12 - Linear and Tree-Based Genetic Programming for Solving Geotechnical Engineering Problems
References (0)
Cited by (22)
Genetic programming for predictions of effectiveness of rolling dynamic compaction with dynamic cone penetrometer test results
2019, Journal of Rock Mechanics and Geotechnical EngineeringCitation Excerpt :This machine learning technique aligns with the theory of Darwinian natural selection and was first introduced by Koza (1992). Generally, GP is considered as an extension to genetic algorithms (GAs), in which most of the genetic operators used in GAs are also applicable, albeit with slight modifications (Alavi et al., 2013). However, the main differences between GP and GAs lie in the representation of the solution.
An empirical model for shear capacity of RC deep beams using genetic-simulated annealing
2013, Archives of Civil and Mechanical EngineeringCitation Excerpt :As observed in Fig. 4(b), in tree-based GP, the data flow is more rigidly determined by the tree structure of the program [9]. In the LGP system utilized here, an individual program is interpreted as a variable-length sequence of simple C instructions [4,5]. Considering the above explanations for GP and SA, the coupled GSA algorithm uses the following main steps to evolve a computer program [2,14,16]:
Metaheuristic Algorithms in Modeling and Optimization
2013, Metaheuristic Applications in Structures and InfrastructuresProgressive Machine Learning Approaches for Predicting the Soil Compaction Parameters
2023, Transportation Infrastructure GeotechnologyINTELLIGENT PREDICTION MODELS FOR UCS OF CEMENT/LIME STABILIZED QLD SOIL
2022, Australian Geomechanics Journal