PLACE:  1160 Sweeney

SPEAKER:
Professor Carey Priebe
Department of Mathematcial Science, The Johns Hopkins University

TITLE:
Statistical Pattern Recognition for an Artificial Nose

ABSTRACT:

This talk presents results from an ongoing investigation into a fiber-optic ``artificial nose'' system constructed at Tufts University.

The sensor fabrication and preparation results in a sensor for which a change in fluorescence intensity is in response to a change in the molecular environment of a solvatochromic dye due to interactions of a polymer matrix with an analyte present.

Detection of the presence of a single prespecified chemical analyte at low concentration in complex backgrounds is a difficult application for chemical sensors.

We consider in particular a database of artificial nose observations designed specifically to allow for the investigation of chemical sensor data analysis performance on the problem of detecting the environmental contaminant trichloroethylene (TCE).

Nonparametric statistical pattern recognition methodologies based on interpoint distances are considered, and experimental results are presented indicating that our nonparametric methodology is a useful tool in olfactory classification.
 
 

COFFEE: 3:45 p.m. Room 104 Snedecor Hall