A machine learning approach for biomass characterization

• 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 a 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. 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 achieved 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. © 2019 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/) Peer-review under responsibility of the scientific committee of ICAE2018 - The 10th International Conference on Applied Energy.

Ämnesord

TEKNIK OCH TEKNOLOGIER  -- Maskinteknik -- Energiteknik (hsv//swe)

ENGINEERING AND TECHNOLOGY  -- Mechanical Engineering -- Energy Engineering (hsv//eng)

Nyckelord

Artificial Neural Network

Chemometrics

Gaussian Process Regression

Multiplicative Scatter Correction

Near Infrared Spectroscopy

Partial Least Squares

Savitzky-Golay derivatives

Standard Normal Variate

Support Vector Regression

Data handling

Gaussian distribution

Gaussian noise (electronic)

Genetic algorithms

Infrared devices

Iterative methods

Learning algorithms

Least squares approximations

Light scattering

Machine learning

Moisture

Moisture determination

Neural networks

Partial least square (PLS)

Savitzky-Golay

Standard normal variates

Support vector regression (SVR)

Regression analysis

Publikations- och innehållstyp

ref (ämneskategori)

kon (ämneskategori)