High performance concrete compressive strength forecasting using ensemble models based on discrete wavelet transform

Erdal H. I., Karakurt O., NAMLI E.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, cilt.26, sa.4, ss.1246-1254, 2013 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 26 Sayı: 4
  • Basım Tarihi: 2013
  • Doi Numarası: 10.1016/j.engappai.2012.10.014
  • Dergi Adı: ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.1246-1254
  • Anahtar Kelimeler: Artificial neural networks, Bagging (bootstrap aggregation), Discrete wavelet transform, Ensemble models, Gradient boosting, High performance concrete strength, ARTIFICIAL NEURAL-NETWORKS, SILICA FUME, PREDICTION, DESIGN
  • Gazi Üniversitesi Adresli: Evet

Özet

This paper investigates the use of wavelet ensemble models for high performance concrete (HPC) compressive strength forecasting. More specifically, we incorporate bagging and gradient boosting methods in building artificial neural networks (ANN) ensembles (bagged artificial neural networks (BANN) and gradient boosted artificial neural networks (GBANN)), first. Coefficient of determination (R-2), mean absolute error (MAE) and the root mean squared error (RMSE) statics are used for performance evaluation of proposed predictive models. Empirical results show that ensemble models (R-BANN(2)=0.9278, R-GBANN(2)=0.9270) are superior to a conventional ANN model (R-ANN(2)=0.9088). Then, we use the coupling of discrete wavelet transform (DWT) and ANN ensembles for enhancing the prediction accuracy. The study concludes that DWT is an effective tool for increasing the accuracy of the ANN ensembles (R-WBANN(2)=0.9397. R-WGBANN(2)=0.9528). (C) 2012 Elsevier Ltd. All rights reserved.