Principal component Analysis (Principal Component ANALYSIS,PCA

principal component Analysis ( Principal Component Analysis , PCA is a multivariate statistical analysis method that transforms multiple variables through a linear transformation to select fewer important variables.

principle: When we use the statistical analysis method to study the multi-variable problem, the number of variables will increase the complexity of the subject. It is natural to expect a smaller number of variables to get more information. In many cases, there is a certain correlation between the variables, when there is a certain correlation between the two variables, it can be explained that the two variables reflect this subject's information has some overlap. Principal component analysis is for all previously proposed variables, the repetition of variables (closely related variables) to delete redundant, to create as few new variables as possible, so that these new variables are 22 irrelevant, and these new variables in the information to reflect the subject as far as possible to maintain the original information.

Try to regroup the original variables into a new set of unrelated composite variables, and according to the actual need to take a few of the less complex variables as much as possible to reflect the original variable information of the statistical method is called principal component analysis or principal component analysis, but also mathematically used to reduce the dimension of a method.

PCA   x-y The coordinates are decomposed into u1-u2 u1 The main axis of the characteristic changes ( intrinsic u2 The characteristics of a small change, can be fully understood as some noise disturbance and not to consider it. PCA The task is to find the u1 u2

program_lpgpca:http://www.codeforge.cn/article/224647

Principal component Analysis PCA:http://www.cnblogs.com/zhangchaoyang/articles/2222048.html http://tieba.baidu.com/p/2199392852#
PCA (principal component analysis) detailed (for beginners) combined with MATLAB: http://www.360doc.com/content/14/0526/06/15831056_380900310.shtml

On The understanding of principal component Analysis (PCA) algorithm:

http://blog.csdn.net/passball/article/details/24037593
principal component analysis:http://ufldl.stanford.edu/wiki/index.php/principal Component Analysis


Eigenvalue decomposition, singular value decomposition, PCA concept finishing:
http://blog.csdn.net/jinshengtao/article/details/18448355

Principal component Analysis (Principal Component ANALYSIS,PCA