摘要
应用主分量分析法和K-近邻法对基因芯片(微阵列)数据进行分析。主分量分析法是一种提取海量数据有效特征的有效方法,可以获得与原来基因芯片数据更为接近的成分的提取特征的效果。实验结果表明,用主分量分析法预先对数据处理可以提高基因芯片数据分析的准确性。
The data of gene chip (micoarray) is analyzed by applying the principle component analysis (PCA) and K-Nearest Neighbor. PCA, a developed and efficient method for analyzing numerous data, can extract the features much closer to the gene data expression of originality. It shows that when PCA is pre-disposing of the data set, the accuracy of classification of gasoline is improved noticeably.
出处
《北华大学学报(自然科学版)》
CAS
2008年第1期12-15,共4页
Journal of Beihua University(Natural Science)
关键词
基因芯片
主分量分析
K-近邻法
Gene chip
Principle component analysis (PCA)
K-Nearest Neighbor(KNN)