Assessment of Artificial Intelligence Models for Developing Single-Value and Loop Rating Curves

Table 2

Values of MGGP controlling parameters.

Parameter	Values
Function set	Arithmetic (trigonometric, plog, psqroot, and exponential functions) and operations
Number of generations	120
Maximum number of genes allowed in individual	5
Maximum tree depth	4
Tournament size	4
Elitism	0.05 of population
Crossover events	0.85
High-level crossover	0.2
Low-level crossover	0.8
Standard deviation of perturbation applied in mutation Gaussian perturbation of a randomly selected constant	0.1
Subtree mutation	0.9
Replacing input terminal with another random terminal	0.05
Gaussian perturbation of randomly selected constant	0.05
Direct reproduction	0.05
Ephemeral random constants	[−10, 10]