An algorithm for removing redundancy features in microarray data

With the continuous development of science and technology, information acquisition ability is constantly improved. It constantly produces all kinds of high-dimensional data, triggering the “dimension disaster”. It is urgent to reduce the dimension of these high-dimensional data and discover the feature that is truly meaningful. Here, a new multi-stage dimensionality reduction algorithm based on removing redundancy features is proposed. The irrelevant features are removed firstly, and then the redundant features are removed. The experiment result shows that the algorithm is feasible and effective in microarray data.