摘要
在Matlab的基础上,以3种经典的数据降维方法——主成分分析(PCA)、线性判别分析(LDA)和保局投影算法(LPP)为例,给出3种降维方法的最优化比较结果,对数据降维实验方法进行了探讨和设计。通过UCI标准数据集和ORL、Yale人脸数据集的比较实验表明:3种降维方法均能较好地完成降维任务,其中LPP和LDA数据降维方法效率较优,但在不同的实验条件下,表现略有不同。
The dimension reduction experiments based on Matlab simulation are designed.The performances of several traditional dimension reduction methods such as the principal component analysis(PCA),the linear discriminant analysis(LDA),the locally preserving projection(LPP)algorithm are compared in the standard datasets,and it can be concluded that the above methods can complete the dimension reduction task while their performances are slightly different from each other in different cases.
出处
《实验技术与管理》
CAS
北大核心
2016年第9期119-121,133,共4页
Experimental Technology and Management
基金
山西省高等学校科技创新项目(2014142)
关键词
数据降维
MATLAB仿真
主成分分析
线性判别分析
保局投影算法
dimension reduction
Matlab simulation
principal component analysis(PCA)
linear discriminant analysis(LDA)
locally preserving projection(LPP)algorithm