Rapid determination of starch and alcohol contents in fermented grains by hyperspectral imaging combined with data fusion techniques

• Published in: Journal of food science 2024-06, Vol.89 (6), p.3540-3553
• Main Authors: Liang, Yan, Tian, Jianping, Hu, Xinjun, Huang, Yuexiang, He, Kangling, Xie, Liangliang, Yang, Haili, Huang, Dan, Zhou, Yifei, Xia, Yuanyuan
• Format: Article
• Language: English
• Subjects: Adaptive sampling; Alcohol; Alcohols; Alcohols - analysis; Algorithms; data fusion; Data integration; Edible Grain - chemistry; Fermentation; Fermented Foods - analysis; fermented grains; Hyperspectral imaging; Hyperspectral Imaging - methods; integrated learning; Least squares method; Least-Squares Analysis; Near infrared radiation; Preprocessing; Principal Component Analysis; Principal components analysis; Regression analysis; Regression models; Spectroscopy, Near-Infrared - methods; Starch; Starch - analysis; starch and alcohol; Support Vector Machine; Support vector machines; Wavelengths
• ISSN: 0022-1147; 1750-3841; 1750-3841
• DOI: 10.1111/1750-3841.17102

Starch and alcohol serve as pivotal indicators in assessing the quality of lees fermentation. In this paper, two hyperspectral imaging (HSI) techniques (visible–near‐infrared (Vis–NIR) and NIR) were utilized to acquire separate HSI data, which were then fused and analyzed toforecast the starch and alcohol contents during the fermentation of lees. Five preprocessing methods were first used to preprocess the Vis–NIR, NIR, and the fused Vis–NIR and NIR data, after which partial least squares regression models were established to determine the best preprocessing method. Following, competitive adaptive reweighted sampling, successive projection algorithm, and principal component analysis algorithms were used to extract the characteristic wavelengths to accurately predict the starch and alcohol levels. Finally, support vector machine (SVM)‐AdaBoost and XGBoost models were built based on the low‐level fusion (LLF) and intermediate‐level fusion (ILF) of single Vis–NIR and NIR as well as the fused data. The results showed that the SVM‐AdaBoost model built using the LLF data afterpreprocessing by standard normalized variable was most accurate for predicting the starch content, with an RP2$\ R_P^2$ of 0.9976 and a root mean square error of prediction (RMSEP) of 0.0992. The XGBoost model built using ILF data was most accurate for predicting the alcohol content, with an RP2$R_P^2$ of 0.9969 and an RMSEP of 0.0605. In conclusion, the analysis of fused data from distinct HSI technologies facilitates rapid and precise determination of the starch and alcohol contents in fermented grains.