PERBANDINGAN KINERJA ARTIFICIAL INTELLIGENCE DALAM MEMPREDIKSI KUAT TEKAN BETON

Authors

  • Nico Christiono Student
  • Doddy Prayogo co-authors

DOI:

https://doi.org/10.9744/duts.7.2.1-17

Keywords:

prediction, concrete compressive strength, artificial intelligence, ANN, SVM, CART, LR

Abstract

Today, concrete quality prediction can be performed with the help of artificial intelligence (AI) to solve existing problems. However, determining the best AI method for predicting concrete compressive strength remains an open question. Therefore, this research evaluates the most accurate AI modeling for predicting various kinds of concrete mixtures. AI methods used in this study are artificial neural networks (ANN), support vector machines (SVM), classification and regression trees (CART), and linear regression (LR). Furthermore, these four AI methods are run with several parameters and tested with 4 different kinds of concrete dataset. Four error indicators and 1 normalization indicator are used to evaluate AI and determine the best AI method. From the Obtained results, indicate that ANN has the best performance when compared with 3 other AI methods. It can be seen that from  ANN produced smaller error values when compared to the other three AI methods.

Downloads

Published

2020-10-30

How to Cite

Christiono, N., & Prayogo, D. (2020). PERBANDINGAN KINERJA ARTIFICIAL INTELLIGENCE DALAM MEMPREDIKSI KUAT TEKAN BETON. Dimensi Utama Teknik Sipil, 7(2), 1–17. https://doi.org/10.9744/duts.7.2.1-17