|
Abstract
|
|
|---|---|
| Self-Organizing Maps (SOM) are a well know classification tool, commonly used in a wide variety of problems. The two important features of SOM, topological preservation and easy visualization, give it great potential for analyzing multi-dimensional time series, specifically air concentrationtime series in an urban monitoring network. In order to reveal structures and environmental behavior, this paper research the application of SOM in the representation of multi-dimensional air time series. First, SOMs are applied to cluster the time series and to project each multi-dimensional vector onto a two-dimensional SOM while preserving the topological relationships of the original data. Then, the easy visualization of the SOMs is utilized to investigate the physical meaning of the clusters as well as how the air concentration vectors evolve with time. Analysis of real world air data shows the effectiveness of these methods for air concentrations analysis, for they can capture the nonlinear information of air concentrations data | |
|
International
|
Si |
|
Congress
|
1st European Workshop on Turbulence and Fractals |
|
|
960 |
|
Place
|
Madrid, Es`paña |
|
Reviewers
|
Si |
|
ISBN/ISSN
|
1870-4069 |
|
|
|
|
Start Date
|
10/12/2009 |
|
End Date
|
10/12/2009 |
|
From page
|
8 |
|
To page
|
14 |
|
|
Proc. of 1st European Workshop on Turbulence and Fractals |