基于最小二乘模糊支持向量机的基因分类研究

With the large number of gene expression data araise, how to analyze these data and extract valuable biological information has become an extremely important issue, and it is a revolutionary change for the prediction and treatment of cancer .Gene classification is a commonly used method for gene expression data processing.A new fuzzy Least square SVM is proposed. The contribution of each sample is defined by setting the fuzzy memberships.By considering the distance not only between the types of samples and the center of classification but also between the samples and samples,noises and outliers are removed.At the same time,the performance of the proposed method on randomly generated data and the United States Wisconsin Breast Cancer Database (WDBC) data is reported to illustrate its effctiveness.