• TUCS Publication Series
• How to Publish in TUCS Series
• Publication Search
• Publication Graph
• Publication Input
• Publication Input Guide
• JuFo Browser

Replacing the time dimension: A Self-Organizing Time Map over any variable

Peter Sarlin, Replacing the time dimension: A Self-Organizing Time Map over any variable. In: Barbara Hammer, Thomas Martinetz, Thomas Villman (Eds.), Proceedings of the Workshop on New Challenges in Neural Computation (NC^2), 17–24, Machine Learning Reports, 2013.

Abstract:

The Self-Organizing Time Map (SOTM) is a recently introduced adaptation of the Self-Organizing Map for visualizing dynamics in cluster structures, or visual dynamic clustering. This paper extends the use of the SOTM to visualize changes in cluster structures over any variable of ordinal, cardinal or higher level of measurement. The rationale and functioning of the SOTM over any variable is illustrated with two real-world cases related to cluster structures in welfare, poverty and development indicators for a global set of countries.

BibTeX entry:

@INPROCEEDINGS{inpSarlin_Peter13c,
  title = {Replacing the time dimension: A Self-Organizing Time Map over any variable},
  booktitle = {Proceedings of the Workshop on New Challenges in Neural Computation (NC^2)},
  author = {Sarlin, Peter},
  editor = {Hammer, Barbara and Martinetz, Thomas and Villman, Thomas},
  publisher = {Machine Learning Reports},
  pages = {17–24},
  year = {2013},
}

Belongs to TUCS Research Unit(s): Data Mining and Knowledge Management Laboratory

Edit publication