Application of neural networks to compound identification in open-path FT-IR spectrometry

Mathematics – Logic

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

Optical Computers, Logic Elements, Interconnects, Switches, Neural Networks, Organic Compounds, Polymers

Scientific paper

Neural networks have been applied in an attempt to determine the feasibility of recognizing whether or not a given analyte is present in an open-path Fourier transform infrared (OP/FT-IR) spectrum measured at low resolution. The neural network architecture used in this paper was a two layer feed-forward network trained by fast backpropagation. A hyperbolic tangent sigmoid transfer function was used in both layers. Each network has only one output and was trained to recognize only one compound. Synthesized open-path spectra, which were obtained by digitally adding randomly scaled reference spectra and open-path background spectra, were used to train the neural networks. Spectral windows containing only the absorption bands of the analyte were used as the neural network input. Trained neural networks were tested by experimentally measured OP/FT-IR spectra.

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

Application of neural networks to compound identification in open-path FT-IR spectrometry 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 neural networks to compound identification in open-path FT-IR spectrometry, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Application of neural networks to compound identification in open-path FT-IR spectrometry will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-1330427

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.