Rajeshwari, R. <br/><br/>
Compressive strength prediction of SCC containing fly ash using SVM and PSO-SVM models 

 - Vol.48, Issue 1 
 - Chennai  CSIR- Strctural Engineering research Centre  2021 
 - 1-11p. 
<br/><br/> Self-Compacting Concrete (SCC), is a highly workable material,<br/>compacted by its self weight without observable segregation and<br/>bleeding. In this study, Support Vector Machine (SVM) and particle<br/>swarm optimization based SVM models are employed to predict the<br/>28 days compressive strength of individual SCC mix. A database of 62<br/>no’s of SCC compressive strength from literature with cement partially<br/>replaced by fly ash is used for training the models. The test data<br/>consists of two groups, an individual study consisting of 9 datasets<br/>and other combination of three studies with 19 datasets tested<br/>separately. Similar input parameters from the train data is extended for<br/>testing the models prediction accuracy. Statistical parameters such as<br/>correlation coefficient, root mean square error and scatter index are<br/>used to evaluate the models’ prediction results. The particle swarm<br/>optimization based SVM model is capable of selecting appropriate<br/>SVM parameters to increase the prediction accuracy. From the results,<br/>it is seen that both SVM and particle swarm optimized SVM models<br/>have good capability in predicting the SCC compressive strength. 
<br/><br/><label>Subjects--Topical Terms: </label><br/>Civil Engineering
<br/><br/><label>Subjects--Index Terms: </label>Fly Ash Support Vector Regression Particle Swarm Optimization