Resolution of multicomponent peaks by orthogonal projection approach, positive matrix factorization and alternating least squares Original Research Article

The application of orthogonal projection approach (OPA), alternating least squares (ALS), and positive matrix factorization (PMF) to resolve HPLC-DAD data into individual concentration profiles and spectra is discussed. OPA was initially described as a purity method but the inclusion of an ALS procedure allows its application as a curve resolution method. PMF is a least square approach to factor analysis that in this study has been used as a tool to tackle the problem of curve resolution. OPA, ALS and PMF have been applied using a single matrix (two-way data) or an augmented matrix containing several data matrices simultaneously. The results obtained with the different resolution methods are compared and evaluated using measures of dissimilarity between the real and the estimated spectra. The study is performed in three data subsets, obtained by segmentation of the original data matrix. Within each data subset, there is a reduced number of species present which makes the resolution easier.