International Journal of Concrete Technology

Prediction of Compressive Strength of Concrete with Decision Trees

  1. Saha Dauji

Abstract

In the past few researchers predicted the compressive strength of concrete from its ingredients employing data driven technique like artificial neural network (ANN) and Decision Tree (DT). For Indian concrete records, only one study was available which had employed ANN for prediction. Evaluation of different performance metrics indicated that there was scope of improvement in the prediction performance. In this paper experimental data from the literature was utilized for development of prediction models with the data-driven technique: Decision Tree (DT). While it is difficult to appreciate the underlying rationale for the predictions by ANN, predictions by DT are rule based which can be easily listed and comprehended by users. Decision tree gave better overall performance compared to ANN models reported in the literature as was ascertained by higher correlation, lesser root mean square error and mean absolute error. In the end, interpretation of the decision rules had been attempted.

Read more of it

Subscribe to one journal or build your own list of several. One invoice, one payment, access for a full year.

Subscribe to journals →

Publish your article

Peer-reviewed journals across every subject, with open access options. Send your manuscript to the right editor today.

Publish with us → Calculate your APC
Support