A sparse feature representation for genetic data analysis

Feature representation is one of the key research issues in machine learning. In some applications with high dimensionality of data, e.g. genomie microarray data, obtaining a good feature representation with effective dimensionality reduction still remains a challenge. In this paper, instead of selecting a subset of original features by feature selection, we use sparse autoencoder to find a reconstructed feature representation for genetic data analysis. The performance of our proposed method is empirically evaluated using one of the genomie microarray dataset provided in ASU Feature Selection Repository. The results show that the proposed method yield better classification accuracy than some representative feature selection methods.