Kernel Partial Least Squares for the Identification of Mixture Content from TeraHertz Spectra

This paper introduces kernel partial least squares (K-PLS) for the identification of mixture content from terahertz spectra. Kernel partial least squares is a nonlinear extension of the partial least squares (PLS) method, commonly used in chemometrics. K-PLS and PLS are considered superior to peak matching methods for mixture spectra of multiple compounds because it avoids having to address the problem of overlapping peaks explicitly. Terahertz (THz) radiation is capable of transmitting easily through most dielectric materials and is used as a new tool to collect the original spectral readings from transmission, diffusion and reflection. A multi-output kernel partial least squares method is presented to model mixture composition based on pure substance training patterns, under the assumption of linear spectral mixture behavior. Preprocessing consists of a wavelet transform of the THz spectra and an independent component analysis (ICA) transform. Preliminary results show that the ICA+K-PLS approach is able to classify pure spectra accurately and allows for an accurate estimate of the composition from THz mixed spectra even where there are severe overlapped peaks in these spectra.