Table 3 MO algorithm with machine learning and variable-fidelity EM models: control parameters.

From: Multi-objective artificial-intelligence-based parameter tuning of antennas using variable-fidelity machine learning

Parameter

Description

Default value

Ninit

The number of initial sample points for

constructing the first ANN surrogate

(cf. Sect. 2.3)

100

Ninfill

The number of infill points generated per

MO iteration (cf. Section 2.5)

10

Ntransition

The number of iterations over which the EM

model fidelity is changed from

Lmin to Lmax (cf. Section 2.6)

5

Na

The span of the moving average for

computing the Pareto front similarity metric

Ea.i (cf. Section 2.7)

5

ε

Termination threshold for the MO process

(cf. Section 2.7)

1