Package unifeat.featureSelection.wrapper.ACOBasedMethods

Class BasicACO<ColonyType>

java.lang.Object
unifeat.featureSelection.FeatureSelection
unifeat.featureSelection.wrapper.WrapperApproach
unifeat.featureSelection.wrapper.ACOBasedMethods.BasicACO<ColonyType>
Type Parameters:
ColonyType - the type of colony implemented in ACO algorithm
Direct Known Subclasses:
OptimalACO
public abstract class BasicACO<ColonyType> extends WrapperApproach
The abstract class contains the main methods and fields that are used in all ACO-based feature selection methods.
Author:
Sina Tabakhi
See Also:

  • Field Details

    • colony

      protected ColonyType colony

    • NUM_ITERATION

      protected final int NUM_ITERATION

    • K_FOLDS

      protected final int K_FOLDS

  • Constructor Details

    • BasicACO

      public BasicACO(Object... arguments)
      Initializes the parameters
      Parameters:
      arguments - array of parameters contains (path, numFeatures, classifierType, selectedClassifierPan, numIteration, colonySize, alphaParameter, betaParameter, evaporationRate, kFolds, initPheromone) in which path is the path of the project, numFeatures is the number of original features in the dataset, classifierType is the classifier type for evaluating the fitness of a solution, selectedClassifierPan is the selected classifier panel, numIteration is the maximum number of allowed iterations that algorithm repeated, colonySize is the size of colony of candidate solutions, alphaParameter is the alpha parameter used in the state transition rule that shows the relative importance of the pheromone, betaParameter is the beta parameter used in the state transition rule that shows the relative importance of heuristic information, evaporationRate is the evaporation rate of the pheromone, kFolds is the number of equal sized subsamples that is used in k-fold cross validation, and initPheromone is the initial value of the pheromone

  • Method Details

    • createSelectedFeatureSubset

      protected abstract int[] createSelectedFeatureSubset()
      This method creates the selected feature subset based on the best ant in the colony.
      Returns:
      the array of indices of the selected feature subset