摘要
对当前基因芯片数据的特征选择算法、效能进行综述并比较其优劣性,指出从特征自身特点出发的特征选择法可获得较好的分类效能和生物医学应用,同时也可为致病基因的寻找提供重要依据。
The paper summarizes the current gene chip data feature selection methods and their efficacies,compares their advantages and disadvantages.It points out that the feature selection method which starts from its own characteristics can obtain better classification performance and biomedical applications,at the same time provide important foundations for finding disease -causing genes.
出处
《医学信息学杂志》
CAS
2012年第10期44-47,共4页
Journal of Medical Informatics
基金
齐齐哈尔市科学技术局科学技术计划项目
关键词
基因芯片
特征选择
过滤法
缠绕法
学习器
Gene chip
Feature selection
Filtration method
Twining method
Learner