Abstract: The design of a pattern classifier includes an attempt
to select, among a set of possible features, a minimum subset of
weakly correlated features that better discriminate the pattern classes.
This is usually a difficult task in practice, normally requiring the
application of heuristic knowledge about the specific problem
domain. The selection and quality of the features representing each
pattern have a considerable bearing on the success of subsequent
pattern classification. Feature extraction is the process of deriving
new features from the original features in order to reduce the cost of
feature measurement, increase classifier efficiency, and allow higher
classification accuracy. Many current feature extraction techniques
involve linear transformations of the original pattern vectors to new
vectors of lower dimensionality. While this is useful for data
visualization and increasing classification efficiency, it does not
necessarily reduce the number of features that must be measured
since each new feature may be a linear combination of all of the
features in the original pattern vector. In this paper a new approach is
presented to feature extraction in which feature selection, feature
extraction, and classifier training are performed simultaneously using
a genetic algorithm. In this approach each feature value is first
normalized by a linear equation, then scaled by the associated weight
prior to training, testing, and classification. A knn classifier is used to
evaluate each set of feature weights. The genetic algorithm optimizes
a vector of feature weights, which are used to scale the individual
features in the original pattern vectors in either a linear or a nonlinear
fashion. By this approach, the number of features used in classifying
can be finely reduced.