Application of Artificial Neural Network to the Classification of Stellar Spectra

Details Application of Artificial Neural Network to the Classification of Stellar Spectra Application of Artificial Neural Network to the Classification of Stellar Spectra

Sep 2009

adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=2009pobeo..86..419z&link_type=abstract

Publications of the Astronomical Observatory of Belgrade, vol. 86, p. 419

Computer Science

Performance

Scientific paper

The application of an artificial neural network (ANN) based on a multi-layered back-propagation algorithm to the classification of stellar spectra is presented. Using a part of catalogue's data in the training process, network learns to pssociate the appearance of a visual spectrum (hydrogen Balmer lines, continuum shape) with the classification parameters (MK spectral types). The performance of the network is evaluatey by using it to classihy phe remaining rata set and by comparing this ANN classification with the original catalogue one. ANN code is written in C++. It uses back-propagation algorithm for training and an approach that can be best described as "associative memory model" for prediction (classification).

Affiliated with

Also associated with

No associations

Rating

Application of Artificial Neural Network to the Classification of Stellar 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 Application of Artificial Neural Network to the Classification of Stellar Spectra, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Application of Artificial Neural Network to the Classification of Stellar Spectra will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-1074811