Paper Info
Title
Genetic algorithm optimized feature transformation: a comparison with different classifiers
Abstract
When using a Genetic Algorithm (GA) to optimize the feature space of pattern classification problems, the performance improvement is not only determined by the data set used, but also depends on the classifier. This work compares the improvements achieved by GA-optimized feature transformations on several simple classifiers. Some traditional feature transformation techniques, such as Principal Components Analysis (PCA) and Linear Discriminant Analysis (LDA) are also tested to see their effects on the GA optimization. The results based on some real-world data and five benchmark data sets from the UCI repository show that the improvements after GA-optimized feature transformation are in reverse ratio with the original classification rate if the classifier is used alone. It is also shown that performing the PCA and LDA transformations on the feature space prior to the GA optimization improved the final result.
Year
DOI
Venue
2003
10.1007/3-540-45110-2_108
genetic and evolutionary computation conference
Keywords
Field
DocType
principal components analysis,real-world data,linear discriminant analysis,different classifier,lda transformation,ga-optimized feature transformation,genetic algorithm optimized feature,ga optimization,benchmark data set,original classification rate,traditional feature transformation technique,feature space,genetic algorithm,principal component analysis
Data mining,Dimensionality reduction,Feature selection,Computer science,Artificial intelligence,Classifier (linguistics),k-nearest neighbors algorithm,Feature vector,Pattern recognition,Linear discriminant analysis,Linear classifier,Machine learning,Principal component analysis
Conference
Citations 
PageRank 
References 
5
0.65
12
Authors
5
Name
Order
Citations
PageRank
Zhijian Huang150.65
Min Pei250.65
Erik Goodman314515.19
Yong Huang450.65
Gaoping Li561.42