A Sparse Coding Based Similarity Measure

In high dimensional data sets not all dimensions contain an equal amount of information and most of the time global features are more important than local differences. This makes it difficult to select a similarity measures that inherently considers these differences in weighting. We are presenting a sparse coding based similarity measure that is capable of extracting and emphasizing relevant elements of a signal given a reference data set.

• Type: Journal
• Year: 2009
• Where: DMIN
• Authors: Sebastian Klenk, Gunther Heidemann
• Keywords: Data Mining, DMIN 2009, Local Differences, Similarity Measure, Time Global Features