Discrimination of Oil Contaminants using Supervised Kohonen Network and Unconventional Steady State Fluorescence Spectroscopy: A Comparative Evaluation

The rapid and reliable detection of oil contaminants is crucial importance for environmental protection. This paper focused on the classification identification six types using unconventional steady-state fluorescence spectroscopy coupled with XY-fused networks (XY-Fs). excitation emission matrix (EEMF) spectroscopy, synchronous (SFS) total (TSFS) samples were measured by a FS920 spectrometer. Further, obtained results compared those partial least square discriminant analysis (PLS-DA), LDA based score multivariate curve resolution-alternating squares (MCR-ALS-LDA) parallel factor (PARAFAC-LDA) analysis. experimental showed that best accuracy (100%) test was TSFS combined XY-Fs. These provide important references discrimination contaminants.