skip to main content
DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Neural network system and methods for analysis of organic materials and structures using spectral data

Abstract

Apparatus and processes for recognizing and identifying materials. Characteristic spectra are obtained for the materials via spectroscopy techniques including nuclear magnetic resonance spectroscopy, infrared absorption analysis, x-ray analysis, mass spectroscopy and gas chromatography. Desired portions of the spectra may be selected and then placed in proper form and format for presentation to a number of input layer neurons in an offline neural network. The network is first trained according to a predetermined training process; it may then be employed to identify particular materials. Such apparatus and processes are particularly useful for recognizing and identifying organic compounds such as complex carbohydrates, whose spectra conventionally require a high level of training and many hours of hard work to identify, and are frequently indistinguishable from one another by human interpretation.

Inventors:
 [1];  [2];  [3]
  1. (Athens, GA)
  2. (Suwanee, GA)
  3. (Fredricksberg, DK)
Issue Date:
Research Org.:
University of Georgia Research Foundation, Inc. (Athens, GA)
Sponsoring Org.:
USDOE
OSTI Identifier:
868814
Patent Number(s):
5218529
Assignee:
University of Georgia Research Foundation, Inc. (Athens, GA) SRO
DOE Contract Number:  
FG09-85ER13426; FG09-87ER13810
Resource Type:
Patent
Country of Publication:
United States
Language:
English
Subject:
neural; network; methods; analysis; organic; materials; structures; spectral; data; apparatus; processes; recognizing; identifying; characteristic; spectra; obtained; via; spectroscopy; techniques; including; nuclear; magnetic; resonance; infrared; absorption; x-ray; mass; gas; chromatography; desired; portions; selected; placed; proper; form; format; presentation; input; layer; neurons; offline; trained; according; predetermined; training; process; employed; identify; particular; particularly; useful; compounds; complex; carbohydrates; conventionally; require; level; hours; hard; frequently; indistinguishable; human; interpretation; resonance spectroscopy; gas chromatography; organic compound; organic materials; magnetic resonance; neural network; organic compounds; particularly useful; nuclear magnetic; organic material; gas chromatograph; mass spectroscopy; particular materials; particular material; training process; neural net; desired portions; desired portion; materials via; /702/700/706/

Citation Formats

Meyer, Bernd J., Sellers, Jeffrey P., and Thomsen, Jan U. Neural network system and methods for analysis of organic materials and structures using spectral data. United States: N. p., 1993. Web.
Meyer, Bernd J., Sellers, Jeffrey P., & Thomsen, Jan U. Neural network system and methods for analysis of organic materials and structures using spectral data. United States.
Meyer, Bernd J., Sellers, Jeffrey P., and Thomsen, Jan U. Fri . "Neural network system and methods for analysis of organic materials and structures using spectral data". United States. https://www.osti.gov/servlets/purl/868814.
@article{osti_868814,
title = {Neural network system and methods for analysis of organic materials and structures using spectral data},
author = {Meyer, Bernd J. and Sellers, Jeffrey P. and Thomsen, Jan U.},
abstractNote = {Apparatus and processes for recognizing and identifying materials. Characteristic spectra are obtained for the materials via spectroscopy techniques including nuclear magnetic resonance spectroscopy, infrared absorption analysis, x-ray analysis, mass spectroscopy and gas chromatography. Desired portions of the spectra may be selected and then placed in proper form and format for presentation to a number of input layer neurons in an offline neural network. The network is first trained according to a predetermined training process; it may then be employed to identify particular materials. Such apparatus and processes are particularly useful for recognizing and identifying organic compounds such as complex carbohydrates, whose spectra conventionally require a high level of training and many hours of hard work to identify, and are frequently indistinguishable from one another by human interpretation.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {1993},
month = {1}
}

Patent:

Save / Share: