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

Authors:
Halil Ibrahim Erdal;Onur Karakurt;Ersin Namli
Affiliations:
Turkish Cooperation and Coordination Agency (TİKA), Atatürk Bulvarı No:15 Ulus Ankara, Turkey;Gazi University, Engineering Faculty, Civil Engineering Department, Celal Bayar Bulvarı Maltepe 06570, Ankara, Turkey;İstanbul University, Engineering Faculty, Industrial Engineering Department, Avcılar 34320, İstanbul, Turkey
Venue:
Engineering Applications of Artificial Intelligence
Year:
2013

Citing 13
Cited 0

Bagging predictors

Machine Learning
Stochastic gradient boosting

Computational Statistics & Data Analysis - Nonlinear methods and data mining
Detection of level of satisfaction and fuzziness patterns for MCDM model with modified flexible S-curve MF

Applied Soft Computing
Fuzzy polynomial neural networks for approximation of the compressive strength of concrete

Applied Soft Computing
Reduced bootstrap aggregating of learning algorithms

Pattern Recognition Letters
Knowledge discovery of concrete material using Genetic Operation Trees

Expert Systems with Applications: An International Journal
Hybrid genetic algorithms and line search method for industrial production planning with non-linear fitness function

Engineering Applications of Artificial Intelligence
Evaluation of face recognition techniques using PCA, wavelets and SVM

Expert Systems with Applications: An International Journal
A comparative assessment of ensemble learning for credit scoring

Expert Systems with Applications: An International Journal
Mammographic Mass Detection using Wavelets as Input to Neural Networks

Journal of Medical Systems
Prediction of the strength of mineral admixture concrete using multivariable regression analysis and an artificial neural network
Poly-bagging predictors for classification modelling for credit scoring

Expert Systems with Applications: An International Journal
Two credit scoring models based on dual strategy ensemble trees

Knowledge-Based Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

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^2"B"A"N"N=0.9278, R^2"G"B"A"N"N=0.9270) are superior to a conventional ANN model (R^2"A"N"N=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^2"W"B"A"N"N=0.9397, R^2"W"G"B"A"N"N=0.9528).