Vapour recognition using organic films and artificial neural networks

Abstract Organic thin-film sensors bases on the thermal evaporation and dip-coating of polyaniline, and on the Langmuir-Blodgett deposition of a vanadium porphyrin, have been fabricated. The d.c. electrical resistance of the individual elements are found to exhibit different changes on exposure to simple vapours (water, proano, ethyl acetate and acetone). These data have been used successfully to train an artificial neural network, based on a back-propagation technique, to recognized two of the vapours.