Many engineering groups desire to construct instrumentation to replace dog-handler teams in identifying and localizing chemical mixtures. This goal requires performance specifications for an “artificial dog-handler team”. Progress toward generating such specifications from laboratory tests of dog-handler teams has been made recently at the Sensory Research Institute, and the method employed is amenable to the measurement of tasks representative of the decision-making that must go on when such teams solve problems in actual (and therefore informationally messy) situations. As progressively more quantitative data are obtained on progressively more complex odor tasks, the boundary conditions of dog-handler performance will be understood in great detail. From experiments leading to this knowledge, one ca develop, as we do in this paper, a taxonomy of test conditions that contain various subsets of the variables encountered in “real world settings”. These tests provide the basis for the rigorous testing that will provide an improved basis for deciding when biological sensing approaches (e.g. dog-handler teams) are best and when “artificial noses” are most valuable.
KEYWORDS: Neural networks, Sensors, Chemical analysis, Nose, Biological and chemical sensing, Chemical detection, Calibration, Control systems, Humidity, Adaptive control
The Sensory Research Institute at the Florida State University has quantitatively characterized a chemical residue detection system with adaptive neural net data processing. Two separate configurations, "Stormy" and "Gaea", were trained by exposure to decreasing amounts of n-amyl acetate from chemical emitters randomly distributed among a collection of non-emitters. The concentration of chemical in the sampled air stream was controlled precisely. The detection threshold for "Stormy" was 1.14 ppt; that for "Gaea" was 1.9 ppt. Cycle time for sampling and chemical analysis of each sample port was on the order of seconds. Possible effects on the sensors of environmental factors such as ambient humidity, temperature, and air velocity were not considered. Besides processing individual air sample data, the neural nets can sense concentration gradients and track to chemical source. The adaptive neural nets are accessed by a voice recognition system and are capable of point testing or free-ranging search. The service life of the detectors, the neural net processors, and auxiliary packaging is approximately 8 years under normal field use. Maintenance requires a good quality kibble and an occasional romp in the park.
Incorporation of independent formation information into inductive log interpretation will become more important as the resolution demands on induction logging increase. Often, such information can consist of a reasoned petrophysical characterization of the target and its inductive signature. This target characterization, together with other information, can be used to adaptively focus array tools as a function of borehole depth.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.