Table 2 Optimum values for all paradigms’ regularization parameters.

From: Artificial intelligence-based framework for precise prediction of asphaltene particle aggregation kinetics in petroleum recovery

Model

Regularization parameter

Value

GWO-RBF

Number of neurons

99

Spread coefficient

0.5803

ELM

Number of neurons

104

MLP

Number of neurons

21

Activation function

Tansig, Tansig

ANFIS

Structure of FIS

TSK

Type of initial FIS

FCM

Number of clusters

18

Training method

Hybrid

Back to article page