05218529 is referenced by 91 patents and cites 2 patents.

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.

Title
Neural network system and methods for analysis of organic materials and structures using spectral data
Application Number
7/559649
Publication Number
5218529
Application Date
July 30, 1990
Publication Date
June 8, 1993
Inventor
Jan U Thomsen
Fredricksberg
DK
Jeffrey P Sellers
Suwanee
GA, US
Bernd J Meyer
Athens
GA, US
Agent
Kilpatrick & Cody
Assignee
University of Georgia Research Foundation
GA, US
IPC
G06F 15/42
View Original Source