ARTIFICIAL NEURAL-NETWORK AND CLASSICAL LEAST-SQUARES METHODS FOR NEUROTRANSMITTER MIXTURE ANALYSIS

Identification of individual components in biological mixtures can be a difficult problem regardless of the analytical method employed. In t his work, Raman spectroscopy was chosen as a prototype analytical meth od due to its inherent versatility and applicability to aqueous media, making it useful for the study of biological samples. Artificial neur al networks (ANNs) and the classical least-squares (CLS) method were u sed to identify and quantify the Raman spectra of the small-molecule n eurotransmitters and mixtures of such molecules. The transfer function s used by a network, as well as the architecture of a network, played an important role in the ability of the network to identify the Raman spectra of individual neurotransmitters and the Raman spectra of neuro transmitter mixtures. Specifically, networks using sigmoid and hyperbo lic tangent transfer functions generalized better from the mixtures in the training data set to those in the testing data sets than networks using sine functions. Networks with connections that permit the local processing of inputs generally performed better than other networks o n all the testing data sets, and better than the CLS method of curve f itting, on novel spectra of some neurotransmitters. The CLS method was found to perform well on noisy, shifted, and difference spectra.