Class BiNormalSeparation

  • All Implemented Interfaces:
    AlphabetCarrying, ConstantMatrix, Vector,

    public class BiNormalSeparation
    extends RankedFeatureVector
    Bi-Normal Separation is a feature weighting algorithm introduced in: An Extensive Empirical Study of Feature Selection Metrics for Text Classification, George Forman, Journal of Machine Learning Research, 3:1289--1305, 2003. It was been shown to have excellent performance when used for feature selection and feature weighting on binary SVM classification tasks.
    Clint Burford
    See Also:
    Serialized Form
    • Constructor Detail

      • BiNormalSeparation

        public BiNormalSeparation​(InstanceList ilist)
        Create a new feature ranking for the given instance list.