强相关树基因选择方法及AE-RSVM分类研究

Strong correlative tree for gene selection and AE-RSVM for classification

对肿瘤基因表达谱进行分析,从而有效区分正常样本与肿瘤样本的关键是:准确找出能够决定样本类别的最少特征基因,并用一个性能较好的分类器进行分类预测。针对该问题,用修订的特征记分准则(RFSC)去除分类无关基因;对两两冗余法进行改进,提出强相关树法用于冗余基因的去除;对粗糙支持向量机(RSVM)改进,提出近似等价粗糙支持向量机(AE-RSVM)对样本集进行分类测试。以肿瘤样本集为例进行测试,实验结果表明了提出方法的可行性和有效性。

The key of distinguishing between normal and tumor samples effectively for tumor gene expression data is to find out the fewest genes which can predict the classes, then use a good performance classifier to classify. Faced with the problem, it uses the Revised Feature Score Criterion（RFSC） to remove the genes irrelevant to the classification task. It improves the pair-wise redundancy method, proposes strong correlative tree to filter the redundant gene. It improves the Rough Support Vector Machine （RSVM） and proposes the Approximate Equivalence Rough Support Vector Machine（AE-RSVM）, and then validates classifica- tion for data sets. Using the tumor data set to test, the experimental results show the feasibility and effectiveness of the method proposed in this paper.