Advanced visualization of Self-Organizing Maps with vector fields

• Published in: Neural networks Vol. 19; no. 6; pp. 911 - 922
• Main Authors: Pölzlbauer, Georg, Dittenbach, Michael, Rauber, Andreas
• Format: Journal Article Conference Proceeding
• Language: English
• Published: Oxford Elsevier Ltd 01-07-2006; Elsevier Science
• Subjects: Algorithms; Applied sciences; Artificial Intelligence; Borderline; Cluster Analysis; Computer Graphics; Computer science; control theory; systems; Computer Simulation; Connectionism. Neural networks; Databases, Factual; Exact sciences and technology; Gradient Field; Image processing; Information theory; Information, signal and communications theory; Neural Networks (Computer); Pattern Recognition, Automated - methods; Self-Organizing Maps; Signal and communications theory; Signal processing; Signal representation. Spectral analysis; Signal, noise; Telecommunications and information theory; Visualization; Visualization; Gradient Field; Self-Organizing Maps; Borderline; Cluster analysis; Data analysis; Automatic classification; Correlation; Industrial application; Data processing; Information extraction; Neural network; Data mining; Signal classification; Detail level; Self-organising feature maps; Multidimensional database; Data visualization; Gradient method; Vector field
• ISSN: 0893-6080; 1879-2782
• DOI: 10.1016/j.neunet.2006.05.013

Self-Organizing Maps have been applied in various industrial applications and have proven to be a valuable data mining tool. In order to fully benefit from their potential, advanced visualization techniques assist the user in analyzing and interpreting the maps. We propose two new methods for depicting the SOM based on vector fields, namely the Gradient Field and Borderline visualization techniques, to show the clustering structure at various levels of detail. We explain how this method can be used on aggregated parts of the SOM that show which factors contribute to the clustering structure, and show how to use it for finding correlations and dependencies in the underlying data. We provide examples on several artificial and real-world data sets to point out the strengths of our technique, specifically as a means to combine different types of visualizations offering effective multidimensional information visualization of SOMs.