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.

scholarly journals Opportunities and Constraints in Applying Artificial Neural Networks (ANNs) in Food Authentication. Honey—A Case Study

2021 ◽  
Vol 11 (15) ◽  
pp. 6723
Author(s):  
Ariana Raluca Hategan ◽  
Romulus Puscas ◽  
Gabriela Cristea ◽  
Adriana Dehelean ◽  
Francois Guyon ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Training Sample ◽  
Training Data ◽  
Elemental Content ◽  
Neural Structure ◽  
Food Authentication ◽  
Data Set ◽  
Artificial Neural

The present work aims to test the potential of the application of Artificial Neural Networks (ANNs) for food authentication. For this purpose, honey was chosen as the working matrix. The samples were originated from two countries: Romania (50) and France (53), having as floral origins: acacia, linden, honeydew, colza, galium verum, coriander, sunflower, thyme, raspberry, lavender and chestnut. The ANNs were built on the isotope and elemental content of the investigated honey samples. This approach conducted to the development of a prediction model for geographical recognition with an accuracy of 96%. Alongside this work, distinct models were developed and tested, with the aim of identifying the most suitable configurations for this application. In this regard, improvements have been continuously performed; the most important of them consisted in overcoming the unwanted phenomenon of over-fitting, observed for the training data set. This was achieved by identifying appropriate values for the number of iterations over the training data and for the size and number of the hidden layers and by introducing of a dropout layer in the configuration of the neural structure. As a conclusion, ANNs can be successfully applied in food authenticity control, but with a degree of caution with respect to the “over optimization” of the correct classification percentage for the training sample set, which can lead to an over-fitted model.

Sign in / Sign up

Export Citation Format

Share Document