MATLAB File Help: prtFeatSelSfs
  prtFeatSelSfs   Sequential forward feature selection object.
     FEATSEL = prtFeatSelSfs creates a sequental forward feature selection
     FEATSEL = prtFeatSelSfs(PROPERTY1, VALUE1, ...) constructs a
     prttFeatSelSfs object FEATSEL with properties as specified by
     A prtFeatSelSfsobject has the following properties:
     nFeatures             - The number of features to be selected
     showProgressBar       - Flag indicating whether or not to show the
                             progress bar during feature selection.
     evaluationMetric      - The metric to be used to determine which
                             features are selected. evaluationMetric must
                             be a function handle. The function handle must
                             be in the form:
                             @(dataSet)prtEval(prtClass, dataSet, varargin)
                             where prtEvak is a prtEval function, prtClass
                             is a prt classifier object, and varargin
                             represents optional input arguments to a
                             prtEval function.
     peformance            - The performance obtained by the using the
                             features selected.
     selectedFeatures      - The indices of the features selected that gave
                             the best performance.
    A prtFeatSelExhaustive object inherits the TRAIN and RUN methods
    from prtClass.
    dataSet = prtDataGenFeatureSelection;         % Generate a data set
    featSel = prtFeatSelSfs;          % Create a feature selction object
    featSel.nFeatures = 3;            % Select only one feature of the data
    featSel = featSel.train(dataSet); % Train the feature selection object
    outDataSet =;% Extract the data set with only the
                                      % selected features
    %   Change the scoring function to prtScorePdAtPf, and change the
    %   classification method to prtClassMAP
    featSel.evaluationMetric = @(DS)prtEvalPdAtPf(prtClassMap, DS, .9);
    featSel = featSel.train(dataSet);
    outDataSet =;
See Also
Class Details
Superclasses prtFeatSel
Sealed false
Construct on load false
Constructor Summary
prtFeatSelSfs Sequential forward feature selection object. 
Property Summary
dataSet The training prtDataSet, only stored if verboseStorage is true.  
dataSetSummary Structure that summarizes prtDataSet. 
evaluationMetric The metric used to evaluate performance 
isCrossValidateValid False 
isSupervised True 
isTrained Indicates if prtAction object has been trained. 
nFeatures General Classifier Properties 
name Sequentual Feature Selection 
nameAbbreviation SFS 
performance The evalutationMetric for the selected features 
selectedFeatures The integer values of the selected features 
userData User specified data 
verboseStorage Specifies whether or not to store the training prtDataset. 
Method Summary
  crossValidate Cross validate prtAction using prtDataSet and cross validation keys. 
  get get the object properties 
  kfolds Perform K-folds cross-validation of prtAction 
  optimize Optimize action parameter by exhaustive function maximization. 
  run Run a prtAction object on a prtDataSet object. 
  set set the object properties 
  train Train a prtAction object using training a prtDataSet object.