Application of PCA and SPCA in classification

Chenze Fan

doi:10.1117/12.2627693

22 April 2022 Application of PCA and SPCA in classification

Chenze Fan

Proceedings Volume 12163, International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2021); 121631X (2022) https://doi.org/10.1117/12.2627693
Event: International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2021), 2021, Nanjing, China

Abstract

In this article, we first introduce the classic PCA, including its ideas and efficient algorithms like SVD and how PCA can be seen as a linear regression problem. Then the author will introduce SPCA by L1 Penalty and also provide an algorithm to calculate its loading matrix. After that, the article focuses on the differences between PCA and SPCA by applying them on several simple cases. Finally, the author will apply them on 2 gene expression cases. It turns out that in the first data set which has more samples than features, PCA performs better than SPCA. While on the second data set which has more features than samples, SPCA performs better than PCA. As a result, the sparsity of SPCA may be useful when data set contains tens of thousands of features.

Citation Download Citation

Chenze Fan "Application of PCA and SPCA in classification", Proc. SPIE 12163, International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2021), 121631X (22 April 2022); https://doi.org/10.1117/12.2627693

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available