A common problem when using real data is the fact that the values usually exhibit some degree of uncertainty. Measurement uncertainties therefore represent a major challenge when trying to interpret and draw conclusions from real data. This is especially true in on-site analysis in the environmental sector where the uncertainty in sample plays such a large role. An approach for the modelling and analysis of data for polluted water and the inclusion of measurement uncertainties is presented. This approach is based on fuzzy modelling, in which the uncertainty of the parameters is represented by so-called fuzzy numbers and thus reflect a possible blurred range of these parameter values. The result is a fuzzy pattern classifier, which allows a fuzzy and thus realistic characterization of unknown water samples. The procedure is exemplified using the extinction spectra taken using a UV/Vis spectrometer.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.