Feature Extraction for DNA Microarray Data

In this study we perform wavelet analysis on high dimensional microarray data. We perform two methods of feature extraction on microarray data, using approximation coefficients and detail coefficients. A set of orthogonal wavelet approximation coefficients based on wavelet decomposition are extracted to compress the gene profiles and reduce the dimensionality of microarray data. A set of orthogonal wavelet detail coefficients are extracted to characterize the localized features of gene profiles and reduce dimensionality. Experiments are performed on two datasets. The experimental results show a highly competitive accuracy is achieved compared to the best performance of other kinds of classification models using wavelet coefficients.