Efficient Extraction and Classification of Spectra

Details Efficient Extraction and Classification of Spectra Efficient Extraction and Classification of Spectra

Oct 2011

adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=2011epsc.conf.1266s&link_type=abstract

EPSC-DPS Joint Meeting 2011, held 2-7 October 2011 in Nantes, France. http://meetings.copernicus.org/epsc-dps2011, p.1266

Computer Science

Scientific paper

Imaging spectrometers deliver very large amounts are data which call for automatic summarisation for exploratory data analysis. In the frequent absence of ground truth for planetary data, unsupervised analysis methods can provide unbiased information about the data. In this work, we investigate the use of unsupervised analysis based on non-negative matrix approximation [3, 4] combined with subsequent classification [2] to provide scientists with succinct summaries. Since typically there often is no ground truth to compare to, unsupervised rather than supervised methods allow to extract new information from data sets. We designed particularly efficient methods to cope with the large data volumes which are typical for this type of instrument.

Affiliated with

Also associated with

No associations

Rating

Efficient Extraction and Classification of Spectra does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Efficient Extraction and Classification of Spectra, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Efficient Extraction and Classification of Spectra will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-1483503