Combined neural network approach for mining order-preserving sub matrices from repeated dataset

Abstract

Order-preserving sub matrices (OPSM's) have been shown useful in capturing concurrent patterns in data when the relative magnitudes of data items are more important than their correct values. For example, in analyzing gene expression profiles obtained from micro-array experiments, the comparative magnitudes are important both since they represent the change of gene activities across the experiments, and since there is naturally a high level of noise in data that makes the exact values non trustable. To manage with data noise, repeated experiments are often conducted to collect multiple measurements. This paper includes Eigen value decomposition combined for solving data mining from order preserving sub-matrices from repeated dataset. Experimental results shows this method gives far better results in terms of time and candidate pattern ratio.