Abstract—Electronic Tongue is a kind of intelligent equipment which is used to distinguish tastes. An electronic tongue made by a sensor array of ion-selective electrodes (ISE) has been developed and used for the qualitative analysis of five different kinds of mineral water. The acquired original data has been optimized by the principle component analysis (PCA) and independent component analysis (ICA). Then a wavelet neural network (WNN) model was designed based on the local optimalizing searching characteristic of BP neural network and an appropriate set of the parameters. The application results show that the performance of the proposed method surpasses the traditional BP algorithm. It can improve convergence and the learning capability of the network, and gives the Electronic Tongue a higher aggregate classification rate. Index Terms—electronic tongue, mineral water, principal component analysis, independent component analysis, wavelet neural network I.
No takes yet. Share an insight, caveat, or question.
Men et al. (2011) studied this question.