Embedded pattern recognition systems for liquids classification: A comparison study

A comparative study among a Fuzzy ARTMAP, a Multi-Layer Feed-Forward network (MLFF) and a Linear Discriminant Analysis (LDA) has been done in a liquids classification system in order to obtain the best implementation on a microcontroller based system. These algorithms are initially trained with a multi-electrode array on a Personal Computer (PC) using several samples of waters to obtain the optimum architecture of the networks. Once it is trained, the computed data are programmed into the microcontroller, which then gives the water classification directly for new unknown water samples. The multi-electrode has been developed using thick-film technology.