Wavelet transform of electronic tongue data

Coupling fast variable selection methods to neural network-based classifiers: Application to multisensor systems

“…The simplest methods are sequential forward selection (SFS), sequential backward selection (SBS) and stepwise selection [10].…”

“…Only those features with higher figure of merit were input to a fuzzy ARTMAP classifier. Using the same variance criterion, Artursson and Holmberg [10] showed that it was possible to effectively perform data compression from a pulsed-voltammetry-based electronic tongue. The e-tongue was aimed at monitoring water quality at different stages of the process undergone by water in a drinking water production plant.…”

A fuzzy technique for food- and water quality assessment with an electronic tongue

“…The most common method used for that purpose is principal component analysis (PCA). Recently, the use of the wavelet transform for feature extraction has also been considered for electronic tongue data in Artursson et al [1], and Robertsson and Wide [18]. The advantage of PCA is that the dimensionality of the data is dramatically reduced, typically to two or three dimensions.…”

Classification and authentication of unknown water samples using machine learning algorithms

“…In recent years, multi-sensor systems have been developed, called the electronic tongue (popularly known as E-Tongue) systems, which are capable of sensing the characteristics of the wet chemical by a special data acquisition method, called voltametric method [1,2]. D'Amico et al, defined electronic tongues as instruments that include arrays of non-specific solid state ion sensors, transducers even of different types, data collectors and data analysis tools, all oriented to the classification of liquid samples and the quantification of chemical species presented into them [3]. The time series signal and the corresponding raw data represent the measurement from the * Corresponding author.…”