Partial least squares discriminant analysis: A dimensionality reduction method to classify hyperspectral data

Abstract

The recent development of more sophisticated spectroscopic methods allows acqui- sition of high dimensional datasets from which valuable information may be extracted using multivariate statistical analyses, such as dimensionality reduction and automatic classification (supervised and unsupervised). In this work, a supervised classification through a partial least squares discriminant analysis (PLS-DA) is performed on the hy- perspectral data. The obtained results are compared with those obtained by the most commonly used classification approaches.