Table 3 The tested models and hyperparameter settings.

Evolutionary

GA-ELM

Genetic Algorithm⁵⁵

Crossover probability \(p_{c} = 0.85\) and the mutation probability \(p_{m} = 0.05\)

CRO-ELM

Coral Reefs Optimization⁵⁶

\(p_{o} = 0.85\), \(F_{b} = 0.9\), \(F_{a} = 0.1\), \(F_{d} = 0.1\), \(P_{d} = 0.1\), \(GCR = 0.1\), gamma \(\gamma_{min} = 0.02\), gamma \(\delta_{max} = 0.02\)

Swarm

AGTO-ELM

Artificial Gorilla Troops Optimization⁵⁷

\(p = 0.05\), \(w = 0.8\), updating coefficient \(beta = 3.0\)

DMOA-ELM

Dwarf Mongoose Optimization Algorithm⁵⁸

N/A

HGS-ELM

Hunger Games Search⁵⁹

\(pup = 0.03\), \(LH = 1000\)

WOA-ELM

Whale Optimization Algorithm⁶⁰

N/A

Physics

NRO-ELM

Nuclear Reaction Optimization⁶¹

N/A

HGSO-ELM

Henry Gas Solubility Optimization⁶²

Number of clusters \(n_{clusters} = 2\)

ASO-ELM

Atom Search Optimization⁶³

Depth weight \(\alpha = 10\), multiplier \(\beta = 0.2\)

Human

GSKA-ELM

Gaining Sharing Knowledge-based Algorithm⁶⁴

\(p_{b} = 0.1\), \(k_{f} = 0.5\), knowledge ratio \(k_{r} = 0.9\),\(k_{g} = 5\)

LCO-ELM

Life Choice-based Optimization⁶⁵

Step size \(r_{1} = 2.35\)

Biology

SMA-ELM

Slime Mould Algorithm⁶⁶

Probability threshold \(p_{t} = 0.03\)

SOA-ELM

Seagull Optimization Algorithm⁶⁷

Frequency of employing \(fc = 2\)

TSA-ELM

Tunicate Swarm Algorithm⁶⁸

N/A

System

AEO-ELM

Artificial Ecosystem-based Optimization⁵⁴

N/A

Music

HS-ELM

Harmony Search⁶⁹

Consideration rate \(c_{r} = 0.95\), pitch adjustment rate \(pa_{r} = 0.05\)

Math

GBO-ELM

Gradient-Based Optimizer⁷⁰

\(p_{r} = 0.5\), \(\beta_{min} = 0.2\),\(\beta_{max} = 1.2\)

PSS-ELM

Pareto-like Sequential Sampling

Acceptance rate \(ar = 0.9\), \(sampling = LHS\) (Latin-Hypercube)

INFO-ELM

weighted meaN oF vectOrs

N/A

RUN-ELM

RUNge Kutta optimizer

\(a = 20, b = 12\)