Cancer Gene Expression Data Attribute Partial Ordered Representation And Knowledge Discovery
In this paper,basic concepts and the related definitions of attribute partial-ordered structure diagram have been researched,and a scheme of knowledge discovery to collect new information from cancer gene expression data has been proposed,which was based on the feature selection and attribute partialordered structure diagram.Then the resource of lung adenocarcinoma gene expression data to be processed has been introduced in the paper.Both the T-test method and the Elastic net method have been used in the feature gene selection of lung adenocarcinoma gene expression data,and a total of 35 feature genes have been selected.This process sharply reduced the dimension of the data set.Finally,the c# program has been applied to disperse the data in order to generate the form of binary formal context,then the structural partial-ordered attribute diagram was generated,and the knowledge discovery has been produced based on the distribution and aggregation hierarchy diagram.
attribute partial-ordered structure diagram lung adenocarcinoma gene expression data feature selection knowledge discovery
Yang Li Wenxue Hong Shaoxiong Li Jialin Song Xulong Liu
Institute of Electrical Engineering, Yanshan University Qinhuangdao, 066004, China Institute of Electrical Engineering, Yanshan University Qinhuangdao, 066004, China;Big Data Visualiz College of Computer and Communication Engineering, Northeastern University at Qinhuangdao 066004, Qi
国际会议
秦皇岛
英文
861-865
2015-09-18（万方平台首次上网日期，不代表论文的发表时间）