Advances in infrared spectroscopy and hyperspectral imaging combined with artificial intelligence for the detection of cereals quality

Harnessing artificial intelligence for advancements in Rice / wheat functional food Research and Development

In recent years, the research and development (R&D) of rice and wheat functional foods has attracted a widespread attention from food researchers, driven by the increasing global food consumption and growing consumer demand for healthier and safer food. Artificial intelligence (AI) has the potential to enhance efficiency, quality, and safety through the AI's problem-solving and decision-support capabilities. This review provides a comprehensive overview of AI-related technologies applied in food industry, including machine learning, large language models, computer vision, and intelligent sensor. It then explores AI applications in rice / wheat functional food R&D over the past five years (2020-2024), covering key topics such as crops cultivation and screening, food processing, food quality and safety, challenges and future prospects. The introduction of AI technology has led the field towards higher efficiency, non-destructive analysis, better robustness and greater stability. In practical applications, combining AI technology with various spectroscopic and sensing technologies has shown great promise in addressing critical problems such as low crop yields, insufficient functional nutrition in grains, over-processing, and ecological contamination caused by traditional detection methods. Nevertheless, the implementation of AI in this field still faces several challenges, including narrow application scope, limited data availability, high application cost, and trust-related concerns. Looking ahead, as the application scenarios and functionalities of AI continue to broaden, AI is poised to emerge as a disruptive technology that would fundamentally transform the landscape of rice / wheat functional food R&D.

Hyperspectral Imaging and Deep Learning for Quality and Safety Inspection of Fruits and Vegetables: A Review

Quality inspection of fruits and vegetables linked to food safety monitoring and quality control. Traditional chemical analysis and physical measurement techniques are reliable, they are also time-consuming, costly, and susceptible to environmental and sample changes. Hyperspectral imaging technology combined with deep learning methods can effectively overcome these problems. Compared with human evaluation, automated inspection improves inspection efficiency, reduces subjective error, and promotes the intelligent and precise fruit and vegetable quality inspection. This paper reviews reports on the application of hyperspectral imaging technology combined to deep learning methods in various aspects of fruits and vegetables quality assessment. In addition, the latest applications of these technologies in the fields of fruit and vegetable safety, internal quality, and external quality inspection are reviewed, and the challenges and future development directions of hyperspectral imaging technology combined with deep learning in this field are prospected. Hyperspectral imaging combined with deep learning has shown significant advantages in fruit and vegetable quality inspection, especially in improving inspection accuracy and efficiency. Future research should focus on reducing costs, optimizing equipment, personalizing feature extraction, and model generalizability. In addition, the development of lightweight models and the balance of accuracy, the enhancement of the database and the importance of quantitative research should also be brought to attention. These efforts will promote the wide application of hyperspectral imaging technology in fruit and vegetable inspection, improve its practicability in the actual production environment, and bring important progress for food safety and quality management.

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 [...].

Non-Destructive Detection of Soybean Storage Quality Using Hyperspectral Imaging Technology

(1) Background: Soybean storage quality is crucial for subsequent processing and consumption, making it essential to explore an objective, rapid, and non-destructive technology for assessing its quality. (2) Methods: crude fatty acid value is an important indicator for evaluating the storage quality of soybeans. In this study, three types of soybeans were subjected to accelerated aging to analyze trends in crude fatty acid values. The study focused on acquiring raw spectral information using hyperspectral imaging technology, preprocessing by the derivative method (1ST, 2ND), multiplicative scatter correction (MSC), and standard normal variate (SNV). The feature variables were extracted by a variable iterative space shrinkage approach (VISSA), competitive adaptive reweighted sampling (CARS), and a successive projections algorithm (SPA). Partial least squares regression (PLSR), support vector machine (SVM), and extreme learning machine (ELM) models were developed to predict crude fatty acid values of soybeans. The optimal model was used to visualize the dynamic distribution of these values. (3) Results: the crude fatty acid values exhibited a positive correlation with storage time, functioning as a direct indicator of soybean quality. The 1ST-VISSA-SVM model was the optimal predictive model for crude fatty acid values, achieving a coefficient of determination (R2) of 0.9888 and a root mean square error (RMSE) of 0.1857 and enabling the visualization of related chemical information. (4) Conclusions: it has been confirmed that hyperspectral imaging technology possesses the capability for the non-destructive and rapid detection of soybean storage quality.

Applications of synchrotron light in seed research: an array of x-ray and infrared imaging methodologies

Synchrotron radiation (SR) provides a wide spectrum of bright light that can be tailored to test myriad research questions. SR provides avenues to illuminate structure and composition across scales, making it ideally suited to the study of plants and seeds. Here, we present an array of methodologies and the data outputs available at a light source facility. Datasets feature seed and grain from a range of crop species including Citrullus sp. (watermelon), Brassica sp. (canola), Pisum sativum (pea), and Triticum durum (wheat), to demonstrate the power of SR for advancing plant science. The application of SR micro-computed tomography (SR-µCT) imaging revealed internal seed microstructures and their three-dimensional morphologies in exquisite detail, without the need for destructive sectioning. Spectroscopy in the infrared spectrum probed sample biochemistry, detailing the spatial distribution of seed macronutrients such as lipid, protein and carbohydrate in the embryo, endosperm and seed coat. Methods using synchrotron X-rays, including X-ray absorption spectroscopy (XAS) and X-ray fluorescence (XRF) imaging revealed elemental distributions, to spatially map micronutrients in seed subcompartments and to determine their speciation. Synchrotron spectromicroscopy (SM) allowed chemical composition to be resolved at the nano-scale level. Diverse crop seed datasets showcase the range of structural and chemical insights provided by five beamlines at the Canadian Light Source, and the potential for synchrotron imaging for informing plant and agricultural research.

AI-based processing of future prepared foods: Progress and prospects

The prepared foods sector has grown rapidly in recent years, driven by the fast pace of modern living and increasing consumer demand for convenience. Prepared foods are taking an increasingly important role in the modern catering industry due to their ease of storage, transportation, and operation. However, their processing faces several challenges, including labor shortages, inefficient sorting, inadequate cleaning, unsafe cutting processes, and a lack of industry standards. The development of artificial intelligence (AI) will change the processing of prepared foods. This review summarizes the progress and prospects of AI applications in the sorting/classification, cleaning, cutting, preprocessing, and freezing of prepared foods, encompassing techniques such as mathematical modeling, chemometrics, machine learning, fuzzy logic, and adaptive neuro fuzzy inference system. For example, AI-powered sorting systems using computer vision have improved accuracy in ingredient classification, while deep learning models in cleaning processes have enhanced microbial contamination detection with high spectral imaging techniques. Despite challenges like managing large-scale data and complex models, AI has shown significant potential to inspire both industry practice and research. AI applications can enhance the efficiency, accuracy, and consistency of prepared foods processing, while also reducing labor costs, improving hygiene monitoring, minimizing resource waste, and decreasing environmental impact. Furthermore, AI-driven resource optimization has demonstrated its potential in reducing energy consumption and promoting sustainable food production practices. In the future, AI technology is expected to further improve model generalization and operation precision, driving the food processing industry toward smarter, more sustainable development. This study provides valuable insights to encourage further innovation in AI applications within food processing and technological advancement in the food industry.

Quantitative predictions of protein and total flavonoids content in Tartary and common buckwheat using near-infrared spectroscopy and chemometrics

A rapid method was developed for determining the total flavonoid and protein content in Tartary buckwheat by employing near-infrared spectroscopy (NIRS) and various machine learning algorithms, including partial least squares regression (PLSR), support vector regression (SVR), and backpropagation neural network (BPNN). The RAW-SPA-CV-SVR model exhibited superior predictive accuracy for both Tartary and common buckwheat, with a high coefficient of determination (R2p = 0.9811) and a root mean squared error of prediction (RMSEP = 0.1071) for flavonoids, outperforming both PLSR and BPNN models. Additionally, the MMN-SPA-PSO-SVR model demonstrated exceptional performance in predicting protein content (R2p = 0.9247, RMSEP = 0.3906), enhancing the effectiveness of the MMN preprocessing technique for preserving the original data distribution. These findings indicate that the proposed methodology could efficiently assess buckwheat adulteration analysis. It can also provide new insights for the development of a promising method for quantifying food adulteration and controlling food quality.

Comparative Quantitative and Discriminant Analysis of Wheat Flour with Different Levels of Chemical Azodicarbonamide Using NIR Spectroscopy and Hyperspectral Imaging

This study investigated and comprehensively compared the performance of spectra (950-1660 nm) acquired respectively from NIR and HSI in the rapid and non-destructive quantification of azodicarbonamide (ADA) content (0-100 mg/kg) in WF and simultaneously identified WF containing excessive ADA (>45 mg/kg). The raw spectra were preprocessed using 14 methods and then mined by the partial least squares (PLS) algorithm to fit ADA levels using different numbers of WF samples for training and validation in five datasets (NTraining/Validation = 189/21, 168/42, 147/63, 126/84, 105/105), yielding better abilities of NIR Savitzky-Golay 1st derivative (SG1D) spectra-based PLS models and raw HSI spectra-based PLS models in quantifying ADA with higher determination coefficients and lower root-mean-square errors in validation (R2V & RMSEV), as well as establishing 100% accuracy in PLS discriminant analysis (PLS-DA) models for identifying excessive ADA-contained WF in each dataset. Twenty-four wavelengths selected from a NIR SG1D spectra in a 168/42 dataset and 23 from a raw HSI spectra in a 147/63 dataset allowed for the better performance of quantitative models in ADA determination with higher R2V and RMSEV in validation (R2V > 0.98, RMSEV < 3.87 mg/kg) and for discriminant models in WF classification with 100% accuracy. In summary, NIR technology may be sufficient if visualization is not required.

Unveiling the relationship between food unit operations and food industry 4.0: A short review

The fourth industrial revolution (Industry 4.0) is driving significant changes across multiple sectors, including the food industry. This review examines how Industry 4.0 technologies, such as smart sensors, artificial intelligence, robotics, and blockchain, among others, are transforming unit operations within the food sector. These operations, which include preparation, processing/transformation, preservation/stabilization, and packaging and transportation, are crucial for converting raw materials into high-quality food products. By incorporating advanced digital, physical, and biological innovations, Industry 4.0 technologies are enhancing precision, productivity, and environmental responsibility in food production. The review highlights innovative applications and key findings that showcase how these technologies can streamline processes, minimize waste, and improve food product quality. The adoption of Industry 4.0 innovations is increasingly reshaping the way food is prepared, transformed, preserved, packaged, and transported to the final consumer. The work provides a valuable roadmap for various sectors within agriculture and food industries, promoting the adoption of Industry 4.0 solutions to enhance efficiency, quality, and sustainability throughout the entire food supply chain.

AI in analytical chemistry: Advancements, challenges, and future directions

This article explores the influence and applications of Artificial Intelligence (AI) in analytical chemistry, highlighting its potential to revolutionize the analysis of complex data sets and the development of innovative analytical methods. Additionally, it discusses the role of AI in interpreting large-scale data and optimizing experimental processes. AI has been fundamental in managing heterogeneous data and in advanced analysis of complex spectra in areas such as spectroscopy and chromatography. The article also examines the historical development of AI in chemistry, its current challenges, including the interpretation of AI models and the integration of large volumes of data. Finally, it forecasts future trends and the potential impact of AI on analytical chemistry, emphasizing the need for ethical and secure approaches in the use of AI.

Innovations in nondestructive assessment of baked products: Current trends and future prospects

Rising consumer awareness, coupled with advances in sensor technology, is propelling the food manufacturing industry to innovate and employ tools that ensure the production of safe, nutritious, and environmentally sustainable products. Amidst a plethora of nondestructive techniques available for evaluating the quality attributes of both raw and processed foods, the challenge lies in determining the most fitting solution for diverse products, given that each method possesses its unique strengths and limitations. This comprehensive review focuses on baked goods, wherein we delve into recently published literature on cutting-edge nondestructive methods to assess their feasibility for Industry 4.0 implementation. Emphasizing the need for quality control modalities that align with consumer expectations regarding sensory traits such as texture, flavor, appearance, and nutritional content, the review explores an array of advanced methodologies, including hyperspectral imaging, magnetic resonance imaging, terahertz, acoustics, ultrasound, X-ray systems, and infrared spectroscopy. By elucidating the principles, applications, and impacts of these techniques on the quality of baked goods, the review provides a thorough synthesis of the most current published studies and industry practices. It highlights how these methodologies enable defect detection, nutritional content prediction, texture evaluation, shelf-life forecasting, and real-time monitoring of baking processes. Additionally, the review addresses the inherent challenges these nondestructive techniques face, ranging from cost considerations to calibration, standardization, and the industry's overreliance on big data.

Hyperspectral Imaging and Machine Learning as a Nondestructive Method for Proso Millet Seed Detection and Classification

Millet is a small-seeded cereal crop with big potential. There are many different cultivars of proso millet (Panicum miliaceum L.) with different characteristics, bringing forth the issue of sorting which are important for growers, processors, and consumers. Current methods of grain cultivar detection and classification are subjective, destructive, and time-consuming. Therefore, there is a need to develop nondestructive methods for sorting the cultivars of proso millet. In this study, the feasibility of using near-infrared (NIR) hyperspectral imaging (900-1700 nm) to discriminate between different cultivars of proso millet seeds was evaluated. A total of 5000 proso millet seeds were randomly obtained and investigated from the ten most popular cultivars in the United States, namely Cerise, Cope, Earlybird, Huntsman, Minco, Plateau, Rise, Snowbird, Sunrise, and Sunup. To reduce the large dimensionality of the hyperspectral imaging, principal component analysis (PCA) was applied, and the first two principal components were used as spectral features for building the classification models because they had the largest variance. The classification performance showed prediction accuracy rates as high as 99% for classifying the different cultivars of proso millet using a Gradient tree boosting ensemble machine learning algorithm. Moreover, the classification was successfully performed using only 15 and 5 selected spectral features (wavelengths), with an accuracy of 98.14% and 97.6%, respectively. The overall results indicate that NIR hyperspectral imaging could be used as a rapid and nondestructive method for the classification of proso millet seeds.

Advancements, limitations and challenges in hyperspectral imaging for comprehensive assessment of wheat quality: An up-to-date review

The potential of hyperspectral imaging technology (HIT) for the determination of physicochemical and nutritional components, evaluation of fungal/mycotoxins contamination, wheat varieties classification, identification of non-mildew-damaged wheat kernels, as well as detection of flour adulteration is comprehensively illustrated and reviewed. The latest findings (2018-2023) of HIT in wheat quality evaluation through internal and external attributes are compared and summarized in detail. The limitations and challenges of HIT to improve assessment accuracy are clearly described. Additionally, various practical recommendations and strategies for the potential application of HIT are highlighted. The future trends and prospects of HIT in evaluating wheat quality are also mentioned. In conclusion, HIT stands as a cutting-edge technology with immense potential for revolutionizing wheat quality evaluation. As advancements in HIT continue, it will play a pivotal role in shaping the future of wheat quality assessment and contributing to a more sustainable and efficient food supply chain.

Combining AI Tools with Non-Destructive Technologies for Crop-Based Food Safety: A Comprehensive Review

On a global scale, food safety and security aspects entail consideration throughout the farm-to-fork continuum, considering food's supply chain. Generally, the agrifood system is a multiplex network of interconnected features and processes, with a hard predictive rate, where maintaining the food's safety is an indispensable element and is part of the Sustainable Development Goals (SDGs). It has led the scientific community to develop advanced applied analytical methods, such as machine learning (ML) and deep learning (DL) techniques applied for assessing foodborne diseases. The main objective of this paper is to contribute to the development of the consensus version of ongoing research about the application of Artificial Intelligence (AI) tools in the domain of food-crop safety from an analytical point of view. Writing a comprehensive review for a more specific topic can also be challenging, especially when searching within the literature. To our knowledge, this review is the first to address this issue. This work consisted of conducting a unique and exhaustive study of the literature, using our TriScope Keywords-based Synthesis methodology. All available literature related to our topic was investigated according to our criteria of inclusion and exclusion. The final count of data papers was subject to deep reading and analysis to extract the necessary information to answer our research questions. Although many studies have been conducted, limited attention has been paid to outlining the applications of AI tools combined with analytical strategies for crop-based food safety specifically.

Classification of multi-year and multi-variety pumpkin seeds using hyperspectral imaging technology and three-dimensional convolutional neural network

BACKGROUND

Pumpkin seeds are major oil crops with high nutritional value and high oil content. The collection and identification of different pumpkin germplasm resources play a significant role in the realization of precision breeding and variety improvement. In this research, we collected 75 species of pumpkin from the Zhejiang Province of China. 35,927 near-infrared hyperspectral images of 75 types of pumpkin seeds were used as the research object.

RESULTS

To realize the rapid classification of pumpkin seed varieties, position attention embedded three-dimensional convolutional neural network (PA-3DCNN) was designed based on hyperspectral image technology. The experimental results showed that PA-3DCNN had the best classification effect than other classical machine learning technology. The classification accuracy of 99.14% and 95.20% were severally reached on the training and test sets. We also demonstrated that the PA-3DCNN model performed well in next year's classification with fine-tuning and met with 94.8% accuracy.

CONCLUSIONS

The model performance improved by introducing double convolution and pooling structure and position attention module. Meanwhile, the generalization performance of the model was verified, which can be adopted for the classification of pumpkin seeds in multiple years. This study provided a new strategy and a feasible technical approach for identifying germplasm resources of pumpkin seeds.

Nanoelectromechanical Infrared Spectroscopy with In Situ Separation by Thermal Desorption: NEMS-IR-TD

We present a novel method for the quantitative analysis of mixtures of semivolatile chemical compounds. For the first time, thermal desorption is integrated directly with nanoelectromechanical infrared spectroscopy (NEMS-IR-TD). In this new technique, an analyte mixture is deposited via nebulization on the surface of a NEMS sensor and subsequently desorbed using heating under vacuum. The desorption process is monitored in situ via infrared spectroscopy and thermogravimetric analysis. The resulting spectro-temporal maps allow for selective identification and analysis of the mixture. In addition, the corresponding thermogravimetric data allow for analysis of the desorption dynamics of the mixture components. As a demonstration, caffeine and theobromine were selectively identified and quantified from a mixture with a detection limit of less than 6 pg (about 30 fmol). With its exceptional sensitivity, NEMS-IR-TD allows for the analysis of low abundance and complex analytes with potential applications ranging from environmental sensing to life sciences.

Emerging technologies for preservation and quality evaluation of postharvest edible mushrooms: A review

Edible mushrooms are the highly demanded foods of which production and consumption have been steadily increasing globally. Owing to the quality loss and short shelf-life in harvested mushrooms, it is necessary for the implementation of effective preservation and intelligent evaluation technologies to alleviate this issue. The aim of this review was to analyze the development and innovation thematic lines, topics, and trends by bibliometric analysis and review of the literature methods. The challenges faced in researching these topics were proposed and the mechanisms of quality loss in mushrooms during storage were updated. This review summarized the effects of chemical processing (antioxidants, ozone, and coatings), physical treatments (non-thermal plasma, packaging and latent thermal storage) and other emerging application on the quality of fresh mushrooms while discussing the efficiency in extending the shelf-life. It also discussed the emerging evaluation techniques based on the various chemometric methods and computer vision system in monitoring the freshness and predicting the shelf-life of mushrooms which have been developed. Preservation technology optimization and dynamic quality evaluation are vital for achieving mushroom quality control. This review can provide a comprehensive research reference for reducing mushroom quality loss and extending shelf-life, along with optimizing efficiency of storage and transportation operations.

Detection of protein, starch, oil, and moisture content of corn kernels using one-dimensional convolutional autoencoder and near-infrared spectroscopy

Background

Analysis of the nutritional values and chemical composition of grain products plays an essential role in determining the quality of the products. Near-infrared spectroscopy has attracted the attention of researchers in recent years due to its advantages in the analysis process. However, preprocessing and regression models in near-infrared spectroscopy are usually determined by trial and error. Combining newly popular deep learning algorithms with near-infrared spectroscopy has brought a new perspective to this area.

Methods

This article presents a new method that combines a one-dimensional convolutional autoencoder with near-infrared spectroscopy to analyze the protein, moisture, oil, and starch content of corn kernels. First, a one-dimensional convolutional autoencoder model was created for three different spectra in the corn dataset. Thirty-two latent variables were obtained for each spectrum, which is a low-dimensional spectrum representation. Multiple linear regression models were built for each target using the latent variables of obtained autoencoder models.

Results

R², RMSE, and RMSPE were used to show the performance of the proposed model. The created one-dimensional convolutional autoencoder model achieved a high reconstruction rate with a mean RMSPE value of 1.90% and 2.27% for calibration and prediction sets, respectively. This way, a spectrum with 700 features was converted to only 32 features. The created MLR models which use these features as input were compared to partial least squares regression and principal component regression combined with various preprocessing methods. Experimental results indicate that the proposed method has superior performance, especially in MP5 and MP6 datasets.

Quantification of Photosynthetic Pigments in Neopyropia yezoensis Using Hyperspectral Imagery

Phycobilisomes and chlorophyll-a (Chla) play important roles in the photosynthetic physiology of red macroalgae and serve as the primary light-harvesting antennae and reaction center for photosystem II. Neopyropia is an economically important red macroalga widely cultivated in East Asian countries. The contents and ratios of 3 main phycobiliproteins and Chla are visible traits to evaluate its commercial quality. The traditional analytical methods used for measuring these components have several limitations. Therefore, a high-throughput, nondestructive, optical method based on hyperspectral imaging technology was developed for phenotyping the pigments phycoerythrin (PE), phycocyanin (PC), allophycocyanin (APC), and Chla in Neopyropia thalli in this study. The average spectra from the region of interest were collected at wavelengths ranging from 400 to 1000 nm using a hyperspectral camera. Following different preprocessing methods, 2 machine learning methods, partial least squares regression (PLSR) and support vector machine regression (SVR), were performed to establish the best prediction models for PE, PC, APC, and Chla contents. The prediction results showed that the PLSR model performed the best for PE (R _Test ² = 0.96, MAPE = 8.31%, RPD = 5.21) and the SVR model performed the best for PC (R _Test ² = 0.94, MAPE = 7.18%, RPD = 4.16) and APC (R _Test ² = 0.84, MAPE = 18.25%, RPD = 2.53). Two models (PLSR and SVR) performed almost the same for Chla (PLSR: R _Test ² = 0.92, MAPE = 12.77%, RPD = 3.61; SVR: R _Test ² = 0.93, MAPE = 13.51%, RPD =3.60). Further validation of the optimal models was performed using field-collected samples, and the result demonstrated satisfactory robustness and accuracy. The distribution of PE, PC, APC, and Chla contents within a thallus was visualized according to the optimal prediction models. The results showed that hyperspectral imaging technology was effective for fast, accurate, and noninvasive phenotyping of the PE, PC, APC, and Chla contents of Neopyropia in situ. This could benefit the efficiency of macroalgae breeding, phenomics research, and other related applications.

Combination of spectral index and transfer learning strategy for glyphosate-resistant cultivar identification

Glyphosate is one of the most widely used non-selective herbicides, and the creation of glyphosate-resistant cultivars solves the problem of limited spraying area. Therefore, it is of great significance to quickly identify resistant cultivars without destruction during the development of superior cultivars. This work took maize seedlings as the experimental object, and the spectral indices of leaves were calculated to construct a model with good robustness that could be used in different experiments. Compared with no transfer strategies, transferability of support vector machine learning model was improved by randomly selecting 14% of source domain from target domain to train and applying transfer component analysis algorithm, the accuracy on target domain reached 83% (increased by 71%), recall increased from 10 to 100%, and F1-score increased from 0.17 to 0.86. The overall results showed that both transfer component analysis algorithm and updating source domain could improve the transferability of model among experiments, and these two transfer strategies could complement each other's advantages to achieve the best classification performance. Therefore, this work is beneficial to timely understanding of the physiological status of plants, identifying glyphosate resistant cultivars, and ultimately provides theoretical basis and technical support for new cultivar creation and high-throughput selection.