ParLeS: Software for chemometric analysis of spectroscopic data

This paper describes the development and implementation of ParLeS, chemometrics software for multivariate modelling and prediction. ParLeS is shareware that was developed for teaching and research in chemometrics and spectroscopy; however, it may also be used with other types of multivariate data. ParLeS may be used to transform, preprocess and pretreat spectra using various algorithms; it may be used to implement principal components analysis (PCA); partial least squares regression (PLSR) with leave-n-out cross validation; and bootstrap aggregation-PLSR (bagging-PLSR). ParLeS facilitates the implementation of a large number of preprocessing techniques as well as bagging-PLSR, which can improve the robustness and accuracy of PLSR models. Other unique features of ParLeS include the provision of a number of assessment statistics and graphical output as well as a user-friendly interface and functionality. The implementation of ParLeS is demonstrated by modelling soil mid infrared (mid-IR) diffuse reflectance spectra for predictions of soil organic carbon.