TRACE-LEVEL IDENTITY CONFIRMATION FROM INFRARED-SPECTRA BY LIBRARY SEARCHING AND ARTIFICIAL NEURAL NETWORKS

Confirmation of the identity of analytes at trace-level concentrations from infrared spectra is described. Both library search and artificia l neural networks (ANNs) are used for this purpose. The effect of pre- processing, library composition and search algorithm on the results ar e investigated. Best separation of positives and negatives is obtained with ANN. Library search methods, however, are superior when preventi on of false positives is essential. The correlation coefficient is sca le-invariant and gives excellent results.