations of these regression techniques for real-world data scenarios, aiding data scientists and promoting advancements in machine learning. The outcomes can have practical implications in various domains, enhancing knowledge and comprehension of regression techniques and their applications. The dataset consisted of 147 samples with 11 independent variables and 1 dependent variable, and statistical measurements, such as MSE, MAE, and RMSE, were used to evaluate the accuracy of the models. These findings underscore the importance of selecting the appropriate regression model tailored to the specific dataset to ensure accurate predictions and reliable insights. Based on these findings, it can be concluded that the Linear Regression model is the most suitable for predicting compressive strength based on the given dataset. However, further research and analysis may be required to explore additional factors that could improve the accuracy of the models and enhance the understanding of the relationship between the independent variables and compressive strength.
Prediction of compressive strength of GGBFS and Flyash-based geopolymer composite by linear regression, lasso regression, and ridge regression
Asian J Civ Eng
Sharma, Ujjwal (author) / Gupta, Nakul (author) / Verma, Manvendra (author)
Asian Journal of Civil Engineering ; 24 ; 3399-3411
2023-12-01
13 pages
Article (Journal)
Electronic Resource
English
EVALUATING SHEAR STRENGTH OF SAND- GGBFS BASED GEOPOLYMER COMPOSITE MATERIAL
| BASE | 2019
Adaptive lasso penalised censored composite quantile regression
| British Library Online Contents | 2016