Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

From outliers to prototypes: Ordering data

: Harmeling, S.; Dornhege, G.; Tax, D.; Meinecke, F.; Müller, K.-R.


Puntonet, C.G.:
Blind source separation and independent component analysis : Selected papers from the ICA 2004 meeting, Granada, Spain
Amsterdam: Elsevier, 2006 (Neurocomputing 69.2006, Nr.13-15)
International Conference on Independent Component Analysis and Blind Signal Seperation (ICA) <5, 2004, Granada>
Conference Paper, Journal Article
Fraunhofer FIRST ()

We propose simple and fast methods based on nearest neighbors that order objects from high-dimensional data sets from typical points to untypical points. On the one hand, we show that these easy-to-compute orderings allow us to detect outliers (i.e. very untypical points) with a performance comparable to or better than other often much more sophisticated methods. On the other hand, we show how to use these orderings to detect prototypes (very typical points) which facilitate exploratory data analysis algorithms such as noisy nonlinear dimensionality reduction and clustering. Comprehensive experiments demonstrate the validity of our approach.