Advances in Distributed Computing and Artificial Intelligence Jornual Special Issue #2

Odor feature vector, Neural networks Separation of mixed gasses Odor classification Compared with metal oxide semiconductor gas sensors, quarts crystal micro-balance (QCM) sensors are sensitive for odors. Using an array of QCM sensors, we measure mixed odors and classify them into an original odor class before mixing based on neural networks. For simplicity we consider the case that two kinds of odor are mixed since more than two becomes too complex to analyze the classification results. We have used eight sensors and four kinds of odor are used as the original odors. The neural network used here is a conventional lay-ered neural network. The classification is acceptable although the perfect classi-fication could not been achieved