Modelling formulations using gene expression programming – A comparative analysis with artificial neural networks

2011 ◽  
Vol 44 (3) ◽  
pp. 366-374 ◽  
Author(s):  
E.A. Colbourn ◽  
S.J. Roskilly ◽  
R.C. Rowe ◽  
P. York
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Comparative Analysis ◽  
Gene Expression Programming ◽  
Artificial Neural

scholarly journals A simple formulation for early-stage cost estimation of building construction projects

2021 ◽  
Vol 73 (08) ◽  
pp. 819-832
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Construction Projects ◽  
Early Stage ◽  
Gene Expression Programming ◽  
Cost Calculation ◽  
Data Set ◽  
Algorithm Configuration ◽  
Artificial Neural

This study is aimed at improving a formula that enables easy, correct, and fast estimation of an Early-Stage Cost of Buildings (ESCE). This formula, enabling estimation of ESCE, was developed by the authors based on artificial neural networks and gene expression programming. A quantity survey was conducted for a hundred construction projects, and a data set was created. This data set was analysed with many Artificial Neural Networks to determine the variables that affect ESCE. An algorithm configuration was made with Gene Expression Programming, and the ESCE formula was created using this algorithm configuration. This formula estimates ESCE with satisfactory precision. The use of the proposed formula in the early-stage building cost calculations is important not only for faster and easier cost calculation but also to prevent any differences that may arise due to the individual making the calculations.

Evaluation Compressive Strength of Cement-Limestone-Slag Ternary Blended Concrete Using Artificial Neural Networks (ANN) and Gene Expression Programming (GEP)

2020 ◽  
Vol 837 ◽  
pp. 119-124
Author(s):  
Xiao Yong Wang
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Gene Expression Programming ◽  
Concrete Strength ◽  
Correlation Coefficients ◽  
Strength Development ◽  
Ann Model ◽  
Artificial Neural ◽  
Ternary Blended Concrete

Limestone and slag blended concrete is an innovative concrete which belongs to the family of limestone calcined clay cement (LC3) concrete. Strength is an important property of structural concrete. This study shows artificial neural networks (ANN) and gene expression programming (GEP) models for predicting strength development of limestone and slag blended concrete. ANN model consists of an input layer, a hidden layer, and output layer. GEP model consists of the sum of three expression trees. The input parameters of ANN and GEP models are mixtures and ages. The output parameter is a strength. The correlation coefficients of ANN and GEP model are 0.99 and 0.98, respectively. Both ANN and GEP model can produce prediction results of the strength of ternary blended concrete reliably.

Sign in / Sign up

Export Citation Format

Share Document