Neural network architectures for artificial noses

The paper presents a review of electronic noses with emphasis of the usage of live olfactory receptor neurons as detectors interfaced with electronics. The paper focuses on the pattern recognition issue using artificial neural networks. The proposed architecture seems to be very simple and powerful at the same time. The architecture was verified in recognition of noisy images with characters where pixels are represented by analog values in the range 0 to 1. In the case of odor recondition instead of analog values only discrete 0 or 1 values were given to neural network inputs and the system proved to be equally reliable.