Browsing by Subject "NIR spectroscopy"

Now showing 1 - 2 of 2

Improved prediction of wheat quality and functionality using near-infrared spectroscopy and novel approaches involving flour fractionation and data fusion
(2025) Ziegler, Denise; Buck, Lukas; Scherf, Katharina Anne; Popper, Lutz; Schaum, Alexander; Hitzmann, Bernd; Ziegler, Denise; Department of Process Analytics, Institute of Food Science and Biotechnology, University of Hohenheim, Stuttgart, Germany; Buck, Lukas; Department of Bioactive and Functional Food Chemistry, Institute of Applied Biosciences, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany; Scherf, Katharina Anne; Department of Bioactive and Functional Food Chemistry, Institute of Applied Biosciences, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany; Popper, Lutz; Mühlenchemie GmbH & Co. KG, Ahrensburg, Germany; Schaum, Alexander; Department of Process Analytics, Institute of Food Science and Biotechnology, University of Hohenheim, Stuttgart, Germany; Hitzmann, Bernd; Department of Process Analytics, Institute of Food Science and Biotechnology, University of Hohenheim, Stuttgart, Germany
The accurate and rapid determination of wheat quality is of great importance for the wheat supply chain. Near-infrared (NIR) spectroscopy has become an established method for this purpose. So far, however, predictions for most wheat quality characteristics are not accurate enough to replace reference measurements, with the exception of protein content. This study investigates the potential to improve the prediction of 41 wheat quality parameters (protein- and starch-related parameters, solvent retention capacity, farinograph, extensograph, alveograph) based on a flour fractionation approach (sieve fractionation, dough preparation, gluten washing) and data fusion using the established techniques of NIR spectroscopy and chemometrics. Results show that preprocessing of flour significantly altered the composition of the samples, which reflected in spectral differences of their NIR spectra. This also led to a change in the prediction accuracy for many wheat quality parameters. Compared to the prediction using flour spectra, flour fractionation with or without data fusion improved the RMSECV between 5.6 and 28.6% for 35 out of the 41 quality parameters tested, leading to R2CV between 0.80 and 0.96 for many of them. Gluten, dough, and the 50–75 µm and the 75–100 µm fractions were particularly important for the improved predictions. The best predictions were often based on data fusion of spectra from different sample types, demonstrating the importance of using complementary information from different data sources to improve predictions. The results underline the potential of this novel approach to be established in the industry as an extension of conventional NIR spectroscopy to improve wheat quality prediction.
Novel method for the detection of adulterants in coffee and the determination of a coffee's geographical origin using near infrared spectroscopy complemented by an autoencoder
(2023) Munyendo, Leah; Njoroge, Daniel; Zhang, Yanyan; Hitzmann, Bernd
Coffee authenticity is a foundational aspect of quality when considering coffee's market value. This has become important given frequent adulteration and mislabelling for economic gains. Therefore, this research aimed to investigate the ability of a deep autoencoder neural network to detect adulterants in roasted coffee and to determine a coffee's geographical origin (roasted) using near infrared (NIR) spectroscopy. Arabica coffee was adulterated with robusta coffee or chicory at adulteration levels ranging from 2.5% to 30% in increments of 2.5% at light, medium and dark roast levels. First, the autoencoder was trained using pure arabica coffee before being used to detect the presence of adulterants in the samples. Furthermore, it was used to determine the geographical origin of coffee. All samples adulterated with chicory were detectable by the autoencoder at all roast levels. In the case of robusta‐adulterated samples, detection was possible at adulteration levels above 7.5% at medium and dark roasts. Additionally, it was possible to differentiate coffee samples from different geographical origins. PCA analysis of adulterated samples showed grouping based on the type and concentration of the adulterant. In conclusion, using an autoencoder neural network in conjunction with NIR spectroscopy could be a reliable technique to ensure coffee authenticity.