Lfda Model For The Assessment Of Water Quality Through Microtox (R) Using Excitation-Emission Matrices

Fluorescence spectroscopic excitation-emission matrices (EEMs) can be used to characterize dissolved organic matter in water with high sensitivity. Our goal is to predict the standard biosensor-based measurement Microtox (R) utilizing EEMs, pH, turbidity and conductivity, among other variables. EEMs have been modeled using novel latent fluorescent Dirichlet allocation (LFDA) based probabilistic graphical model. We found that nonparametric techniques offer a better mapping from, LFDA based EEMs scores and other measurements, to Microtox (R) measurements. The final decision on Microtox (R) measurement is given using an evidence fusion mechanism. In general, the novel LFDA based graphical model can be utilized in analyzing two dimensional data.