Indirect Estimation of Swelling Pressure of Expansive Soil: GEP versus MEP Modelling

Table 4

Parameters setting for GEP and MEP algorithms.

	Settings for Ps
GEP parameters
General
Training records	134
Validation records	66
Number of chromosomes	30
Number of genes	3
Head size	13
Linking function	Addition
Function set	+, −, ×, ÷, X^2, X^1/3
Numerical constants
Constants per gene	10
Type of data	Floating point
Maximum complexity	10
Ephemeral random constant	[−10, 10]
Genetic operators
Mutation	0.00138
Inversion rate	0.00546
IS transposition rate	0.00546
RIS transposition rate	0.00546
One-point recombination rate	0.00277
Two-point recombination rate	0.00277
Gene recombination rate	0.00277
Uniform recombination	0.00755
MEP parameters
Num of subpopulation	10
Subpopulation size	2000
Code length	50
Crossover probability	0.9
Crossover type	Uniform
Mutation probability	0.01
Tournament size	6
Operators	0.5
Variables	0.5
Constants	0
Number of generations	1400
Function set	+, −, ×,/
Terminal set	Problem input
Replication number	10
Error measure	Mean squared error
Problem type	Regression
Simplified	Yes
Random seed	0
Number of runs	20
Number of threads	1