https://github.com/mvazramos/cbpso-pca
Implementation of the paper "A new principal component analysis by particle swarm optimization with an environmental application for data science".
https://github.com/mvazramos/cbpso-pca
cbpso-pca clustering clustering-of-variables particle-swarm-optimization pca r
Last synced: 8 months ago
JSON representation
Implementation of the paper "A new principal component analysis by particle swarm optimization with an environmental application for data science".
- Host: GitHub
- URL: https://github.com/mvazramos/cbpso-pca
- Owner: mvazramos
- License: mit
- Created: 2021-06-09T09:03:45.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2024-04-05T23:13:30.000Z (over 1 year ago)
- Last Synced: 2025-01-02T15:32:26.353Z (10 months ago)
- Topics: cbpso-pca, clustering, clustering-of-variables, particle-swarm-optimization, pca, r
- Language: R
- Homepage:
- Size: 208 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# CBPSO-PCA (An R Implementation)
This implementation resulted from my studies, in my Master's degree dissertation on "Clustering of Variables in High Dimensional Data", and was based on the paper from Ramirez-Figueroa *et al.*:
*Ramirez-Figueroa, J.A., Martin-Barreiro, C., Nieto-Librero, A. et al. A new principal component analysis by particle swarm optimization with an environmental application for data science. Stoch Environ Res Risk Assess (2021). https://doi.org/10.1007/s00477-020-01961-3*
Also available in pre-print in aRxiv.org : *https://arxiv.org/abs/2004.10701*
This algorithm was not designed by me, I merely implemented it in **R**, in order to compare it with other algorithms. It is not original work of mine.
The data file used to reproduce the results from the paper is freely availabe in: *http://weppi.gtk.fi/publ/foregsatlas/ForegsData.php*, in the subsoil file section.
The **functions** used to compute the **random matrices** and to compute the **loading matrices** were not writen by me, they are available in the **biplotbootGUI** package, in the **CDpca** function conde - available at https://CRAN.R-project.org/package=biplotbootGUI.
The produced work was done under the supervision of the Associate Professor Adelaide Freitas.
I would also like to deeply thanks the authors of the paper for their time and opneness to discuss details of their paper and validate my implementation.