Mathematics – Logic
Scientific paper
Jun 1998
adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=1998aipc..430..245y&link_type=abstract
The eleventh international conference on fourier transform spectroscopy. AIP Conference Proceedings, Volume 430, pp. 245-248 (1
Mathematics
Logic
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.
Griffiths Peter R.
Yang Husheng
No associations
LandOfFree
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.
Profile ID: LFWR-SCP-O-1330427