Prediction of Wheat Quality Parameters Combining Raman, Fluorescence and Near‐Infrared Spectroscopy (NIRS)

Estimating baselines of Raman spectra based on transformer and manually annotated data

Raman spectroscopy is a powerful and non-invasive analytical method for determining the chemical composition and molecular structure of a wide range of materials, including complex biological tissues. However, the captured signals typically suffer from interferences manifested as noise and baseline, which need to be removed for successful data analysis. Effective baseline correction is critical in quantitative analysis, as it may impact peak signature derivation. Current baseline correction methods can be labor-intensive and may require extensive parameter adjustment depending on the input spectrum characteristics. In contrast, deep learning-based baseline correction models trained across various materials, offer a promising and more versatile alternative. This study reports an approach to manually identify the ground-truth baselines for eight different biological materials through extensively tuning the parameters of three classical baseline correction methods, Modified Multi-Polynomial Fit (Modpoly), Improved Modified Multi-Polynomial Fitting (IModpoly), and Adaptive Iteratively Reweighted Penalized Least Squares (airPLS), and combining the outputs to best fit the training data. We designed a one-dimensional Transformer (1dTrans) tailored to fit Raman spectral data for estimating their baselines, and evaluated its performance against convolutional neural network (CNN), ResUNet, and three aforementioned parametric methods. The 1dTrans model achieved lower mean absolute error (MAE) and spectral angle mapper (SAM) scores when compared to the other methods in both development and evaluation of the manually labeled original raw Raman spectra, highlighting the effectiveness of the method in Raman spectra pre-processing.

Recent Advances in the Assessment of Cereal and Cereal-Based Product Quality

Cereals are rich in nutrients, such as carbohydrates, fats, proteins, vitamins, and minerals, which make them a very important source of food for the human diet and human health [...].

"Raman plus X" dual-modal spectroscopy technology for food analysis: A review

Raman spectroscopy, a nondestructive optical technique that provides detailed chemical information, has attracted growing interest in the food industry. Complementary spectroscopic methods, such as near-infrared (NIR) spectroscopy, nuclear magnetic resonance (NMR), terahertz (THz) spectroscopy, laser-induced breakdown spectroscopy (LIBS), and fluorescence spectroscopy (Flu), enhance Raman spectroscopy's capabilities in various applications. The integration of Raman with these techniques, termed "Raman plus X," has shown significant potential in agri-food analysis. This review highlights the latest advances and applications of dual-modal spectroscopy methods combining Raman spectroscopy with NIR, NMR, THz, LIBS, and Flu in food analysis. Key applications include detecting harmful contaminants, evaluating food quality, identifying adulteration, and characterizing structure. The synergistic use of Raman-based dual-modal spectroscopy provides more comprehensive information and improves modeling accuracy compared to single techniques. The review also explores the role of data fusion in multisource spectral analysis and discusses challenges and prospects of "Raman plus X," including the development of integrated hardware and advanced data fusion algorithms. These advancements aim to streamline multisource data analysis, offering valuable insights to select appropriate analytical methods for practical applications in the food industry.

Predicting the properties of wheat flour from grains during debranning: A machine learning approach

In the food industry, meeting food quality demands is challenging. The quality of wheat flour, one of the most commonly used ingredients, depends on the extent of debranning done to remove the aleurone layer before milling. Therefore, the end product management can be simplified by predicting the properties of wheat flour during the debranning stage. Therefore, the chemical and rheological properties of grains were analyzed at different debranning durations (0, 30, 60 s). Then the images of wheat grain were taken to develop a regression model for predicting the chemical quality (i.e., ash, starch, fat, and protein contents) of the wheat flour. The resulting regression model comprises a convolutional neural network and is evaluated using the coefficient of determination (R 2), root-mean-square error, and mean absolute error as metrics. The results demonstrated that wheat flour contained more fat and protein and less ash with increasing debranning time. The model proved reliable in terms of root-mean-square error, mean absolute error, and R 2 for predicting ash content but not starch, fat, or protein contents, which can be attributed to the lack of features in the collected images of wheat kernels during debranning. In addition, the selected method, debranning, was beneficial to the rheological characteristics of wheat flour. The proportion of fine particles increased with the debranning time. The study experimentally revealed that the end product diversity for wheat flour can be controlled to provide selectable ingredients to customers.

Feature engineering and parameter tuning: improving phenomic prediction ability in multi-environmental durum wheat breeding trials

KEY MESSAGE

Optimized phenomic selection in durum wheat uses near-infrared spectra, feature engineering and parameter tuning. Our study reports improvements in predictive ability and emphasizes customized preprocessing for different traits and models. The success of plant breeding programs depends on efficient selection decisions. Phenomic selection has been proposed as a tool to predict phenotype performance based on near-infrared spectra (NIRS) to support selection decisions. In this study, we test the performance of phenomic selection in multi-environmental trials from our durum wheat breeding program for three breeding scenarios and use feature engineering as well as parameter tuning to improve the phenomic prediction ability. In addition, we investigate the influence of genotype and environment on the phenomic prediction ability for agronomic and quality traits. Preprocessing, based on a grid search over the Savitzky-Golay filter parameters based on 756,000 genotype best linear unbiased estimate (BLUE) computations, improved the phenomic prediction ability by up to 1500% (0.02-0.3). Furthermore, we show that preprocessing should be optimized depending on the dataset, trait, and model used for prediction. The phenomic prediction scenarios in our durum breeding program resulted in low-to-moderate prediction abilities with the highest and most stable prediction results when predicting new genotypes in the same environment as used for model training. This is consistent with the finding that NIRS capture both the genotype and genotype-by-environment ( G × E ) interaction variance.

Challenges to Increasing Dietary Fiber in White Flour and Bread

Increasing the intake of dietary fiber from staple foods is a key strategy to improve the health of consumers. White bread is an attractive vehicle to deliver increased fiber as it is widely consumed and available to all socio-economic groups. However, fiber only accounts for about 4% of the dry weight of white flour and bread compared to 10-15% in whole grain bread and flour. We therefore discuss the challenges and barriers to developing and exploiting new types of wheat with high fiber content in white flour. These include defining and quantifying individual fiber components and understanding how they are affected by genetic and environmental factors. Rapid high throughput assays suitable for determining fiber content during plant breeding and in grain-utilizing industries are urgently required, while the impact of fiber amount and composition on flour processing quality needs to be understood. Overcoming these challenges should have significant effects on human health.

Fluorescence in depth: integration of spectroscopy and imaging with Raman, IR, and CD for advanced research

Fluorescence spectroscopy serves as a vital technique for studying the interaction between light and fluorescent molecules. It encompasses a range of methods, each presenting unique advantages and applications. This technique finds utility in various chemical studies. This review discusses Fluorescence spectroscopy, its branches such as Time-Resolved Fluorescence Spectroscopy (TRFS) and Fluorescence Lifetime Imaging Microscopy (FLIM), and their integration with other spectroscopic methods, including Raman, Infrared (IR), and Circular Dichroism (CD) spectroscopies. By delving into these methods, we aim to provide a comprehensive understanding of the capabilities and significance of fluorescence spectroscopy in scientific research, highlighting its diverse applications and the enhanced understanding it brings when combined with other spectroscopic methods. This review looks at each technique's unique features and applications. It discusses the prospects of their combined use in advancing scientific understanding and applications across various domains.

Multimodal fiber probe for simultaneous mid-infrared and Raman spectroscopy

A fiber probe has been developed that enables simultaneous acquisition of mid-infrared (MIR) and Raman spectra in the region of 3100-2600 cm-1. Multimodal measurement is based on a proposed ZrO2 crystal design at the tip of an attenuated total reflection (ATR) probe. Mid-infrared ATR spectra are obtained through a pair of chalcogenide infrared (CIR) fibers mounted at the base of the crystal. The probe enables both excitation and acquisition of a weak Raman signal from a portion of the sample in front of the crystal using an additional pair of silica fibers located in a plane perpendicular to the CIR fibers. The advantages of combining MIR and Raman spectra in a single probe have been discussed.

A data fusion approach for nondestructive tracking of the ripening process and quality attributes of green Hayward kiwifruit using artificial olfaction and proximal hyperspectral imaging techniques

A data fusion strategy based on hyperspectral imaging (HSI) and electronic nose (e-nose) systems was developed in this study to inspect the postharvest ripening process of Hayward kiwifruit. The extracted features from the e-nose and HSI techniques, in single or combined mode, were used to develop machine learning algorithms. Performance evaluations proved that the fusion of olfactory and reflectance data improves the performance of discriminative and predictive algorithms. Accordingly, with high classification accuracies of 100% and 94.44% in the calibration and test stages, the data fusion-based support vector machine (SVM) outperformed the partial least square discriminant analysis (PLSDA) for discriminating the kiwifruit samples into eight classes based on storage time. Moreover, the data fusion-based support vector regression (SVR) was a better predictor than partial least squares regression (PLSR) for kiwifruit firmness, soluble solids content (SSC), and titratable acidity (TA) measures. The prediction R 2 and RMSE criteria of the SVR algorithm on the test data were 0.962 and 0.408 for firmness, 0.964 and 0.337 for SSC, and 0.955 and 0.039 for TA, respectively. It was concluded that the hybrid of e-nose and HSI systems coupled with the SVM algorithm delivers an effective tool for accurate and nondestructive monitoring of kiwifruit quality during storage.