Assessment of artificial neural network and genetic programming as predictive tools

Gandomi, Amir H.; Roke, David A.

doi:10.1016/j.advengsoft.2015.05.007

Cited by 306 publications

(144 citation statements)

References 27 publications

Supporting

Mentioning

125

Contrasting

Order By: Relevance

“…Since R value does not change by equal shifting of the output values predicted by a model, it is acknowledged not to be a good indicator on its own for evaluating the accuracy of a model on its own. On the other hand, besides assuming the impact of various data divisions for the learning and validation data, the performance index ( ρ ) simultaneously takes into account the changes of RRMSE and R. Lower RRMSE and higher R values yield in lower OBJ indicating a more accurate model (Gandomi, Roke 2015). The values obtained for R, RRMSE, and ρ are respectively, 0.8467, 0.4065, and 0.220.…”

Section: Nomentioning

confidence: 96%

See 1 more Smart Citation

Gene Expression Programming Approach to Cost Estimation Formulation for Utility Projects

Shahrara

Çelik

Gandomi

2017

Journal of Civil Engineering and Management

Self Cite

View full text Add to dashboard Cite

Abstract. This article utilizes gene expression programming (GEP) technique to develop a prediction model in order to automate estimating the construction cost of water and sewer replacement/rehabilitation projects. A database gathered for developing the model was established on the basis of data related to 210 actual water and sewer projects obtained from the City of San Diego, California, USA. To verify the predictability of the GEP model, it was examined to estimate the cost of the projects that were not included in the modelling process. Sensitivity analysis technique and professional experiences were employed to determine the contributions of the qualitative factors and quantifiable parameters affecting the cost estimate. The proposed model with correlation coefficient of 0.8467 is adequately capable of estimating the cost of water and sewer replacement/rehabilitation projects. The GEP-based design equation can easily be used for predesign purposes to help allocate budgets and available limited resources effectively.

show abstract

Section: Nomentioning

confidence: 96%

“…GP is intrinsically capable of finding the best solution by evaluating fitness of the computer programs over numerous generations; on the contrary, as mentioned earlier, in ANN, data should be normalized at the outset, and best network architecture first should be established (Gandomi, Roke 2015).…”

Section: Introductionmentioning

confidence: 99%

Gene Expression Programming Approach to Cost Estimation Formulation for Utility Projects

Shahrara

Çelik

Gandomi

2017

Journal of Civil Engineering and Management

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although ANNs are generally successful in prediction, they are only appropriate to use as part of a computer program, not for the development of practical prediction equations. In addition, ANN requires data to be initially normalized based on the suitable activation function and the best network architecture to be determined by the user, and it can have a complex structure and a high potential for over-fitting [10]. SVMs, on the other hand, are one of the efficient kernel-based methods that can solve a convex constrained quadratic programming (CCQP) problem to find a set of parameters.…”

Section: Introductionmentioning

confidence: 99%

Genetic programming for experimental big data mining: A case study on concrete creep formulation

Gandomi

Sajedi

Kiani

et al. 2016

Automation in Construction

Self Cite

View full text Add to dashboard Cite

This paper proposes a new algorithm called multi-objective genetic programming (MOGP) for complex civil engineering systems. The proposed technique effectively combines the model structure selection ability of a standard genetic programming with the parameter estimation power of classical regression, and it simultaneously optimizes both the complexity and goodness-of-fit in a system through a non-dominated sorting algorithm. The performance of MOGP is illustrated by modeling a complex civil engineering problem: the timedependent total creep of concrete. A Big Data is used for the model development so that the proposed concrete creep model-referred to as a "genetic programming based creep model" or "G-C model" in this study-is valid for both normal and high strength concrete with a wide range of structural properties. The G-C model is then compared with currently accepted creep prediction models. The G-C model obtained by MOGP is simple, straightforward to use, and provides more accurate predictions than other prediction models.

show abstract

“…Recently, Peng et al (2014) proposed an improved GEP algorithm especially suitable for dealing with SR problems. Gandomi and Roke (2015) compared the forecasting performance of artificial neural network models to that of GEP techniques.…”

Section: Literature Reviewmentioning

confidence: 99%

Let the Data Do the Talking: Empirical Modelling of Survey-Based Expectations by Means of Genetic Programming

2017

View full text Add to dashboard Cite

Assessment of artificial neural network and genetic programming as predictive tools

Cited by 306 publications

References 27 publications

Gene Expression Programming Approach to Cost Estimation Formulation for Utility Projects

Gene Expression Programming Approach to Cost Estimation Formulation for Utility Projects

Genetic programming for experimental big data mining: A case study on concrete creep formulation

Let the Data Do the Talking: Empirical Modelling of Survey-Based Expectations by Means of Genetic Programming

Contact Info

Product

Resources

About