Authors: Mobyen Uddin Ahmed, Peter Andersson, Tim Andersson, Elena Tomas Aparicio, Hampus Baaz, Shaibal Barua, Albert Bergström, Daniel Bengtsson, Jan Skvaril, Jesús Zambrano (MDH University)
Conference: International Conference of Applied Energy (ICAE, 2018), Hong Kong, China, Agosto 22-25
Abstract: The aim of this work is to apply and evaluate different chemometric approaches employing several machine learning techniques in order to characterize the moisture content in biomass from data obtained by Near Infrared (NIR) spectroscopy. The approaches include three main parts: a) data pre-processing, b) wavelength selection and c) development of an actual regression model enabling moisture content measurement. Standard Normal Variate (SNV), Multiplicative Scatter Correction and Savitzky-Golay first (SG1) and second (SG2) derivatives and its combinations were applied for data pre-processing. Genetic algorithm (GA) and iterative PLS (iPLS) were used for wavelength selection. Moreover, Artificial Neural Network (ANN), Gaussian Process Regression (GPR), Support Vector Regression (SVR) and traditional Partial Least Squares (PLS) regression, were employed as machine learning regression methods. Results shows that SNV combined with SG1 first derivative performs the best in data pre-processing. The GA is the most effective methods for variable selection and GPR is achieving a high accuracy in regression modeling while having low demands on computation time. Overall, the machine learning techniques demonstrate a great potential to be used in future NIR spectroscopy applications.
Key words: Artificial neural network, Chemometrics, Gaussian Process Regression, Multiplicative Scatter Correction, Standard Normal Variate, Support Vector Regression, Partial Least Squares, Savitzky-Golay Derivatives