RAPID ANALYTE RECOGNITION IN A DEVICE BASED ON OPTICAL SENSORS AND THE OLFACTORY SYSTEM

We report here the development of a new vapor sensing device that is d esigned as an array of optically based chemosensors providing input to a pattern recognition system incorporating artificial neural networks , Distributed sensors providing inputs to an integrative circuit is a principle derived from studies of the vertebrate olfactory system. In the present device, primary chemosensing input is provided by an array of fiber-optic sensors. The individual fiber sensors, which are broad ly yet differentially responsive, were constructed by immobilizing mol ecules of the fluorescent indicator dye Nile Red in polymer matrices o f varying polarity, hydrophobicity, pore size, elasticity, and swellin g tendency, creating unique sensing regions that interact differently with vapor molecules, The fluorescent signals obtained from each fiber sensor in response to 2-s applications of different analyte vapors ha ve unique temporal characteristics. Using signals from the fiber array as inputs, artificial neural networks were trained to identify both s ingle analytes and binary mixtures, as well as relative concentrations . Networks trained with integrated response data from the array or wit h temporal data from a single fiber made numerous errors in analyte id entification across concentrations, However, when trained with tempora l information from the fiber array, networks using ''name'' or ''chara cteristic'' output codes performed well in identifying test analytes.