Discrimination of chemically similar organic vapours and vapour mixtures using the Kohonen network

A Kohonen network was employed to discriminate between a series of chemically similar alcohols and mixtures of organic solvents. The input data for the Kohonen analysis was generated using an optimized eight-sensor array designed to sample the headspace of the solvents. Different sizes of output grid were investigated to devise a network that gave optimum discrimination and maintained relationships within the data set. When the output grid was large compared to the number of classes in the sample set, discrimination was shown to be enhanced compared to a small output grid. An advantage of the small output grid is that it was shown to maintain information within the original data set. The Kohonen network generated easily distinguishable output patterns, which could be used as an alternative to pattern recognition or in conjunction with output grid maps.