Neural network system and methods for analysis of organic materials and structures using spectral data
Abstract
Apparatus and processes are described 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:
- Issue Date:
- OSTI Identifier:
- 6047833
- Patent Number(s):
- 5218529
- Application Number:
- PPN: US 7-559649
- Assignee:
- Univ. of Georgia Research Foundation, Inc., Athens, GA (United States)
- DOE Contract Number:
- FG09-85ER13426; FG09-87ER13810
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 30 Jul 1990
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 37 INORGANIC, ORGANIC, PHYSICAL AND ANALYTICAL CHEMISTRY; 99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; NEURAL NETWORKS; DESIGN; ORGANIC COMPOUNDS; SPECTRA; DATA ANALYSIS; ABSORPTION SPECTROSCOPY; CARBOHYDRATES; GAS CHROMATOGRAPHY; INFRARED RADIATION; MASS SPECTROSCOPY; NUCLEAR MAGNETIC RESONANCE; OPERATION; TRAINING; X-RAY SPECTROSCOPY; CHROMATOGRAPHY; EDUCATION; ELECTROMAGNETIC RADIATION; MAGNETIC RESONANCE; RADIATIONS; RESONANCE; SEPARATION PROCESSES; SPECTROSCOPY; 400100* - Analytical & Separations Chemistry; 990200 - Mathematics & Computers
Citation Formats
Meyer, B J, Sellers, J P, and Thomsen, J U. Neural network system and methods for analysis of organic materials and structures using spectral data. United States: N. p., 1993.
Web.
Meyer, B J, Sellers, J P, & Thomsen, J U. Neural network system and methods for analysis of organic materials and structures using spectral data. United States.
Meyer, B J, Sellers, J P, and Thomsen, J U. Tue .
"Neural network system and methods for analysis of organic materials and structures using spectral data". United States.
@article{osti_6047833,
title = {Neural network system and methods for analysis of organic materials and structures using spectral data},
author = {Meyer, B J and Sellers, J P and Thomsen, J U},
abstractNote = {Apparatus and processes are described 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 = {6}
}