Package {MetaEEEA}

Type:	Package
Title:	Metaheuristic Algorithms with Explicit Exploration
Description:	Solves single-objective optimization problems by using bio-inspired metaheuristic algorithms. The implemented metaheuristics are the Butterfly Optimization Algorithm, the Ladybug Beetle Optimization Algorithm and the Prairie Dog Optimization Algorithm. For all these optimization algorithms, the search of optimal values can be reinforced with the explicit exploration strategy proposed by Salinas-Gutiérrez and Muñoz Zavala (2023) <doi:10.1016/j.asoc.2023.110230>.
Version:	1.0.0
License:	GPL-3
Encoding:	UTF-8
Imports:	EEEA
Author:	Rogelio Salinas Gutiérrez [aut, cre, cph], Cristina Díaz Esquivel [aut, cph], Angela María Gallegos Martínez [aut, cph], Agustín Moreno Cruz [aut, cph], Miguel Angel Moreno Urbina [aut, cph], Pedro Abraham Montoya Calzada [aut, cph], Carlos Alberto López Hernández [aut, cph], Ilse Daniela Saldivar Olvera [aut, cph]
Maintainer:	Rogelio Salinas Gutiérrez <rogelio.salinas@edu.uaa.mx>
Suggests:	testthat (≥ 3.0.0)
Config/testthat/edition:	3
Config/roxygen2/version:	8.0.0
NeedsCompilation:	no
Packaged:	2026-07-17 01:14:20 UTC; rogel
Repository:	CRAN
Date/Publication:	2026-07-24 10:00:26 UTC

Butterfly Optimization Algorithm (BOA)

Description

Provides an implementation of the Butterfly Optimization (BOA) for optimization problems.

Usage

  boa_metaheuristic(
    obj.fun,
    pop.size=30,
    dim=2,
    lb,
    ub,
    gen=100,
    pb=0,
    EE=FALSE,
    p=0.8,
    a=0.1,
    c=0.01,
    ...)

Arguments

Details

The Butterfly Optimization Algorithm is a swarm intelligence metaheuristic inspired by the biological foraging and mating behaviors of butterflies. The algorithm simulates the fragrance emission and perception to create a social network of individuals, utilizing global search toward the current best butterfly (highly fragrant stimulus) and local random walks when sensory modality drops, effectively balancing exploration and exploitation within the feasible search space.

Value

Returns a list with the following entries:

References

Arora, S., & Singh, S. (2019). Butterfly optimization algorithm: A novel approach for global optimization. Soft Computing, 23(3), 715–734. doi:10.1007/s00500-018-3102-4 Okwu, M. O., & Tartibu, L. K. (2021). Butterfly Optimization Algorithm. In Metaheuristic Optimization: Nature-Inspired Algorithms Swarm and Computational Intelligence, Theory and Applications (Studies in Computational Intelligence, Vol. 927, pp. 105–114). Springer Nature Switzerland AG. doi:10.1007/978-3-030-61111-8_11

Examples

  obj.fun <- function (x){
  y <- sum(x^2)
  return (y)
  }
  pop.size <- 30
  dim <- 2
  lb <- -5.12
  ub <- 5.12
  gen <- 100
  pb <- 20
  EE <- TRUE

  res.sphere <- boa_metaheuristic(obj.fun, pop.size, dim, lb, ub, gen, pb, EE)

  cat("Best value on Sphere: ", paste(round(res.sphere$best.fit, 4),
      collapse=", "), "\n")
  cat("Best solution en Sphere: ", paste(round(res.sphere$best.sol, 4),
      collapse=", "), "\n")

Ladybug Optimization Algorithm (LBO)

Description

Provides an implementation of the Ladybug Optimization (LBO) algorithm for optimization problems.

Usage

  lbo_metaheuristic(
    obj.fun,
    pop.size=30,
    dim=2,
    lb,
    ub,
    gen=100,
    pb=0,
    EE=FALSE,
    pa=0.1,
    sigma=0.05,
    beta=8,
    temp.init=100,
    ...)

Arguments

Details

The Ladybug Optimization algorithm is a swarm intelligence metaheuristic inspired by the biological behaviors of ladybugs. The algorithm simulates phases such as foraging/dispersion using Lévy flights, hibernation (aggregation based on global heat), and survival during freezing temperatures to explore and exploit the feasible search space.

Value

Returns a list with the following entries:

References

Safiri, S., & Nikoofard, A. (2022). Ladybug Beetle Optimization algorithm: application for real-world problems. The Journal of Supercomputing, 79, 3511-3560. doi:10.1007/s11227-022-04755-2

Examples

  obj.fun <- function (x){
  y <- sum(x^2)
  return (y)
  }
  pop.size <- 30
  dim <- 2
  lb <- -5.12
  ub <- 5.12
  gen <- 100
  pb <- 20
  EE <- TRUE

  res.sphere <- lbo_metaheuristic(obj.fun, pop.size, dim, lb, ub, gen, pb, EE)

  cat("Best value on Sphere: ", paste(round(res.sphere$best.fit, 4),
      collapse=", "), "\n")
  cat("Best solution en Sphere: ", paste(round(res.sphere$best.sol, 4),
      collapse=", "), "\n")

Prairie Dog Optimization Algorithm (PDO)

Description

Provides an implementation of the Prairie Dog Optimization (PDO) algorithm for optimization problems.

Usage

  pdo_metaheuristic(
    obj.fun,
    pop.size=30,
    dim=2,
    lb,
    ub,
    gen=100,
    pb=0,
    EE=FALSE,
    ...)

Arguments

Details

The Prairie Dog Optimization algorithm is a swarm intelligence metaheuristic inspired by the biological behaviors of prairie dogs. The algorithm simulates four distinct time-based phases: foraging/exploration using Lévy flights, burrow construction/exploitation via cooperative digging, food alarm communication using vocal alerts, and randomized flight for predator escape to explore and exploit the feasible search space.

Value

Returns a list with the following entries:

References

Ezugwu, A. E., Agushaka, J. O., Abualigah, L., Mirjalili, S., & Gandomi, A. H. (2022). Prairie Dog Optimization Algorithm. Neural Computing and Applications, vol 34, no. 22, pp. 20017-20065. Springer, London. doi:10.1007/s00521-022-07530-9

Examples

  obj.fun <- function (x){
    y <- sum(x^2)
    return (y)
  }
  pop.size <- 30
  dim <- 2
  lb <- -5.12
  ub <- 5.12
  gen <- 100
  pb <- 20
  EE <- TRUE

  res.sphere <- pdo_metaheuristic(obj.fun, pop.size, dim, lb, ub, gen, pb, EE)

  cat("Best value on Sphere: ", paste(round(res.sphere$best.fit, 4),
      collapse=", "), "\n")
  cat("Best solution en Sphere: ", paste(round(res.sphere$best.sol, 4),
      collapse=", "), "\n")