Quantitative artificial neural network for electronic noses Original Research Article

This paper reports a quantitative artificial neural network (ANN) to implement an electronic nose (enose). A new approach was proposed by the combination of ANN with fundamental aspects of analytical chemistry, especially with the concept of relative error (RE) in quantitative analysis. Thus, both the qualitative and quantitative requirements for ANN in implementing enose can be satisfied. Converging criterion while training the ANN can be set according to RE function (RE-Func) designed in this work. Fast converging speed and good prediction accuracy could be promised with the use of RE-Func. In addition, transform functions in logarithmic, sigmoid and their combined forms to pre-process training data sets were evaluated. Also training methods, such as order of training data magnitude and treatment of data passed the RE requirement checking in last iteration, were optimized. The enose was constructed to response quantitatively towards alcohol vapor within concentration range of 0.001–1 mg/l in the presence of petroleum gas and water vapor. The prediction error was <10%. No qualitative mistake of prediction was observed for samples of alcohol and petroleum vapors, or for their mixtures.