欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
从癌症基因表达谱分析入手，针对基因表达谱维数高、样本少的特点，提出一种用于癌症分类的基于邻域粗糙集和概率神经网络集成的分类方法。首先利用Relief算法对基因进行排序，然后利用邻域粗糙集选取分类特征基因，最后结合概率神经网络集成分类模型进行癌症分类。实验结果表明，该方法可以快速有效地选取癌症特征基因，能获得更好的分类效果。
英文摘要：
Begined with the cancer gene expression profiles analysis and aiming at the characteristics of high dimension and small samples, this paper proposed a classification method for cancer classification which was based on neighborhood rough set and probabilistic neural networks ensemble. Firstly, sorted genes by using Relief algorithm, then selected classification in- formative genes by using the neighborhood rough set, lastly, classified cancers with probabilistic neural networks ensemble classification model. The experiment results show that the method can promptly and effectively select cancer informative genes, and obtain better classification results.
同期刊论文项目
同项目期刊论文
期刊信息
位置：