Raman spectra have fingerprint regions that are highly distinctive and can in principle be used for identification of
explosive residues. However, under most field situations strong illumination by sunlight, impurities in the explosives, or
the presence of a substrate or matrix, cause the Raman spectra to have a strong fluorescence background. Using spectra
of pure explosives, spectra of highly-fluorescent clutter materials including asphalt, cement, sand, soil, and paint chips,
and some spectra of pre-mixed explosive and clutter, we synthesized a library of admixed spectra varying from 5%
explosives and 95% clutter spectra up to 100% explosives and 0% clutter spectra. This represented a signal to noise ratio
for the explosive peaks varying from 0.04 to 5933. Using this library to train a support vector machine, known as a
kernel adatron, we obtained very good identification of the explosive vs. non-explosive. We performed a 40-fold crossvalidation
with leave-100-out for evaluation. Our results show 99.8% correct classification with 0.2% false positives.
Genetic algorithms are a computational paradigm modeled after biological genetics. They allow one to efficiently search a very large optimization-space for good solutions. In this paper we report on two methods of maintaining genetic diversity in a population of organisms being acted on by a genetic algorithm. In both cases the organisms are on a square grid and only interact with their nearest neighbors. The number of interactions is based on the fitness. One method results in ecological niches in sizes from a few organisms to several dozen. In the second method almost every organism in the population remains in a unique ecological niche searching the fitness landscape. The two methods can be used in finding multiple solutions. These methods have been applied to a semiconductor manufacturing process in developing robust plasma etch recipes that reduce the variance about a target mean and allow the dc bias to drift within 15% of a nominal value. The tapered via etch process in our production environment results in an oxide film with a mean value of about 7093 angstroms and a standard deviation of 730 angstroms. In simulations using real production data and a neural network model of the process our new recipes have reduced the standard deviation below 200 angstroms. These results indicate that significant improvement in the proces can be realized by applying these techniques.
The proximity effect, caused by electron beam backscattering during resist exposure, is an important
concern in writing submicron features. It can be compensated by appropriate local changes in the incident
beam dose, but computation of the optimal correction usually requires a prohibitively long time. We present an
example of such a computation on a small test pattern, which we performed by an iterative method. We then
used this solution as a training set for an adaptive neural network. After training, the network computed the
same correction as the iterative method, but in a much shorter time. Correcting the image with a software based
neural network resulted in a decrease in the computation time by a factor of 30, and a hardware based network
enhanced the computation speed by more than a factor of 1000. Both methods had an acceptably small error of
0.5% compared to the results of the iterative computation. Additionally, we verified that the neural network
correctly generalized the solution of the problem to include patterns not contained in its training set.
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.