Supervised discretization for decluttering classification models.

Presented here is the first demonstration of supervised discretization to 'declutter' multivariate classification data in chemical sensor applications. The performance of multivariate classification models is often limited by the non-informative chemical variance within each target class; decluttering methods seek to reduce within-class variance while retaining between-class variance. Supervised discretization is shown to declutter classes in a manner that is superior to the state-of-the-art External Parameter Orthogonalization (EPO) by constructing a more parsimonious model with fewer parameters to optimize and is, consequently, less susceptible to overfitting and information loss. The comparison of supervised discretization and EPO is performed on three classification applications: X-ray fluorescence spectra of pine ash where the pine was grown in three distinct soil types, laser induced breakdown spectroscopy of colored artisanal glasses, and laser induced breakdown spectroscopy of exotic hardwood species.

Assessing utility of handheld laser induced breakdown spectroscopy as a means of Dalbergia speciation.

Many species of Dalbergia are prized hardwoods, generally referred to as 'Rosewood,' and used in high-end products due to their distinctive hue and scent. Despite more than 58 species of Dalbergia being listed as endangered in Appendix 1 of The Convention on International Trade in Endangered Species of Fauna and Flora (CITES), the illegal logging and trade of this timber is ongoing. In this work, a handheld laser induced breakdown spectrometer (LIBS) was used to analyze seven Dalbergia species and two other exotic hardwood species to evaluate the ability of handheld LIBS for rapid classification of Dalbergia in the field. The KNN model of the classification presented 80% to 90% sensitivity for discriminating between Dalbergia species in the training set. PLS-DA models were based on a binary decision tree structure. Cumulatively, the PLS-DA decision tree model showed greater than 97% sensitivity and 99% selectivity for prediction of Dalbergia species included in the training set. The data presented in the following study are promising for the use of handheld LIBS devices and both KNN and PLS-DA models for applications in customs screenings at the port of entry of hard woods, among others.