Subscribe Now Subscribe Today
Science Alert
 
FOLLOW US:     Facebook     Twitter
Blue
   
Curve Top
Journal of Artificial Intelligence
  Year: 2010 | Volume: 3 | Issue: 3 | Page No.: 119-134
DOI: 10.3923/jai.2010.119.134
Comparative Study of Dimensionality Reduction Techniques for Data Visualization
F.S. Tsai

Abstract:
This study analyzed current linear and nonlinear dimensionality reduction techniques in the context of data visualization. A summary of current linear and nonlinear dimensionality reduction techniques was presented. Linear techniques such as Principal Component Analysis (PCA) and Multidimensional Scaling (MDS) are good for handling data that is inherently linear in nature. Nonlinear techniques such as Locally Linear Embedding (LLE), Hessian LLE (HLLE), Isometric Feature Mapping (Isomap), Local Tangent Space Alignment (LTSA), Kernel PCA , diffusion maps and multilayer autoencoders can perform well on nonlinear data. Experiments were conducted on varying the neighborhood, density and noise of data. Results on two real-world datasets (ORL face and business blogs) indicate that dimensionality reduction techniques generally performed better on the synthetic data. In our experiments, the best performing algorithm overall for both real-world and artificial data was Isomap.
PDF Fulltext XML References Citation Report Citation
 RELATED ARTICLES:
  •    Story Summary Visualizer Using L Systems
  •    Facial Gender Classification with Eigenfaces and Least Squares Support Vector Machine
How to cite this article:

F.S. Tsai , 2010. Comparative Study of Dimensionality Reduction Techniques for Data Visualization. Journal of Artificial Intelligence, 3: 119-134.

DOI: 10.3923/jai.2010.119.134

URL: https://scialert.net/abstract/?doi=jai.2010.119.134

 
COMMENT ON THIS PAPER
 
 
 

 

 
 
 
 
 
 
 
 
 

 
 
 
 
 
 

       

       

Curve Bottom