Chapter 5 - Soft computing and statistical tools for developing analytical models

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@InCollection{SAYYAADI:2021:MAOES,

• author = "Hoseyn Sayyaadi",
• title = "Chapter 5 - Soft computing and statistical tools for developing analytical models",
• editor = "Hoseyn Sayyaadi",
• booktitle = "Modeling, Assessment, and Optimization of Energy Systems",
• publisher = "Academic Press",
• pages = "247--325",
• year = "2021",
• isbn13 = "978-0-12-816656-7",
• DOI = "doi:10.1016/B978-0-12-816656-7.00005-1",
• URL = "https://www.sciencedirect.com/science/article/pii/B9780128166567000051",
• keywords = "genetic algorithms, genetic programming, Soft computing and statistical tool (SCST), Artificial neural network (ANN), Group method of data handling (GMDH), Genetic programming (GP), Stepwise regression method (SRM), Multiple linear regression (MLR)",
• abstract = "Analytical modeling provides an accurate and straightforward way of modeling. If, in a case, governing equations can be written and solved quickly, the analytical modeling is done by that. However, in a lot of real cases, it is not possible to write or solve governing equations. In such cases, as an alternative to the numerical models with the mentioned drawbacks, soft computing methods and statistical tools can be employed. They not only make the calculations both fast and straightforward but also do not need running the development algorithm every time they are employed. In contrast to the numerical models, they are developed once, and then, the provided equation(s) or network can be used for further calculations without requiring passing the development process again. Having the mentioned advantages, soft computing and statistical tools are becoming popular more and more among the researchers for modeling energy systems. By using the developed statistical methods, further analyses such as optimization or parametric study can be done much more easily compared to the other models, especially numerical models. Artificial neural networks (ANNs), group method of data handling (GMDH), genetic programming (GP), response surface methodology (RSM), multiple linear regression (MLR), and stepwise regression method (SRM) are the most common statistical methods for modeling of energy systems. This chapter provides information about them",

}

Genetic Programming entries for Hoseyn Sayyaadi

Citations