Prediction of Compressive Strength in High Strength Concrete with Steel Fiber Addition using Support Vector Machine Algorithm

In this study, a support vector machine model available in Weka Algorithms, was utilized to test the predictive capacity of compressive strength in high performance concrete (HSC) with steel fiber addition. To test the performance of the algorithm, a certain percentage were allocated for training of the algorithm, and the rest for test. This was done from 60-40 percent split up to 90-10 percent split for training and testing respectively. Results generated from the model include mean absolute error, root mean squared error, and relative absolute error for each model. It was observed that there was a good correlation between the actual and predicted values, and that errors were relatively low. Utilization of free algorithms in civil engineering construction will enhance the optimization of concrete mixtures. &nbsp