Walter L. Zielinski

Application of a pruning algorithm to optimize artificial neural networks for pharmaceutical fingerprinting.

The present study investigates an application of artificial neural networks (ANNs) for use in pharmaceutical fingerprinting. Several pruning algorithms were applied to decrease the dimension of the input parameter data set. A localized fingerprint region was identified within the original input parameter space from which a subset of input parameters was extracted leading to enhanced ANN performance. The present results confirm that ANNs can provide a fast, accurate, and consistent methodology applicable to pharmaceutical fingerprinting.

Separation and Purification Section :: summary of activities July 1967 to June 1968

The research activities of the Separation and Purification Section are described, including their significance to the program of the Office of Standard Reference Materials. The work involves basic developments to characterize ion exchange resins using infrared spectrophotometry, stoichiometric analysis of resin structure, and the study of chain scission. The availability of spherical particles of homogeneous ion exchange resin has been exploited with the recently developed microstandards. Analytical gas chromatography has been developed with emphasis given to the specialized needs of measuring trace contaminants in purified organic compounds including divinylbenzene, EDTA, and clinical standards such as uric acid and urea. Purification capabilities involving the use of crystallization, analytical distillation, and of the newly installed low temperature (-30°C) laboratory are described. The activities of the ultra-pure reagents project, including work on the laser light scattering measurement of traces of liquid borne particulate matter, on reagent preparation, and methods of reagent storage are described.