HEURISTIC EVOLVING LATENT PROJECTIONS - RESOLVING HYPHENATED CHROMATOGRAPHIC PROFILES BY COMPONENT STRIPPING

A 'component stripping' technique is presented for unique resolution of multicomponent systems (with more than three overlapping components) by means of the heuristic evolving latent projections method. Partial chromatographic selectivity is utilized to resolve clusters of overlapping chromatographic peaks. Analytes with partial chromatographic selectivity are detected and their contributions in terms of estimated concentration profiles and spectra subsequently subtracted to obtain a data matrix of reduced rank. The procedure is repeated on the rank-reduced data until the variation corresponding to chemical components has been exhausted and the data matrix has zero 'chemical' rank in all regions. At this stage, the concentration profiles and spectra of all the pure chemical components should be obtained. The simplicity and efficiency of the proposed approach are proved on a simulated four-component mixture characterized by an unresolved profile of hyphenated chromatographic data. The new method compares favourably with the so-called rank annihilation evolving factor analysis both with respect to preconditions and results.