Application of random forest regression to spectral multivariate calibration

The performance of the random forest (RF) algorithm on the spectroscopic data was studied and compared by bootstrap aggregating of classification and regression trees (bagging CART), partial least squares (PLS) and nonlinear support vector machine (SVM) algorithms. The performances of these algorithms were investigated on four real data sets; these data sets were: (1) UV-Visible spectra of two cardiovascular drugs (hydrochlorothiazide and valsartan); (2) visible spectra of copper, cobalt and nickel complexes with 4-(2-pyridylazo) resorcinol (PAR) as chromogenic reagent; (3) near infrared spectra of corn samples, and (4) near infrared diffuse transmission spectra of pharmaceutical tablets. Results indicate that besides its comparable accuracy and mathematical simplicity, it is computationally fast and robust to noise. Therefore, RF is a useful tool for regression studies and has potential for modeling linear and nonlinear multivariate calibration.