Rancidity and moisture estimation in shelled almond kernels using NIR hyperspectral imaging and chemometric analysis

Lightweight deep learning algorithm for real-time wheat flour quality detection via NIR spectroscopy

Wheat flour quality, determined by factors such as protein and moisture content, is crucial in food production. Traditional methods for analyzing these parameters, though precise, are time-consuming and impractical for large-scale operations. This study presents a lightweight convolutional neural network designed for real-time wheat flour quality monitoring using near-infrared spectroscopy. The model incorporates Ghost bottlenecks, external attention modules, and the Kolmogorov-Arnold network to enhance feature extraction and improve prediction accuracy. Testing results demonstrate high predictive performance with R2 values of 0.9653 (RMSE: 0.2886 g/100 g, RPD: 5.8981) for protein and 0.9683 (RMSE: 0.3061 g/100 g, RPD: 5.1046) for moisture content. The model's robustness across diverse samples and its suitability for online applications make it a promising tool for efficient and non-destructive quality control in the food industry.

Stability and functionality of bovine lactoferrin powder after 9 years of storage

Bovine lactoferrin (bLF) is a multifunctional protein widely used in food industries. Most bLF products are delivered in a powder form; however, their stability remains unclear. Herein, freeze-dried bLF powders were stored at 4 °C and 40 % relative humidity (RH) for 9 years since 2016. After the long-term storage, their functional properties, including antibacterial ability, antioxidant ability and iron-binding ability, were determined and compared with those of eight commercial LF powders. The bLF powder stored for 9 years demonstrated comparable physicochemical and functional properties with those of commercial LF powders (e.g. >93 % water solubility, >100 mg/100 g iron-binding ability, and >1.7 logCFU/mL bacterial growth reduction against Salmonella enteritidis). The haemolysis test indicated that the bLF stored for 9 years exhibited good biocompatibility at a concentration of <5 mg/mL. Therefore, bLF powders can be stored for extremely long periods (>9 years) with minimal side effects. These findings can expand the utilisation of lactoferrin to many specific cases such as voyage and aerospace foods.

Simultaneous monitoring of two comprehensive quality evaluation indexes of frozen-thawed beef meatballs using hyperspectral imaging and multi-task convolutional neural network

The quality of beef meatballs during repeated freeze-thaw (F-T) cycles was assessed by multiple indicators. This study introduced a novel quality evaluation method using hyperspectral imaging (HSI) and multi-task learning. Seventeen quality indicators were analyzed to assess the impact of F-T cycles. Subsequently, a comprehensive quality index (CQI) and a comprehensive weight index (CWI) were constructed from 11 key indicators via factor analysis. By integrating HSI data from 150 samples with multi-task convolutional neural network (MT-CNN), the feasibility of simultaneous monitoring of CQI and CWI of the beef meatballs was explored. The results demonstrated that MT-CNN achieved superior predictions for CQI (RMSEp = 1.24, R2 = 0.94) and CWI (RMSEp = 20.436, R2 = 0.94) compared to traditional machine learning and single-task CNN approaches. Furthermore, the deterioration trends of beef meatballs during multiple F-T cycles were effectively visualized. Thus, the integration of HSI and MT-CNN enabled efficient prediction of comprehensive evaluation indexes for beef meatballs, contributing to their quality control.

Hyperspectral imaging for detection of macronutrients retained in glutinous rice under different drying conditions

This study detected the macronutrients retained in glutinous rice (GR) under different drying conditions by innovatively applying visible-near infrared hyperspectral imaging coupled with different spectra preprocessing and effective wavelength selection techniques (EWs). Subsequently, predictive models were developed based on processed spectra for the detection of the macronutrients, which include protein content (PC), moisture content (MC), fat content (FC), and ash content (AC). The result shows the raw spectra-based model had a prediction accuracy (R p 2 ) of 0.6493, 0.9521, 0.4594, and 0.9773 for PC, MC, FC, and AC, respectively. Applying Savitzky Golay first derivatives (SG1D) method increases theR p 2 value to 0.9972, 0.9970, 0.9857 and 0.9972 for PC, MC, FC, and AC, respectively. Using the variable iterative space shrinkage algorithm (VISSA) as EWs reduces the spectral bands by over 60%, and this increases the accuracy of the model (SG1D-VISSA-PLSR) to 100%. Therefore, the developed SGID-VISSA-PLSR can be used to build a smart and reliable spectral system for detecting the macronutrients in GR grains.

Comparative Analysis of XGB, CNN, and ResNet Models for Predicting Moisture Content in Porphyra yezoensis Using Near-Infrared Spectroscopy

This study explored the performance and reliability of three predictive models-extreme gradient boosting (XGB), convolutional neural network (CNN), and residual neural network (ResNet)-for determining the moisture content in Porphyra yezoensis using near-infrared (NIR) spectroscopy. We meticulously selected 380 samples from various sources to ensure a comprehensive dataset, which was then divided into training (300 samples) and test sets (80 samples). The models were evaluated based on prediction accuracy and stability, employing genetic algorithms (GA) and partial least squares (PLS) for wavelength selection to enhance the interpretability of feature extraction outcomes. The results demonstrated that the XGB model excelled with a determination coefficient (R2) of 0.979, a root mean square error of prediction (RMSEP) of 0.004, and a high ratio of performance to deviation (RPD) of 4.849, outperforming both CNN and ResNet models. A Gaussian process regression (GPR) was employed for uncertainty assessment, reinforcing the reliability of our models. Considering the XGB model's high accuracy and stability, its implementation in industrial settings for quality assurance is recommended, particularly in the food industry where rapid and non-destructive moisture content analysis is essential. This approach facilitates a more efficient process for determining moisture content, thereby enhancing product quality and safety.

In-field and non-destructive determination of comprehensive maturity index and maturity stages of Camellia oleifera fruits using a portable hyperspectral imager

To efficiently detect the maturity stages of Camellia oleifera fruits, this study proposed a non-invasive method based on hyperspectral imaging technology. First, a portable hyperspectral imager was used for the in-field image acquisition of Camellia oleifera fruits at three maturity stages, and ten quality indexes were measured as reference standards. Then, factor analysis was performed to obtain the comprehensive maturity index (CMI) by analyzing the change trends and correlations of different indexes. To reduce the high dimensionality of spectral data, the successive projection algorithm (SPA) was employed to select effective feature wavelengths. The prediction models for CMI, including partial least squares regression (PLSR), support vector regression (SVR), extreme learning machine (ELM), and convolutional neural network regression (CNNR), were constructed based on full spectra and feature wavelengths; for CNNR, only the raw spectra were used as input. The SPA-CNNR model exhibited more promising performance (RP = 0.839, RMSEP = 0.261, and RPD = 1.849). Furthermore, PLS-DA models for maturity discrimination of Camellia oleifera fruits were developed using full wavelength, characteristic wavelengths and their fusion CMI, respectively. The PLS-DA model using the fused dataset achieved the highest maturity classification accuracy, with the best simplified model achieving 88.6 % accuracy in prediction set. This study indicated that a portable hyperspectral imager can be used for in-field determination of the internal quality and maturity stages of Camellia oleifera fruits. It provides strong support for non-destructive quality inspection and timely harvesting of Camellia oleifera fruits in the field.

NIR Sensing Technologies for the Detection of Fraud in Nuts and Nut Products: A Review

Food fraud is a major threat to the integrity of the nut supply chain. Strategies using a wide range of analytical techniques have been developed over the past few years to detect fraud and to assure the quality, safety, and authenticity of nut products. However, most of these techniques present the limitations of being slow and destructive and entailing a high cost per analysis. Nevertheless, near-infrared (NIR) spectroscopy and NIR imaging techniques represent a suitable non-destructive alternative to prevent fraud in the nut industry with the advantages of a high throughput and low cost per analysis. This review collects and includes all major findings of all of the published studies focused on the application of NIR spectroscopy and NIR imaging technologies to detect fraud in the nut supply chain from 2018 onwards. The results suggest that NIR spectroscopy and NIR imaging are suitable technologies to detect the main types of fraud in nuts.

A fresh-cut papaya freshness prediction model based on partial least squares regression and support vector machine regression

This study investigated the physicochemical and flavor quality changes in fresh-cut papaya that was stored at 4 °C. Multivariate statistical analysis was used to evaluate the freshness of fresh-cut papaya. Aerobic plate counts were selected as a predictor of freshness of fresh-cut papaya, and a prediction model for freshness was established using partial least squares regression (PLSR), and support vector machine regression (SVMR) algorithms. Freshness of fresh-cut papaya could be well distinguished based on physicochemical and flavor quality analyses. The aerobic plate counts, as a predictor of freshness of fresh-cut papaya, significantly correlated with storage time. The SVMR model had a higher prediction accuracy than the PLSR model. Combining flavor quality with multivariate statistical analysis can be effectively used for evaluating the freshness of fresh-cut papaya.

Integrating spectral and image information for prediction of cottonseed vitality

Cotton plays a significant role in people's lives, and cottonseeds serve as a vital assurance for successful cotton cultivation and production. Premium-quality cottonseeds can significantly enhance the germination rate of cottonseeds, resulting in increased cotton yields. The vitality of cottonseeds is a crucial metric that reflects the quality of the seeds. However, currently, the industry lacks a non-destructive method to directly assess cottonseed vitality without compromising the integrity of the seeds. To address this challenge, this study employed a hyperspectral imaging acquisition system to gather hyperspectral data on cottonseeds. This system enables the simultaneous collection of hyperspectral data from 25 cottonseeds. This study extracted spectral and image information from the hyperspectral data of cottonseeds to predict their vitality. SG, SNV, and MSC methods were utilized to preprocess the spectral data of cottonseeds. Following this preprocessing step, feature wavelength points of the cottonseeds were extracted using SPA and CARS algorithms. Subsequently, GLCM was employed to extract texture features from images corresponding to these feature wavelength points, including attributes such as Contrast, Correlation, Energy, and Entropy. Finally, the vitality of cottonseeds was predicted using PLSR, SVR, and a self-built 1D-CNN model. For spectral data analysis, the 1D-CNN model constructed after MSC+CARS preprocessing demonstrated the highest performance, achieving a test set correlation coefficient of 0.9214 and an RMSE of 0.7017. For image data analysis, the 1D-CNN model constructed after SG+CARS preprocessing outperformed the others, yielding a test set correlation coefficient of 0.8032 and an RMSE of 0.9683. In the case of fused spectral and image data, the 1D-CNN model built after SG+SPA preprocessing displayed the best performance, attaining a test set correlation coefficient of 0.9427 and an RMSE of 0.6872. These findings highlight the effectiveness of the 1D-CNN model and the fusion of spectral and image features for cottonseed vitality prediction. This research contributes significantly to the development of automated detection devices for assessing cottonseed vitality.

D2O assisted FTIR spectroscopic analysis of moisture in edible oil

D₂O-assisted moisture analysis of edible oils was investigated. The acetonitrile extract of the oil samples was split into two parts. The spectrum of one part was taken as is, another was recorded after addition of excess D₂O. Changes in spectral absorption of the H-O-H bending band (1600-1660 cm^-1) was used to calculate moisture in oil samples. To effectively depleting absorption of water in the acetonitrile extract, a 30-fold excess of D₂O is required. The typical OH-containing constituents in oil did not show significant interference on the H/D exchange. Validation experiments by using five oils with five levels of moisture spiked (50-1000 μg/g) suggested that the prediction tracked the spiked amounts well. The results of variance analysis indicate that there is no difference in terms of analytical methods and oil types used (p < 0.001). The D₂O method developed is generally applicable to the accurate analysis of moisture at trace levels (<100 μg/g) in edible oils.

The Application of Hyperspectral Imaging Technologies for the Prediction and Measurement of the Moisture Content of Various Agricultural Crops during the Drying Process

Drying is one of the common procedures in the food processing steps. The moisture content (MC) is also of crucial significance in the evaluation of the drying technique and quality of the final product. However, conventional MC evaluation methods suffer from several drawbacks, such as long processing time, destruction of the sample and the inability to determine the moisture of single grain samples. In this regard, the technology and knowledge of hyperspectral imaging (HSI) were addressed first. Then, the reports on the use of this technology as a rapid, non-destructive, and precise method were explored for the prediction and detection of the MC of crops during their drying process. After spectrometry, researchers have employed various pre-processing and merging data techniques to decrease and eliminate spectral noise. Then, diverse methods such as linear and multiple regressions and machine learning were used to model and predict the MC. Finally, the best wavelength capable of precise estimation of the MC was reported. Investigation of the previous studies revealed that HSI technology could be employed as a valuable technique to precisely control the drying process. Smart dryers are expected to be commercialised and industrialised soon by the development of portable systems capable of an online MC measurement.

Hyperspectral Imaging for the Detection of Bitter Almonds in Sweet Almond Batches

A common fraud in the sweet almond industry is the presence of bitter almonds in commercial batches. The presence of bitter almonds not only causes unpleasant flavours but also problems in the commercialisation and toxicity for consumers. Hyperspectral Imaging (HSI) has been proved to be suitable for the rapid and non-destructive quality evaluation in foods as it integrates the spectral and spatial dimensions. Thus, we aimed to study the feasibility of using an HSI system to identify single bitter almond kernels in commercial sweet almond batches. For this purpose, sweet and bitter almond batches, as well as different mixtures, were analysed in bulk using an HSI system which works in the spectral range 946.6–1648.0 nm. Qualitative models were developed using Partial Least Squares-Discriminant Analysis (PLS-DA) to differentiate between sweet and bitter almonds, obtaining a classification success of over the 99%. Furthermore, data reduction, as a function of the most relevant wavelengths (VIP scores), was applied to evaluate its performance. Then, the pixel-by-pixel validation of the mixtures was carried out, identifying correctly between 61–85% of the adulterations, depending on the group of mixtures and the cultivar analysed. The results confirm that HSI, without VIP scores data reduction, can be considered a promising approach for classifying the bitterness of almonds analysed in bulk, enabling identifying individual bitter almonds inside sweet almond batches. However, a more complex mathematical analysis is necessary before its implementation in the processing lines.