Embedded Files
What scientists have been saying about GPTIPS
What scientists have been saying about GPTIPS
Note: MGGP is multigene genetic programming, the machine learning model discovery engine that powers GPTIPS
"Numerical examples show the superb accuracy, efficiency, and great potential of MGGP. Contrary to artificial neural networks and many other soft computing tools, MGGP provides constitutive prediction equations."1
"Numerical examples show the superb accuracy, efficiency, and great potential of MGGP. Contrary to artificial neural networks and many other soft computing tools, MGGP provides constitutive prediction equations."1
One of the most powerful methods used for non-linear regression problems ... The results obtained show the power of MGGP for producing an efficient nonlinear regression model, in terms of accuracy and complexity. 2
A remarkable control can be exerted over the maximum complexity of the model evolved by MGGP in comparison with the standard GP.1
It can be observed (...) that the MGGP-based solution remarkably outperforms the other models. In addition to its high performance, the MGGP-based equation is very simple, and therefore, it can easily be manipulated in practical circumstances.1
MGGP has an advantage that once the evolved models are trained, they can be used as quick and accurate tools for prediction purposes.1
The efficacy of the developed MGGP based models (Mode-I and Model-II) are compared with that of the available ANN and SVM models respectively. It is found that the performance of Model-I is better than the ANN model in terms of rate of successful prediction …, whereas Model-II is as good as the SVM model.3
We reviewed existing models of the drag coefficient for the smooth sphere ... We used multigene genetic programming for developing high accurate drag coefficient models... The developed models give (up to almost 70%) better results than the best existing correlations in terms of the sum of squares of logarithmic deviations (SSLD).4
Of the two AI methods, MGGP has shown better performance than SVR [support vector regression]. The excellent performance of the MGGP model on the testing data indicates that it is able to extrapolate the behavior of SWCNTs [carbon nanotubes] at temperatures of 600 and 900 K. In addition, the implementation of MGGP requires only the adjustment of its few parameter settings such as population size, number of generations, maximum number of genes, maximum depth of tree, etc. which can also be set without having in-depth knowledge about its functioning.5
MGGP was employed to predict the total amount of measured solar irradiation from six different independent variables. The proposed methodology is backed by adequate numerical simulation and is proved to give better results than the previous approaches by other researchers using fuzzy logic and neural networks.6
The developed model equation is found to more compact compared to the MARS and other AI models and can easily be used by the professionals with the help of a spreadsheet without going into the complexity of model development.7
The proposed GP model is found to be (more) effective and efficient than MARS, ANN (DENN, BRNN), SVM and other statistical models7
1. Gandomi, AH & Alavi, AH, A new multi-gene genetic programming approach to non-linear system modeling. Part II: geotechnical and earthquake engineering problems, Neural Comput & Applic, Springer, DOI 10.1007/s00521-011-0735-y, 2011.2. M. Amiri, M. Eftekhari, M. Dehestani and A. Tajaddini, Modeling intermolecular potential of He–F2 dimer from symmetry-adapted perturbation theory using multi-gene genetic programming, Scientia Iranica, Volume 20, Issue 3, Pages 543-548, ISSN 1026-3098, DOI: 10.1016/j.scient.2012.12.040, June 2013. 3. Pradyut Kumar Muduli and Sarat Kumar Das, CPT-based seismic liquefaction potential evaluation using multi-gene genetic programming approach, Indian Geotechnical Journal, DOI: 10.1007/s40098-013-0048-4, Springer-Verlag, Print ISSN: 0971-9555, Online: ISSN: 2277-3347, March 2013.4. Barati et al., Development of empirical models with high accuracy for estimation of drag coefficient of flow around a smooth sphere: An evolutionary approach, Powder Technology, Vol. 257, pp. 11-19, DOI: 10.1016/j.powtec.2014.02.045, Elsevier, May 2014.5. V. Vijayaraghavan, A. Garg, C. H. Wong and K. Tai, Estimation of mechanical properties of nanomaterials using artificial intelligence methods, Applied Physics A, Print ISSN: 0947-8396, pp. 1-9, DOI: 10.1007/s00339-013-8192-3, Springer Berlin Heidelberg, 2013.6. Pan, Indranil and Pandey, Daya Shankar and Das, Saptarshi, Global solar irradiation prediction using a multi-gene genetic programming approach, Journal of Renewable and Sustainable Energy, 5, 063129, DOI: 10.1063/1.4850495 , 2013.7. Pradyut Kumar Muduli, Manas Ranjan Das, Sarat Kumar Das & Swagatika Senapati, Lateral load capacity of piles in clay using genetic programming and multivariate adaptive regression spline, Indian Geotechnical Journal, DOI: 10.1007/s40098-014-0142-2, Springer India, Jan. 2015.
Page updated
Google Sites
Report abuse