Building parsimonious fuzzy ARTMAP models by variable selection with a cascaded genetic algorithm: application to multisensor systems for gas analysis

摘要: Considerable attention has been given to strategies for variable selection in gas analysis using multisensor systems. Of the stochastic methods, genetic algorithms (GAs) have found be useful selection, although they do not prevent irrelevant variables from being selected. Here we introduce cascaded algorithm, a new and simple approach that removes initially selected variables. We coupled method fuzzy ARTMAP classifier used it analyze single vapors binary mixtures of three volatile organic compounds 12-element metal oxide sensor array. The allowed reduce number build classifiers 120 down nine, which significantly increased generalization ability classifier. Success rates 91.67 88.33% were reached simultaneous identification, quantification vapors, identification their mixtures, respectively.