Table 2 UDFs of soft computing models.

From: Development of soft computing-based models for forecasting water quality index of Lorestan Province, Iran

Data-driven Models

UDFs

GP

puk kernel

Gaussian noise (0.01), σ(1), ω(0.1)

rbf kernel

Gaussian noise γ(0.01), (1)

GEP

Mutation rate (0.044), inversion rate (0.1), incessant rate (0.1), root scale transport rate (0.1). one-point crossover rate (0.13), two-point crossover rate (0.3), gene recombination rate (0.1), transportation rate (0.1), number of chromosomes (30), head size (3), and no. of gene per chromosomes (3).

REPt

Maximum tree depth: −1; minimum total instance weight in the leaf: 2; minimum likelihood of variance: 0.001

BREPt

Batch size-80, bag Size percent = 100, Classifier = REPTree, numbers of executions slots = 1, number of iterations = 100

ANN-FFA

Iteration (1000), population (150), α (0.05), β (0.5), γ(0.8) and neuron (12)