Fuzzy characterization and classification of solvents according to their polarity and selectivity. A comparison with the Snyder approach

Advanced chemometric methods, such as fuzzy c-means, a semi-supervised clustering method, and fuzzy discriminant analysis, a robust supervised method, have been successfully applied for characterization and classification of 72 solvents according to the chemical parameters (P' and xi) developed by Snyder. The obtained results (fuzzy partitions) and parameters of the prototypes (robust fuzzy means) clearly demonstrated the efficiency and information power of the advanced fuzzy methods in solvent characterization and classification, and allow a rationale choice of a good solvent or an efficient mixture of solvents in chromatography and other fields. Also, this methodology generates the premises for future investigations using other different properties of solvents.