Abstract: Now a days, data mining has been exploited to retrieve the valuable information in a wide spread fields especially in DNA microarray technology. The DNA mciroarray technology produces a huge amount of gene data i.e., expression levels of thousands of genes for a very few samples. From the microarray gene data, the process of extracting the required knowledge remains an open challenge. In order to retrieve the required information, gene classification is vital however, the task is complex because of the data characteristics, high dimensionality and smaller sample size. In this study, the propose an effective gene classification technique based on LPP and SVM. In the proposed gene classification technique firstly, the high dimensionality of the microarray gene data is reduced using LPP. The LPP is chosen for the dimensionality reduction because of its ability of preserving locality of neighborhood relationship. Secondly, the SVM is trained by the dimensionality reduced gene data for effective classification. SVM has the ability to learn with very few samples and so it is selected for the proposed technique. Hence, the classification technique developed with the blending of LPP and SVM results in effectual and powerful classification of gene expression data. Moreover, a comparative study is made with the ANN-based and PCA-based gene classification techniques.
J. Jacinth Salome and R. M. Suresh, 2011. An Effective Classification Technique for Microarray Gene Expression by Blending of LPP and SVM. Asian Journal of Information Technology, 10: 142-148.