Systematic profile/feature-based intelligence for spectral sensors

Michael C. Vogt

doi:10.1117/12.417394

13 February 2001 Systematic profile/feature-based intelligence for spectral sensors

Michael C. Vogt

Proceedings Volume 4201, Optical Methods for Industrial Processes; (2001) https://doi.org/10.1117/12.417394
Event: Environmental and Industrial Sensing, 2000, Boston, MA, United States

Abstract

12 Argonne National Laboratory has been creating a special- purpose software-engineering tool to support research and development of spectrum-output-type [chemical] sensors. The modular software system is called SAGE, the Sensor Algorithm Generation Environment and includes general- purpose signal conditioning algorithms (GP/SAGE) as well as intelligent classifiers, pattern recognizers, response accelerators, and sensitivity analyzers. GP/SAGE is an implementation of an approach for delivering a level of encapsulated intelligence to a wide range of sensors and instruments. It capitalizes on the generic classification and analysis needed to process most profile-type data. The GP/SAGe native data format is a generalized 1D vector, signature, or spectrum. GP/SAGE modules form a computer- aided software engineering `workbench' where users can experiment with various conditioning, filtering, and pattern recognition stages, then automatically generate final algorithm source code for data acquisition and analysis systems.

Citation Download Citation

Michael C. Vogt "Systematic profile/feature-based intelligence for spectral sensors", Proc. SPIE 4201, Optical Methods for Industrial Processes, (13 February 2001); https://doi.org/10.1117/12.417394

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available