Method and Apparatus for Classifying and Identifying Unknown Specimens using Spectral Properties
The Problem:
Much research has been conducted for military and related purposes in the field of target signature recognition via sonar and radar or by related spectral data identification. Target recognition and identification must be immediate so that an enemy target does not acquire target recognition first, for example, in military applications. Targets may intentionally change their signatures to attempt to foil recognition.
The Solution:
Researchers at the University of Tennessee have developed a Method and apparatus classifying specimens and media using spectral properties and identifying unknown specimens and media having like spectral properties. The informing databases comprising an electrical, electromagnetic, acoustic spectral database (ESD), a micro-body assemblage database (MAD) and a database of image data.
Measured properties of specimens, media, objects and entrained materials can be utilized, in conjunction with a database that supports search and retrieval based upon object similarities, to provide information about the object and to predict further properties or traits or values or measures thereof.
Benefits:
Dr. Doug Birdwell is a Professor Emeritus in the Department of Electrical and Computer Engineering at UT. His research expertise includes control systems, information processing, high-performance databases, data mining, and bioinformatics, Dr. Bridwell received his PhD in Electrical Engineering from MIT, specializing in reliable control systems and design.
Dr. Tsewei Wang is an Associate Professor Emeritus of Chemical and Biomolecular Engineering at UT. Her research interests include data mining, process monitoring and fault detection using multivariate statistical methods; and bioinformatics, especially in the field of DNA forensics, using DNA for human identification.