A Systematic Review of Multi-Class and One-vs-Rest Classification Techniques for Near-Infrared Spectra of Crop Cultivars

Near-infrared (NIR) spectroscopy is a simple and non-destructive technique that provides a wealth of information on the chemical composition and physical properties of a sample. NIR spectra are produced as a function of the energy transition between electromagnetic radiation in the near-infrared region (700 - 2500 nm) and matter. The spectra are complex and typically contain broad overlapping absorption bands that are difficult to interpret. Chemometrics is the field of study that encompasses various multivariate data analysis methods for qualitative and quantitative analysis of chemical data via methods such as spectroscopy. Due to the volatile nature of spectroscopic data, there is no one-size-fits-all approach to modelling such tasks. In this work, we perform a systematic review of various modelling approaches for the task of crop cultivar identification of Barley, Chickpea, and Sorghum grains. Our analysis includes two established discriminant analysis methods commonly applied in chemometrics, and three Machine Learning algorithms. Fur-thermore, we compare multiclass classification, as the task was originally represented, with a one-vs-rest classification approach. We demonstrate that one-vs-rest classification is a strong al-ternative modelling approach with the ability to improve the classification score and highlight the weaker target classes that affect performance in multiclass classification problems.