Improved Calibration of Near-Infrared Spectra by Using Ensembles of Neural Network Models
This work addresses calibration challenges in spectroscopy for analytical chemistry applications, representing an incremental improvement over existing neural network methods.
The paper tackles the problem of nonlinear calibration in near-infrared spectroscopy by proposing an ensemble of neural network models, resulting in significantly more accurate and robust calibration compared to conventional regression methods.
IR or near-infrared (NIR) spectroscopy is a method used to identify a compound or to analyze the composition of a material. Calibration of NIR spectra refers to the use of the spectra as multivariate descriptors to predict concentrations of the constituents. To build a calibration model, state-of-the-art software predominantly uses linear regression techniques. For nonlinear calibration problems, neural network-based models have proved to be an interesting alternative. In this paper, we propose a novel extension of the conventional neural network-based approach, the use of an ensemble of neural network models. The individual neural networks are obtained by resampling the available training data with bootstrapping or cross-validation techniques. The results obtained for a realistic calibration example show that the ensemble-based approach produces a significantly more accurate and robust calibration model than conventional regression methods.