Please use this identifier to cite or link to this item:
https://ir.swu.ac.th/jspui/handle/123456789/17584
ชื่อเรื่อง: | Prediction of geopolymer concrete compressive strength using novel machine learning algorithms |
ผู้แต่ง: | Ahmad A. Ahmad W. Chaiyasarn K. Ostrowski K.A. Aslam F. Zajdel P. Joyklad P. |
Keywords: | Adaptive boosting Compressive strength Concretes Fly ash Geopolymers Inorganic polymers Neural networks Sensitivity analysis Slags Supervised learning Sustainable development Coefficient of determination Concrete compressive strength Environment Environmental threats Geopolymer concrete Machine learning algorithms Machine learning approaches Machine learning techniques Properties of concretes Supervised machine learning Forecasting |
วันที่เผยแพร่: | 2021 |
บทคัดย่อ: | The innovation of geopolymer concrete (GPC) plays a vital role not only in reducing the environmental threat but also as an exceptional material for sustainable development. The application of supervised machine learning (ML) algorithms to forecast the mechanical properties of concrete also has a significant role in developing the innovative environment in the field of civil engineering. This study was based on the use of the artificial neural network (ANN), boosting, and AdaBoost ML approaches, based on the python coding to predict the compressive strength (CS) of high calcium fly-ash-based GPC. The performance comparison of both the employed techniques in terms of prediction reveals that the ensemble ML approaches, AdaBoost, and boosting were more effective than the individual ML technique (ANN). The boosting indicates the highest value of R2 equals 0.96, and AdaBoost gives 0.93, while the ANN model was less accurate, indicating the coefficient of determination value equals 0.87. The lesser values of the errors, MAE, MSE, and RMSE of the boosting technique give 1.69 MPa, 4.16 MPa, and 2.04 MPa, respectively, indicating the high accuracy of the boosting algorithm. However, the statistical check of the errors (MAE, MSE, RMSE) and k-fold cross-validation method confirms the high precision of the boosting technique. In addition, the sensitivity analysis was also introduced to evaluate the contribution level of the input parameters towards the prediction of CS of GPC. The better accuracy can be achieved by incorporating other ensemble ML techniques such as AdaBoost, bagging, and gradient boosting. © 2021 by the authors. Licensee MDPI, Basel, Switzerland. |
URI: | https://ir.swu.ac.th/jspui/handle/123456789/17584 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85116312721&doi=10.3390%2fpolym13193389&partnerID=40&md5=85b8d04195a27ee1120672e0aca36bea |
ISSN: | 20734360 |
Appears in Collections: | Scopus 1983-2021 |
Files in This Item:
There are no files associated with this item.
Items in SWU repository are protected by copyright, with all rights reserved, unless otherwise indicated.