Recognition of six microbial species with an electronic tongue

An electronic tongue based on pulsed voltammetry over an array of electrodes with different selectivity and sensitivity patterns was used to recognize six different microorganisms: one yeast, two bacteria, and three molds. Measurements were performed during the whole growth period, from the lag phase to the stationary phase. The electrode array was dipped into the malt extract growth medium and voltage was applied over the electrodes in pulses of different amplitude and the resulting current data was sampled and collected in a matrix. Evaluation of the electronic tongue data was made with principal component analysis (PCA) and soft independent modeling of class analogy (SIMCA). PCA was performed on data from the lag, the logarithmic, and also the stationary growth phase. In the lag growth phase no recognition of species was visible in the PCA score plots. After further growth however all the included microbial species could be recognized from each other. The ability to predict membership of new replicates of the species to the right classes was verified with SIMCA.