Machine learning techniques for analysis of hyperspectral images to determine quality of food products: A review

Smartphone video imaging: A versatile, low-cost technology for food authentication

This study presents a low-cost smartphone-based imaging technique called smartphone video imaging (SVI) to capture short videos of samples that are illuminated by a colour-changing screen. Assisted by artificial intelligence, the study develops new capabilities to make SVI a versatile imaging technique such as the hyperspectral imaging (HSI). SVI enables classification of samples with heterogeneous contents, spatial representation of analyte contents and reconstruction of hyperspectral images from videos. When integrated with a residual neural network, SVI outperforms traditional computer vision methods for ginseng classification. Moreover, the technique effectively maps the spatial distribution of saffron purity in powder mixtures with predictive performance that is comparable to that of HSI. In addition, SVI combined with the U-Net deep learning module can produce high-quality images that closely resemble the target images acquired by HSI. These results suggest that SVI can serve as a consumer-oriented solution for food authentication.

Combining Vis-NIR and NIR hyperspectral imaging techniques with a data fusion strategy for prediction of norfloxacin residues in mutton

Norfloxacin is an antibacterial compound that belongs to the fluoroquinolone family. Currently, hyperspectral imaging (HSI) for the detection of antibiotic residues focuses mostly on individual systems. Attempts to integrate different HSI systems with complementary spectral ranges are still lacking. This study investigates the feasibility of applying data fusion strategies with two HSI techniques (Visible near-infrared and near-infrared) in combination to predict norfloxacin residue levels in mutton. Spectral data from the two spectral techniques were analyzed using partial least squares regression (PLSR), support vector regression (SVR) and stochastic configuration networks (SCN), respectively, and the two data fusion strategies were fused at the data level (low-level fusion) and feature level (middle-level fusion, mid-level fusion). The results indicated that the modeling performance of the two fused datasets was better than that of the individual systems. Mid-level fusion data achieved the best model based on uninformative variable elimination (UVE) combined with SCN, in which the determination coefficient of prediction set (R2p) of 0.9312, (root mean square error of prediction set) RMSEP of 0.3316 and residual prediction deviation (RPD) of 2.7434, in comparison with all others. Therefore, two HSI systems with complementary spectral ranges, combined with data fusion strategies and feature selection, could be used synergistically to improve the detection of norfloxacin residues. This study may provide a valuable reference for the non-destructive detection of antibiotic residues in meat.

Seabream Quality Monitoring Throughout the Supply Chain Using a Portable Multispectral Imaging Device

Monitoring food quality throughout the supply chain in a rapid and cost-effective way allows on-time decision-making, reducing food waste, and increasing sustainability. A portable multispectral imaging sensor was used for the rapid prediction of microbiological quality of fish fillets. Seabream fillets, packaged either in aerobic or vacuum conditions, were collected from both aquaculture and retail stores, while images were also acquired both from the skin and the flesh side of the fish fillets. In parallel to image acquisition, the microbial quality was also estimated for each fish fillet. The data were used for the training of predictive artificial neural network (ANN) models for the estimation of total aerobic counts (TACs). Models were built separately for fish parts (i.e., skin, flesh) and packaging conditions and were validated using two approaches (i.e., validation with data partitioning and external validation using samples from retail stores). The performance of the ANN models for the validation set with data partitioning was similar for the data collected from the flesh (RMSE = 0.402-0.547) and the skin side (RMSE = 0.500-0.533) of the fish fillets. Similar performance also was obtained from validation of the models of the different packaging conditions (i.e., aerobic, vacuum). The prediction capability of the models combining both air and vacuum packaged samples (RMSE = 0.531) was slightly lower compared to the models trained and validated per packaging condition, individually (RMSE = 0.510, 0.516 in air and vacuum, respectively). The models tested with unknown samples (i.e., fish fillets from retail stores-external validation) showed poorer performance (RMSE = 1.061-1.414) compared to the models validated with data partitioning (RMSE = 0.402-0.547). Multispectral imaging sensor appeared to be efficient for the rapid assessment of the microbiological quality of fish fillets for all the different cases evaluated. Hence, these outcomes could be beneficial not only for the industry and food operators but also for the authorities and consumers.

Towards Sustainable and Dynamic Modeling Analysis in Korean Pine Nuts: An Online Learning Approach with NIRS

Due to its advantages such as speed and noninvasive nature, near-infrared spectroscopy (NIRS) technology has been widely used in detecting the nutritional content of nut food. This study aims to address the problem of offline quantitative analysis models producing unsatisfactory results for different batches of samples due to complex and unquantifiable factors such as storage conditions and origin differences of Korean pine nuts. Based on the offline model, an online learning model was proposed using recursive partial least squares (RPLS) regression with online multiplicative scatter correction (OMSC) preprocessing. This approach enables online updates of the original detection model using a small amount of sample data, thereby improving its generalization ability. The OMSC algorithm reduces the prediction error caused by the inability to perform effective scatter correction on the updated dataset. The uninformative variable elimination (UVE) algorithm appropriately increases the number of selected feature bands during the model updating process to expand the range of potentially relevant features. The final model is iteratively obtained by combining new sample feature data with RPLS. The results show that, after OMSC preprocessing, with the number of features increased to 100, the new online model's R2 value for the prediction set is 0.8945. The root mean square error of prediction (RMSEP) is 3.5964, significantly outperforming the offline model, which yields values of 0.4525 and 24.6543, respectively. This indicates that the online model has dynamic and sustainable characteristics that closely approximate practical detection, and it provides technical references and methodologies for the design and development of detection systems. It also offers an environmentally friendly tool for rapid on-site analysis for nut food regulatory agencies and production enterprises.

Simultaneously predicting SPAD and water content in rice leaves using hyperspectral imaging with deep multi-task regression and transfer component analysis

BACKGROUND

Water content and chlorophyll content are important indicators for monitoring rice growth status. Simultaneous detection of water content and chlorophyll content is of significance. Different varieties of rice show differences in phenotype, resulting in the difficulties of establishing a universal model. In this study, hyperspectral imaging was used to detect the Soil and Plant Analyzer Development (SPAD) values and water content of fresh rice leaves of three rice varieties (Jiahua 1, Xiushui 121 and Xiushui 134).

RESULTS

Both partial least squares regression and convolutional neural networks were used to establish single-task and multi-task models. Transfer component analysis (TCA) was used as transfer learning to learn the common features to achieve an approximate identical distribution between any two varieties. Single-task and multi-task models were also built using the features of the source domain, and these models were applied to the target domain. These results indicated that for models of each rice variety the prediction accuracy of most multi-task models was close to that of single-task models. As for TCA, the results showed that the single-task model achieved good performance for all transfer learning tasks.

CONCLUSION

Compared with the original model, good and differentiated results were obtained for the models using features learned by TCA for both the source domain and target domain. The multi-task models could be constructed to predict SPAD values and water content simultaneously and then transferred to another rice variety, which could improve the efficiency of model construction and realize rapid detection of rice growth indicators. © 2024 Society of Chemical Industry.

Hyperspectral imaging with deep learning for quantification of tissue hemoglobin, melanin, and scattering

Significance

Hyperspectral cameras capture spectral information at each pixel in an image. Acquired spectra can be analyzed to estimate quantities of absorbing and scattering components, but the use of traditional fitting algorithms over megapixel images can be computationally intensive. Deep learning algorithms can be trained to rapidly analyze spectral data and can potentially process hyperspectral camera data in real time.

Aim

A hyperspectral camera was used to capture 1216 × 1936   pixel wide-field reflectance images of in vivo human tissue at 205 wavelength bands from 420 to 830 nm.

Approach

The optical properties of oxyhemoglobin, deoxyhemoglobin, melanin, and scattering were used with multi-layer Monte Carlo models to generate simulated diffuse reflectance spectra for 24,000 random combinations of physiologically relevant tissue components. These spectra were then used to train an artificial neural network (ANN) to predict tissue component concentrations from an input reflectance spectrum.

Results

The ANN achieved low root mean square errors in a test set of 6000 independent simulated diffuse reflectance spectra while calculating concentration values more than 4000× faster than a conventional iterative least squares approach.

Conclusions

In vivo finger occlusion and gingival abrasion studies demonstrate the ability of this approach to rapidly generate high-resolution images of tissue component concentrations from a hyperspectral dataset acquired from human subjects.

A Microscope Setup and Methodology for Capturing Hyperspectral and RGB Histopathological Imaging Databases

The digitization of pathology departments in hospitals around the world is now a reality. The current commercial solutions applied to digitize histopathological samples consist of a robotic microscope with an RGB-type camera attached to it. This technology is very limited in terms of information captured, as it only works with three spectral bands of the visible electromagnetic spectrum. Therefore, we present an automated system that combines RGB and hyperspectral technology. Throughout this work, the hardware of the system and its components are described along with the developed software and a working methodology to ensure the correct capture of histopathological samples. The software is integrated by the controller of the microscope, which features an autofocus functionality, whole slide scanning with a stitching algorithm, and hyperspectral scanning functionality. As a reference, the time to capture and process a complete sample with 20 regions of high biological interest using the proposed method is estimated at a maximum of 79 min, reducing the time required by a manual operator by at least three times. Both hardware and software can be easily adapted to other systems that might benefit from the advantages of hyperspectral technology.

Stochastic image spectroscopy: a discriminative generative approach to hyperspectral image modelling and classification

This paper introduces a new latent variable probabilistic framework for representing spectral data of high spatial and spectral dimensionality, such as hyperspectral images. We use a generative Bayesian model to represent the image formation process and provide interpretable and efficient inference and learning methods. Surprisingly, our approach can be implemented with simple tools and does not require extensive training data, detailed pixel-by-pixel labeling, or significant computational resources. Numerous experiments with simulated data and real benchmark scenarios show encouraging image classification performance. These results validate the unique ability of our framework to discriminate complex hyperspectral images, irrespective of the presence of highly discriminative spectral signatures.

Specific spectral sub-images for machine learning evaluation of optical differences between carbon ion and X ray radiation effects

Advances in radiotherapy, particularly the exploration of alternative radiation types such as carbon ions have updated our understanding of its effects and applicability on chondrosarcoma cells. Here we compare the optical effects produced by carbon ions (CI) and X-rays (XR) radiations on chondrosarcoma cells nuclei and set an automated method for evaluating the radiation-induced alterations without the need of chemical marking. Hyperspectral images (HSI) of SW1353 chondrosarcoma line carry detectable optical changes of the cells irradiated either with CI or XR compared to non-irradiated ones (REF). The differences between the spectral profiles of CI, XR and REF nuclei classes led to partitioning the HSIs into spectral sub-images. The changes are detected by support vector machine (SVM) classifiers whose performances are evaluated by the most used point metrics: sensitivity (SEN), accuracy (ACC), and precision (PREC), applied on spatial feature values. Specific interaction mechanisms by radiation type reveal distinct subintervals where HSIs changes are more prominent, and the classifiers perform at best. For CI the best classifiers are obtained for sub-images in the interval (424-436 nm), while for XR the best classifiers are obtained for sub-images in the interval (436-445 nm). The classifiers work better with texture features than roughness features in both cases. The classifier with the best SEN point metric in the testing phase is the most suitable to measure the irradiation efficiency irrespective of the radiation type. The altered nuclei are easier to discriminate when irradiated with CI than with XR. The study proves that SVM with optical data offers a rapid, automated, and label-free method for evaluating radiation-induced alterations in chondrosarcoma nuclei, thereby enabling effective analysis of extensive data.

Spectral characterization of intraoperative renal perfusion using hyperspectral imaging and artificial intelligence

Accurate intraoperative assessment of organ perfusion is a pivotal determinant in preserving organ function e.g. during kidney surgery including partial nephrectomy or kidney transplantation. Hyperspectral imaging (HSI) has great potential to objectively describe and quantify this perfusion as opposed to conventional surrogate techniques such as ultrasound flowmeter, indocyanine green or the subjective eye of the surgeon. An established live porcine model under general anesthesia received median laparotomy and renal mobilization. Different scenarios that were measured using HSI were (1) complete, (2) gradual and (3) partial malperfusion. The differences in spectral reflectance as well as HSI oxygenation (StO2) between different perfusion states were compelling and as high as 56.9% with 70.3% (± 11.0%) for "physiological" vs. 13.4% (± 3.1%) for "venous congestion". A machine learning (ML) algorithm was able to distinguish between these perfusion states with a balanced prediction accuracy of 97.8%. Data from this porcine study including 1300 recordings across 57 individuals was compared to a human dataset of 104 recordings across 17 individuals suggesting clinical transferability. Therefore, HSI is a highly promising tool for intraoperative microvascular evaluation of perfusion states with great advantages over existing surrogate techniques. Clinical trials are required to prove patient benefit.

Application of machine learning approach on halal meat authentication principle, challenges, and prospects: A review

Meat is a source of essential amino acids that are necessary for human growth and development, meat can come from dead, alive, Halal, or non-Halal animal species which are intentionally or economically (adulteration) sold to consumers. Sharia has prohibited the consumption of pork by Muslims. Because of the activities of adulterators in recent times, consumers are aware of what they eat. In the past, several methods were employed for the authentication of Halal meat, but numerous drawbacks are attached to this method such as lack of flexibility, limited application, time,consumption and low level of accuracy and sensitivity. Machine Learning (ML) is the concept of learning through the development and application of algorithms from given data and making predictions or decisions without being explicitly programmed. The techniques compared with traditional methods in Halal meat authentication are fast, flexible, scaled, automated, less expensive, high accuracy and sensitivity. Some of the ML approaches used in Halal meat authentication have proven a high percentage of accuracy in meat authenticity while other approaches show no evidence of Halal meat authentication for now. The paper critically highlighted some of the principles, challenges, successes, and prospects of ML approaches in the authentication of Halal meat.

Histological Hyperspectral Glioblastoma Dataset (HistologyHSI-GB)

Hyperspectral (HS) imaging (HSI) technology combines the main features of two existing technologies: imaging and spectroscopy. This allows to analyse simultaneously the morphological and chemical attributes of the objects captured by a HS camera. In recent years, the use of HSI provides valuable insights into the interaction between light and biological tissues, and makes it possible to detect patterns, cells, or biomarkers, thus, being able to identify diseases. This work presents the HistologyHSI-GB dataset, which contains 469 HS images from 13 patients diagnosed with brain tumours, specifically glioblastoma. The slides were stained with haematoxylin and eosin (H&E) and captured using a microscope at 20× power magnification. Skilled histopathologists diagnosed the slides and provided image-level annotations. The dataset was acquired using custom HSI instrumentation, consisting of a microscope equipped with an HS camera covering the spectral range from 400 to 1000 nm.

Machine Learning Applied to the Detection of Mycotoxin in Food: A Systematic Review

Mycotoxins, toxic secondary metabolites produced by certain fungi, pose significant threats to global food safety and public health. These compounds can contaminate a variety of crops, leading to economic losses and health risks to both humans and animals. Traditional lab analysis methods for mycotoxin detection can be time-consuming and may not always be suitable for large-scale screenings. However, in recent years, machine learning (ML) methods have gained popularity for use in the detection of mycotoxins and in the food safety industry in general due to their accurate and timely predictions. We provide a systematic review on some of the recent ML applications for detecting/predicting the presence of mycotoxin on a variety of food ingredients, highlighting their advantages, challenges, and potential for future advancements. We address the need for reproducibility and transparency in ML research through open access to data and code. An observation from our findings is the frequent lack of detailed reporting on hyperparameters in many studies and a lack of open source code, which raises concerns about the reproducibility and optimisation of the ML models used. The findings reveal that while the majority of studies predominantly utilised neural networks for mycotoxin detection, there was a notable diversity in the types of neural network architectures employed, with convolutional neural networks being the most popular.

SUnSeT: spectral unmixing of hyperspectral images for phenotyping soybean seed traits

KEY MESSAGE

Hyperspectral features enable accurate classification of soybean seeds using linear discriminant analysis and GWAS for novel seed trait genes. Evaluating crop seed traits such as size, shape, and color is crucial for assessing seed quality and improving agricultural productivity. The introduction of the SUnSet toolbox, which employs hyperspectral sensor-derived image analysis, addresses this necessity. In a validation test involving 420 seed accessions from the Korean Soybean Core Collections, the pixel purity index algorithm identified seed- specific hyperspectral endmembers to facilitate segmentation. Various metrics extracted from ventral and lateral side images facilitated the categorization of seeds into three size groups and four shape groups. Additionally, quantitative RGB triplets representing seven seed coat colors, averaged reflectance spectra, and pigment indices were acquired. Machine learning models, trained on a dataset comprising 420 accession seeds and 199 predictors encompassing seed size, shape, and reflectance spectra, achieved accuracy rates of 95.8% for linear discriminant analysis model. Furthermore, a genome-wide association study utilizing hyperspectral features uncovered associations between seed traits and genes governing seed pigmentation and shapes. This comprehensive approach underscores the effectiveness of SUnSet in advancing precision agriculture through meticulous seed trait analysis.

Phytobial remediation advances and application of omics and artificial intelligence: a review

Industrialization and urbanization increased the use of chemicals in agriculture, vehicular emissions, etc., and spoiled all environmental sectors. It causes various problems among living beings at multiple levels and concentrations. Phytoremediation and microbial association are emerging as a potential method for removing heavy metals and other contaminants from soil. The treatment uses plant physiology and metabolism to remove or clean up various soil contaminants efficiently. In recent years, omics and artificial intelligence have been seen as powerful techniques for phytobial remediation. Recently, AI and modeling are used to analyze large data generated by omics technologies. Machine learning algorithms can be used to develop predictive models that can help guide the selection of the most appropriate plant and plant growth-promoting rhizobacteria combination that is most effective at remediation. In this review, emphasis is given to the phytoremediation techniques being explored worldwide in soil contamination.

Essential spectral pixels-based improvement of UMAP classifying hyperspectral imaging data to identify minor compounds in food matrix

Classifying big data in hyperspectral imaging (HSI) can be challenging when minor (low-concentrated) compounds are present in actual samples, as for chemical additives and adulterants in food matrix. Herein, we propose a new strategy to classify HSI data for the identification of adulterants in food material for the first time. This strategy is based on the selection of essential spectral pixels of full HSI data followed by the feature space construction using uniform manifold approximation and projection as well as the data clustering utilizing hierarchical clustering analysis on the reduced data (named ESPs-UMAP-HCA). We apply our approach to analyze two real NIR datasets and four new Raman datasets. Compared with non-ESPs UMAP-HCA and t-distributed stochastic neighbor embedding combined with ESPs and HCA (ESPs-t-SNE-HCA), the developed strategy provides well-separated clusters for major and minor compounds in food matrix. Finally, the adulterants as minor compounds are accurately identified, which is confirmed by the fact that the extracted spectra of them perfectly match with their pure spectra. In addition, their locations are found in the contribution map even though they are present in a few pixels. What's more, the proposed strategy does not need any a priori knowledge of the data structure and the class memberships and therefore reduced the studied difficulty and confirmation bias in the analysis of big HSI datasets. Overall, the proposed ESPs-UMAP-HCA method could be a potential approach for food adulteration detection.

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

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 anR P 2 $\ R_P^2$ 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 anR P 2 $R_P^2$ 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.

Online System for Monitoring the Degree of Fermentation of Oolong Tea Using Integrated Visible-Near-Infrared Spectroscopy and Image-Processing Technologies

During the fermentation process of Oolong tea, significant changes occur in both its external characteristics and its internal components. This study aims to determine the fermentation degree of Oolong tea using visible-near-infrared spectroscopy (vis-VIS-NIR) and image processing. The preprocessed vis-VIS-NIR spectral data are fused with image features after sequential projection algorithm (SPA) feature selection. Subsequently, traditional machine learning and deep learning classification models are compared, with the support vector machine (SVM) and convolutional neural network (CNN) models yielding the highest prediction rates among traditional machine learning models and deep learning models with 97.14% and 95.15% in the prediction set, respectively. The results indicate that VIS-NIR combined with image processing possesses the capability for rapid non-destructive online determination of the fermentation degree of Oolong tea. Additionally, the predictive rate of traditional machine learning models exceeds that of deep learning models in this study. This study provides a theoretical basis for the fermentation of Oolong tea.

Application of imaging and spectroscopy techniques for grading of bovine embryos - a review

Although embryo transfers have grown considerably in the cattle industry, the selection of embryos required for successful pregnancies remains a challenging task. Visual inspection of 7th-day embryos using a stereomicroscope, followed by classification based on morphological features is the most commonly practiced procedure. However, there are inaccuracies and inconsistencies in the manual grading of bovine embryos. The objective of this review was to evaluate the potential of imaging and spectroscopic techniques in the selection of bovine embryos. Digital analysis of microscopic images through extracting visual features in the embryo region, and classification using machine learning methods have yielded about 88-96% success in pregnancies. The Raman spectral pattern provides valuable information regarding developmental stages and quality of the embryo. The Raman spectroscopy approach has also been successfully used to determine various parameters of bovine oocytes. Besides, Fourier Transform Infrared (FTIR) spectroscopy has the ability to assess embryo quality through analyzing embryo composition, including nucleic acid and amides present. Hyperspectral Imaging has also been used to characterize metabolite production during embryo growth. Although the time-lapse imaging approach is beneficial for morphokinetics evaluation of embryo development, optimized protocols are required for successful implementation in bovine embryo transfers. Most imaging and spectroscopic findings are still only at an experimental stage. Further research is warranted to improve the repeatability and practicality to implement in commercial facilities.

Detection of sweet corn seed viability based on hyperspectral imaging combined with firefly algorithm optimized deep learning

The identification of sweet corn seed vitality is an essential criterion for selecting high-quality varieties. In this research, a combination of hyperspectral imaging technique and diverse deep learning algorithms has been utilized to identify different vitality grades of sweet corn seeds. First, the hyperspectral data of 496 seeds, including four viability-grade seeds, are extracted and preprocessed. Then, support vector machine (SVM) and extreme learning machine (ELM) are used to construct the classification models. Finally, the one-dimensional convolutional neural networks (1DCNN), one-dimensional long short-term memory (1DLSTM), the CNN combined with the LSTM (CNN-LSTM), and the proposed firefly algorithm (FA) optimized CNN-LSTM (FA-CNN-LSTM) are utilized to distinguish spectral images of sweet corn seeds viability grade. The findings from the experimental analysis indicate that the deep learning models exhibit a significant advantage over traditional machine learning approaches in the discrimination of seed vitality levels, boasting a classification accuracy exceeding 94.26% in test datasets and achieving an accuracy improvement of at least 3% compared to the best-performing machine learning model. Moreover, the performance of the FA-CNN-LSTM model proposed in this study demonstrated a slight superiority over the other three models. Besides, the FA-CNN-LSTM achieved a classification accuracy of 97.23%, representing a significant improvement of 2.97% compared to the lowest-performing CNN and a 1.49% enhancement over the CNN-LSTM. In summary, this study reveals the potential of integrating deep learning with hyperspectral imaging as a promising alternative for discriminating sweet corn seed vitality grade, showcasing its value in agricultural research and cultivar breeding.

Non-destructive assessment of cannabis quality during drying process using hyperspectral imaging and machine learning

Cannabis sativa L. is an industrially valuable plant known for its cannabinoids, such as cannabidiol (CBD) and Δ9-tetrahydrocannabinol (THC), renowned for its therapeutic and psychoactive properties. Despite its significance, the cannabis industry has encountered difficulties in guaranteeing consistent product quality throughout the drying process. Hyperspectral imaging (HSI), combined with advanced machine learning technology, has been used to predict phytochemicals that presents a promising solution for maintaining cannabis quality control. We examined the dynamic changes in cannabinoid compositions under diverse drying conditions and developed a non-destructive method to appraise the quality of cannabis flowers using HSI and machine learning. Even when the relative weight and water content remained constant throughout the drying process, drying conditions significantly influenced the levels of CBD, THC, and their precursors. These results emphasize the importance of determining the exact drying endpoint. To develop HSI-based models for predicting cannabis quality indicators, including dryness, precursor conversion of CBD and THC, and CBD : THC ratio, we employed various spectral preprocessing methods and machine learning algorithms, including logistic regression (LR), support vector machine (SVM), k-nearest neighbor (KNN), random forest (RF), and Gaussian naïve Bayes (GNB). The LR model demonstrated the highest accuracy at 94.7-99.7% when used in conjunction with spectral pre-processing techniques such as multiplicative scatter correction (MSC) or Savitzky-Golay filter. We propose that the HSI-based model holds the potential to serve as a valuable tool for monitoring cannabinoid composition and determining optimal drying endpoint. This tool offers the means to achieve uniform cannabis quality and optimize the drying process in the industry.

Rapid quantitative authentication and analysis of camellia oil adulterated with edible oils by electronic nose and FTIR spectroscopy

Camellia oil, recognized as a high-quality edible oil endorsed by the Food and Agriculture Organization, is confronted with authenticity issues arising from fraudulent adulteration practices. These practices not only pose health risks but also lead to economic losses. This study proposes a novel machine learning framework, referred to as a transformer encoder backbone with a support vector machine regressor (TES), coupled with an electronic nose (E-nose), for detecting varying adulteration levels in camellia oil. Experimental results indicate that the proposed TES model exhibits the best performance in identifying the adulterated concentration of camellia oi, compared with five other machine learning models (the support vector machine, random forest, XGBoost, K-nearest neighbors, and backpropagation neural network). The results obtained by E-nose detection are verified by complementary Fourier transform infrared (FTIR) spectroscopy analysis for identifying functional groups, ensuring accuracy and providing a comprehensive assessment of the types of adulterants. The proposed TES model combined with E-nose offers a rapid, effective, and practical tool for detecting camellia oil adulteration. This technique not only safeguards consumer health and economic interests but also promotes the application of E-nose in market supervision.

Terahertz spectra reconstructed using convolutional denoising autoencoder for identification of rice grains infested with Sitophilus oryzae at different growth stages

Rice grains are often infected by Sitophilus oryzae due to improper storage, resulting in quality and quantity losses. The efficacy of terahertz time-domain spectroscopy (THz-TDS) technology in detecting Sitophilus oryzae at different stages of infestation in stored rice was employed in the current research. Terahertz (THz) spectra for rice grains infested by Sitophilus oryzae at different growth stages were acquired. Then, the convolutional denoising autoencoder (CDAE) was used to reconstruct THz spectra to reduce the noise-to-signal ratio. Finally, a random forest classification (RFC) model was developed to identify the infestation levels. Results showed that the RFC model based on the reconstructed second-order derivative spectrum with an accuracy of 84.78%, a specificity of 86.75%, a sensitivity of 86.36% and an F1-score of 85.87% performed better than the original first-order derivative THz spectrum with an accuracy of 89.13%, a specificity of 91.38%, a sensitivity of 88.18% and an F1-score of 89.16%. In addition, the convolutional layers inside the CDAE were visualized using feature maps to explain the improvement in results, illustrating that the CDAE can eliminate noise in the spectral data. Overall, THz spectra reconstructed with the CDAE provided a novel method for effective THz detection of infected grains.

Prediction of Soluble-Solid Content in Citrus Fruit Using Visible-Near-Infrared Hyperspectral Imaging Based on Effective-Wavelength Selection Algorithm

Citrus fruits were sorted based on external qualities, such as size, weight, and color, and internal qualities, such as soluble solid content (SSC), acidity, and firmness. Visible and near-infrared (VNIR) hyperspectral imaging techniques were used as rapid and nondestructive techniques for determining the internal quality of fruits. The applicability of the VNIR hyperspectral imaging technique for predicting the SSC in citrus fruits was evaluated in this study. A VNIR hyperspectral imaging system with a wavelength range of 400-1000 nm and 100 W light source was used to acquire hyperspectral images from citrus fruits in two orientations (i.e., stem and calyx ends). The SSC prediction model was developed using partial least-squares regression (PLSR). Spectrum preprocessing, effective wavelength selection through competitive adaptive reweighted sampling (CARS), and outlier detection were used to improve the model performance. The performance of each model was evaluated using the coefficient of determination (R2) and root mean square error (RMSE). In the present study, the PLSR model was developed using only a citrus cultivar. The SSC prediction CARS-PLSR model with outliers removed exhibited R2 and RMSE values of approximatively 0.75 and 0.56 °Brix, respectively. The results of this study are expected to be useful in similar fields such as agricultural and food post-harvest management, as well as in the development of an online system for determining the SSC of citrus fruits.

A review of machine learning applications in life cycle assessment studies

Life Cycle Assessment (LCA) is a foundational method for quantitative assessment of sustainability. Increasing data availability and rapid development of machine learning (ML) approaches offer new opportunities to advance LCA. Here, we review current progress and knowledge gaps in applying ML techniques to support LCA, and identify future research directions for LCAs to better harness the power of ML. This review analyzes forty studies reporting quantitative assessment with a combination of LCA and ML methods. We found that ML approaches have been used for generating life cycle inventories, computing characterization factors, estimating life cycle impacts, and supporting life cycle interpretation. Most of the reviewed studies employed a single ML method, with artificial neural networks (ANNs) as the most frequently applied approach. Both supervised and unsupervised ML techniques were used in LCA studies. For studies using supervised ML, training datasets were derived from diverse sources, such as literature, lab experiments, existing databases, and model simulations. Over 70 % of these reviewed studies trained ML models with less than 1500 sample datasets. Although these reviewed studies showed that ML approaches help improve prediction accuracy, pattern discovery and computational efficiency, multiple areas deserve further research. First, continuous data collection and compilation is needed to support more reliable ML and LCA modeling. Second, future studies should report sufficient details regarding the selection criteria for ML models and present model uncertainty analysis. Third, incorporating deep learning models into LCA holds promise to further improve life cycle inventory and impact assessment. Finally, the complexity of current environmental challenges calls for interdisciplinary collaborative research to achieve deep integration of ML into LCA to support sustainable development.

Non-Destructive Assessment of Microstructural Changes in Kabuli Chickpeas during Storage

The potential of hyperspectral imaging (HSI) and synchrotron phase-contrast micro computed tomography (SR-µCT) was evaluated to determine changes in chickpea quality during storage. Chickpea samples were stored for 16 wk at different combinations of moisture contents (MC of 9%, 11%, 13%, and 15% wet basis) and temperatures (10 °C, 20 °C, and 30 °C). Hyperspectral imaging was utilized to investigate the overall quality deterioration, and SR-µCT was used to study the microstructural changes during storage. Principal component analysis (PCA) and Partial Least Squares Discriminant Analysis (PLS-DA) were used as multivariate data analysis approaches for HSI data. Principal component analysis successfully grouped the samples based on relative humidity (RH) and storage temperatures, and the PLS-DA classification also resulted in reliable accuracy (between 80 and 99%) for RH-based and temperature-based classification. The SR-µCT results revealed that microstructural changes in kernels (9% and 15% MC) were dominant at higher temperatures (above 20 °C) as compared to lower temperatures (10 °C) during storage due to accelerated spoilage at higher temperatures (above 20 °C). Chickpeas which had internal irregularities like cracked endosperm and air spaces before storage were spoiled at lower moisture from 8 wk of storage.

Combining Feature Selection Techniques and Neurofuzzy Systems for the Prediction of Total Viable Counts in Beef Fillets Using Multispectral Imaging

In the food industry, quality and safety issues are associated with consumers' health condition. There is a growing interest in applying various noninvasive sensorial techniques to obtain quickly quality attributes. One of them, hyperspectral/multispectral imaging technique has been extensively used for inspection of various food products. In this paper, a stacking-based ensemble prediction system has been developed for the prediction of total viable counts of microorganisms in beef fillet samples, an essential cause to meat spoilage, utilizing multispectral imaging information. As the selection of important wavelengths from the multispectral imaging system is considered as an essential stage to the prediction scheme, a features fusion approach has been also explored, by combining wavelengths extracted from various feature selection techniques. Ensemble sub-components include two advanced clustering-based neuro-fuzzy network prediction models, one utilizing information from average reflectance values, while the other one from the standard deviation of the pixels' intensity per wavelength. The performances of neurofuzzy models were compared against established regression algorithms such as multilayer perceptron, support vector machines and partial least squares. Obtained results confirmed the validity of the proposed hypothesis to utilize a combination of feature selection methods with neurofuzzy models in order to assess the microbiological quality of meat products.

Assessment of hyperspectral imaging and CycleGAN-simulated narrowband techniques to detect early esophageal cancer

The clinical signs and symptoms of esophageal cancer (EC) are often not discernible until the intermediate or advanced phases. The detection of EC in advanced stages significantly decreases the survival rate to below 20%. This study conducts a comparative analysis of the efficacy of several imaging techniques, including white light image (WLI), narrowband imaging (NBI), cycle-consistent adversarial network simulated narrowband image (CNBI), and hyperspectral imaging simulated narrowband image (HNBI), in the early detection of esophageal cancer (EC). In conjunction with Kaohsiung Armed Forces General Hospital, a dataset consisting of 1000 EC pictures was used, including 500 images captured using WLI and 500 images captured using NBI. The CycleGAN model was used to generate the CNBI dataset. Additionally, a novel method for HSI imaging was created with the objective of generating HNBI pictures. The evaluation of the efficacy of these four picture types in early detection of EC was conducted using three indicators: CIEDE2000, entropy, and the structural similarity index measure (SSIM). Results of the CIEDE2000, entropy, and SSIM analyses suggest that using CycleGAN to generate CNBI images and HSI model for creating HNBI images is superior in detecting early esophageal cancer compared to the use of conventional WLI and NBI techniques.

Non-destructive prediction of isoflavone and starch by hyperspectral imaging and deep learning in Puerariae Thomsonii Radix

Accurate assessment of isoflavone and starch content in Puerariae Thomsonii Radix (PTR) is crucial for ensuring its quality. However, conventional measurement methods often suffer from time-consuming and labor-intensive procedures. In this study, we propose an innovative and efficient approach that harnesses hyperspectral imaging (HSI) technology and deep learning (DL) to predict the content of isoflavones (puerarin, puerarin apioside, daidzin, daidzein) and starch in PTR. Specifically, we develop a one-dimensional convolutional neural network (1DCNN) model and compare its predictive performance with traditional methods, including partial least squares regression (PLSR), support vector regression (SVR), and CatBoost. To optimize the prediction process, we employ various spectral preprocessing techniques and wavelength selection algorithms. Experimental results unequivocally demonstrate the superior performance of the DL model, achieving exceptional performance with mean coefficient of determination (R2) values surpassing 0.9 for all components. This research underscores the potential of integrating HSI technology with DL methods, thereby establishing the feasibility of HSI as an efficient and non-destructive tool for predicting the content of isoflavones and starch in PTR. Moreover, this methodology holds great promise for enhancing efficiency in quality control within the food industry.

Detection of Red Pepper Powder Adulteration with Allura Red and Red Pepper Seeds Using Hyperspectral Imaging

This study used shortwave infrared (SWIR) technology to determine whether red pepper powder was artificially adulterated with Allura Red and red pepper seeds. First, the ratio of red pepper pericarp to seed was adjusted to 100:0 (P100), 75:25 (P75), 50:50 (P50), 25:75 (P25), or 0:100 (P0), and Allura Red was added to the red pepper pericarp/seed mixture at 0.05% (A), 0.1% (B), and 0.15% (C). The results of principal component analysis (PCA) using the L, a, and b values; hue angle; and chroma showed that the pure pericarp powder (P100) was not easily distinguished from some adulterated samples (P50A-C, P75A-C, and P100B,C). Adulterated red pepper powder was detected by applying machine learning techniques, including linear discriminant analysis (LDA), linear support vector machine (LSVM), and k-nearest neighbor (KNN), based on spectra obtained from SWIR (1,000-1,700 nm). Linear discriminant analysis determined adulteration with 100% accuracy when the samples were divided into four categories (acceptable, adulterated by Allura Red, adulterated by seeds, and adulterated by seeds and Allura Red). The application of SWIR technology and machine learning detects adulteration with Allura Red and seeds in red pepper powder.

MFBP-UNet: A Network for Pear Leaf Disease Segmentation in Natural Agricultural Environments

The accurate prevention and control of pear tree diseases, especially the precise segmentation of leaf diseases, poses a serious challenge to fruit farmers globally. Given the possibility of disease areas being minute with ambiguous boundaries, accurate segmentation becomes difficult. In this study, we propose a pear leaf disease segmentation model named MFBP-UNet. It is based on the UNet network architecture and integrates a Multi-scale Feature Extraction (MFE) module and a Tokenized Multilayer Perceptron (BATok-MLP) module with dynamic sparse attention. The MFE enhances the extraction of detail and semantic features, while the BATok-MLP successfully fuses regional and global attention, striking an effective balance in the extraction capabilities of both global and local information. Additionally, we pioneered the use of a diffusion model for data augmentation. By integrating and analyzing different augmentation methods, we further improved the model's training accuracy and robustness. Experimental results reveal that, compared to other segmentation networks, MFBP-UNet shows a significant improvement across all performance metrics. Specifically, MFBP-UNet achieves scores of 86.15%, 93.53%, 90.89%, and 0.922 on MIoU, MP, MPA, and Dice metrics, marking respective improvements of 5.75%, 5.79%, 1.08%, and 0.074 over the UNet model. These results demonstrate the MFBP-UNet model's superior performance and generalization capabilities in pear leaf disease segmentation and its inherent potential to address analogous challenges in natural environment segmentation tasks.

Phage Endolysins: Advances in the World of Food Safety

As antimicrobial resistance continues to escalate, the exploration of alternative approaches to safeguard food safety becomes more crucial than ever. Phage endolysins are enzymes derived from phages that possess the ability to break down bacterial cell walls. They have emerged as promising antibacterial agents suitable for integration into food processing systems. Their application as food preservatives can effectively regulate pathogens, thus contributing to an overall improvement in food safety. This review summarizes the latest techniques considering endolysins' potential for food safety. These techniques include native and engineered endolysins for controlling bacterial contamination at different points within the food production chain. However, we find that characterizing endolysins through in vitro methods proves to be time consuming and resource intensive. Alternatively, the emergence of advanced high-throughput sequencing technology necessitates the creation of a robust computational framework to efficiently characterize recently identified endolysins, paving the way for future research. Machine learning encompasses potent tools capable of analyzing intricate datasets and pattern recognition. This study briefly reviewed the use of these industry 4.0 technologies for advancing the research in food industry. We aimed to provide current status of endolysins in food industry and new insights by implementing these industry 4.0 strategies revolutionizes endolysin development. It will enhance food safety, customization, efficiency, transparency, and collaboration while reducing regulatory hurdles and ensuring timely product availability.

TinyML-Sensor for Shelf Life Estimation of Fresh Date Fruits

Fresh dates have a limited shelf life and are susceptible to spoilage, which can lead to economic losses for producers and suppliers. The problem of accurate shelf life estimation for fresh dates is essential for various stakeholders involved in the production, supply, and consumption of dates. Modified atmosphere packaging (MAP) is one of the essential methods that improves the quality and increases the shelf life of fresh dates by reducing the rate of ripening. Therefore, this study aims to apply fast and cost-effective non-destructive techniques based on machine learning (ML) to predict and estimate the shelf life of stored fresh date fruits under different conditions. Predicting and estimating the shelf life of stored date fruits is essential for scheduling them for consumption at the right time in the supply chain to benefit from the nutritional advantages of fresh dates. The study observed the physicochemical attributes of fresh date fruits, including moisture content, total soluble solids, sugar content, tannin content, pH, and firmness, during storage in a vacuum and MAP at 5 and 24 ∘C every 7 days to determine the shelf life using a non-destructive approach. TinyML-compatible regression models were employed to predict the stages of fruit development during the storage period. The decrease in the shelf life of the fruits begins when they transition from the Khalal stage to the Rutab stage, and the shelf life ends when they start to spoil or ripen to the Tamr stage. Low-cost Visible-Near-Infrared (VisNIR) spectral sensors (AS7265x-multi-spectral) were used to capture the internal physicochemical attributes of the fresh fruit. Regression models were employed for shelf life estimation. The findings indicated that vacuum and modified atmosphere packaging with 20% CO2 and N balance efficiently increased the shelf life of the stored fresh fruit to 53 days and 44 days, respectively, when maintained at 5 ∘C. However, the shelf life decreased to 44 and 23 days when the vacuum and modified atmosphere packaging with 20% CO2 and N balance were maintained at room temperature (24 ∘C). Edge Impulse supports the training and deployment of models on low-cost microcontrollers, which can be used to predict real-time estimations of the shelf life of fresh dates using TinyML sensors.

Machine Learning Approaches for Predicting Fatty Acid Classes in Popular US Snacks Using NHANES Data

In the US, people frequently snack between meals, consuming calorie-dense foods including baked goods (cakes), sweets, and desserts (ice cream) high in lipids, salt, and sugar. Monounsaturated fatty acid (MUFA) and polyunsaturated fatty acid (PUFA) are reasonably healthy; however, excessive consumption of food high in saturated fatty acid (SFA) has been related to an elevated risk of cardiovascular diseases. The National Health and Nutrition Survey (NHANES) uses a 24 h recall to collect information on people's food habits in the US. The complexity of the NHANES data necessitates using machine learning (ML) methods, a branch of data science that uses algorithms to collect large, unstructured, and structured data sets and identify correlations between the data variables. This study focused on determining the ability of ML regression models including artificial neural networks (ANNs), decision trees (DTs), k-nearest neighbors (KNNs), and support vector machines (SVMs) to assess the variability in total fat content concerning the classes (SFA, MUFA, and PUFA) of US-consumed snacks between 2017 and 2018. KNNs and DTs predicted SFA, MUFA, and PUFA with mean squared error (MSE) of 0.707, 0.489, 0.612, and 1.172, 0.846, 0.738, respectively. SVMs failed to predict the fatty acids accurately; however, ANNs performed satisfactorily. Using ensemble methods, DTs (10.635, 5.120, 7.075) showed higher error values for MSE than linear regression (LiR) (9.086, 3.698, 5.820) for SFA, MUFA, and PUFA prediction, respectively. R2 score ranged between -0.541 to 0.983 and 0.390 to 0.751 for models one and two, respectively. Extreme gradient boost (XGR), Light gradient boost (LightGBM), and random forest (RF) performed better than LiR, with RF having the lowest score for MSE in predicting all the fatty acid classes.

SY-Net: A Rice Seed Instance Segmentation Method Based on a Six-Layer Feature Fusion Network and a Parallel Prediction Head Structure

During the rice quality testing process, the precise segmentation and extraction of grain pixels is a key technique for accurately determining the quality of each seed. Due to the similar physical characteristics, small particles and dense distributions of rice seeds, properly analysing rice is a difficult problem in the field of target segmentation. In this paper, a network called SY-net, which consists of a feature extractor module, a feature pyramid fusion module, a prediction head module and a prototype mask generation module, is proposed for rice seed instance segmentation. In the feature extraction module, a transformer backbone is used to improve the ability of the network to learn rice seed features; in the pyramid fusion module and the prediction head module, a six-layer feature fusion network and a parallel prediction head structure are employed to enhance the utilization of feature information; and in the prototype mask generation module, a large feature map is used to generate high-quality masks. Training and testing were performed on two public datasets and one private rice seed dataset. The results showed that SY-net achieved a mean average precision (mAP) of 90.71% for the private rice seed dataset and an average precision (AP) of 16.5% with small targets in COCO2017. The network improved the efficiency of rice seed segmentation and showed excellent application prospects in performing rice seed quality testing.

Tracing the origin of Taiping Houkui green tea using 1H NMR and HS-SPME-GC-MS chemical fingerprints, data fusion and chemometrics

The narrow geographical traceability of green tea is both important and challenging. This study aimed to establish multi-technology metabolomic and chemometric approaches to finely discriminate the geographic origins of green teas. Taiping Houkui green tea samples were analyzed by headspace solid-phase microextraction coupled with gas chromatography-mass spectrometry and ¹H NMR of polar (D₂O) and non-polar (CDCl₃). Common dimension, low-level and mid-level data fusion approaches were tested to verify if the combination of several analytical sources can improve the classification ability of samples from different origins. In assessments of tea from six origins, the single instrument data test set results in 40.00% to 80.00% accuracy. Data fusion improved single-instrument performance classification with mid-level data fusion to obtain 93.33% accuracy in the test set. These results provide comprehensive metabolomic insights into the origin of TPHK fingerprinting and open up new metabolomic approaches for quality control in the tea industry.

Non-destructive pre-symptomatic detection of gray mold infection in kiwifruit using hyperspectral data and chemometrics

Application of hyperspectral imaging (HSI) and data analysis algorithms was investigated for early and non-destructive detection of Botrytis cinerea infection. Hyperspectral images were collected from laboratory-based contaminated and non-contaminated fruits at different day intervals. The spectral wavelengths of 450 nm to 900 nm were pretreated by applying moving window smoothing (MWS), standard normal variates (SNV), multiplicative scatter correction (MSC), Savitzky-Golay 1^st derivative, and Savitzky-Golay 2^nd derivative algorithms. In addition, three different wavelength selection algorithms, namely; competitive adaptive reweighted sampling (CARS), uninformative variable elimination (UVE), and successive projection algorithm (SPA), were executed on the spectra to invoke the most informative wavelengths. The linear discriminant analysis (LDA), developed with SNV-filtered spectral data, was the most accurate classifier to differentiate the contaminated and non-contaminated kiwifruits with accuracies of 96.67% and 96.00% in the cross-validation and evaluation stages, respectively. The system was able to detect infected samples before the appearance of disease symptoms. Results also showed that the gray-mold infection significantly influenced the kiwifruits' firmness, soluble solid content (SSC), and titratable acidity (TA) attributes. Moreover, the Savitzky-Golay 1^st derivative-CARS-PLSR model obtained the highest prediction rate for kiwifruit firmness, SSC, and TA with the determination coefficient (R²) values of 0.9879, 0.9644, 0.9797, respectively, in calibration stage. The corresponding cross-validation R² values were equal to 0.9722, 0.9317, 0.9500 for firmness, SSC, and TA, respectively. HSI and chemometric analysis demonstrated a high potential for rapid and non-destructive assessments of fungal-infected kiwifruits during storage.

Identification of geographical origins of Radix Paeoniae Alba using hyperspectral imaging with deep learning-based fusion approaches

The Radix Paeoniae Alba (Baishao) is a traditional Chinese medicine (TCM) with numerous clinical and nutritional benefits. Rapid and accurate identification of the geographical origins of Baishao is crucial for planters, traders and consumers. Hyperspectral imaging (HSI) was used in this study to acquire spectral images of Baishao samples from its two sides. Convolutional neural network (CNN) and attention mechanism was used to distinguish the origins of Baishao using spectra extracted from one side. The data-level and feature-level deep fusion models were proposed using information from both sides of the samples. CNN models outperformed the conventional machine learning methods in classifying Baishao origins. The generalized Gradient-weighted Class Activation Mapping (Grad-CAM++) was utilized to visualize and identify important wavelengths that significantly contribute to model performance. The overall results illustrated that HSI combined with deep learning strategies was effective in identifying the geographical origins of Baishao, having good prospects of real-world applications.

Interpretable machine learning assisted spectroscopy for fast characterization of biomass and waste

The combination of machine learning and infrared spectroscopy was reported as effective for fast characterization of biomass and waste (BW). However, this characterization process is lack of interpretability towards its chemical insights, leading to less satisfactory recognition for its reliability. Accordingly, this paper aimed to explore the chemical insights of the machine learning models in the fast characterization process. A novel dimensional reduction method with significant physicochemical meanings was thus proposed, where the high loading spectral peaks of BW were selected as input features. Combined with functional groups attribution of these spectral peaks, the machine learning models established based on the dimensionally reduced spectral data could be explained with clear chemical insights. The performance of classification and regression models between the proposed dimensional reduction method and principal component analysis method was compared. The influence mechanism of each functional group on the characterization results were discussed. CH deformation, CC stretch & CO stretch and ketone/aldehyde CO stretch played essential roles in C, H/ LHV and O prediction, respectively. The results of this work demonstrated the theoretical fundamentals of the machine learning and spectroscopy based BW fast characterization method.

Recognition of Abnormal-Laying Hens Based on Fast Continuous Wavelet and Deep Learning Using Hyperspectral Images

The egg production of laying hens is crucial to breeding enterprises in the laying hen breeding industry. However, there is currently no systematic or accurate method to identify low-egg-production-laying hens in commercial farms, and the majority of these hens are identified by breeders based on their experience. In order to address this issue, we propose a method that is widely applicable and highly precise. First, breeders themselves separate low-egg-production-laying hens and normal-laying hens. Then, under a halogen lamp, hyperspectral images of the two different types of hens are captured via hyperspectral imaging equipment. The vertex component analysis (VCA) algorithm is used to extract the cockscomb end member spectrum to obtain the cockscomb spectral feature curves of low-egg-production-laying hens and normal ones. Next, fast continuous wavelet transform (FCWT) is employed to analyze the data of the feature curves in order to obtain the two-dimensional spectral feature image dataset. Finally, referring to the two-dimensional spectral image dataset of the low-egg-production-laying hens and normal ones, we developed a deep learning model based on a convolutional neural network (CNN). When we tested the model's accuracy by using the prepared dataset, we found that it was 0.975 percent accurate. This outcome demonstrates our identification method, which combines hyperspectral imaging technology, an FCWT data analysis method, and a CNN deep learning model, and is highly effective and precise in laying-hen breeding plants. Furthermore, the attempt to use FCWT for the analysis and processing of hyperspectral data will have a significant impact on the research and application of hyperspectral technology in other fields due to its high efficiency and resolution characteristics for data signal analysis and processing.

Mycotoxin risk management in maize gluten meal

Maize gluten meal (MGM) is a by-product of maize starch and ethanol, produced by the wet milling process. Its high protein content makes it a preferred ingredient in feed. Given the high prevalence of mycotoxins in maize globally, they pose a significant challenge to use of MGM for feed: wet milling could concentrate certain mycotoxins in gluten components, and mycotoxin consumption affects animal health and can contaminate animal-source foods. To help confront this issue, this paper summarizes mycotoxin occurrence in maize, distribution during MGM production and mycotoxin risk management strategies for MGM through a comprehensive literature review. Available data emphasize the importance of mycotoxin control in MGM and the necessity of a systematic control approach, which includes: good agriculture practices (GAP) in the context of climate change, degradation of mycotoxin during MGM processing with SO2 and lactic acid bacteria (LAB) and the prospect of removing or detoxifying mycotoxins using emerging technologies. In the absence of mycotoxin contamination, MGM represents a safe and economically critical component of global animal feed. With a holistic risk assessment-based, seed-to-MGM-feed systematic approach to reducing and decontaminating mycotoxins in maize, costs and negative health impacts associated with MGM use in feed can be effectively reduced.

Artificial Intelligence in Food Safety: A Decade Review and Bibliometric Analysis

Artificial Intelligence (AI) technologies have been powerful solutions used to improve food yield, quality, and nutrition, increase safety and traceability while decreasing resource consumption, and eliminate food waste. Compared with several qualitative reviews on AI in food safety, we conducted an in-depth quantitative and systematic review based on the Core Collection database of WoS (Web of Science). To discover the historical trajectory and identify future trends, we analysed the literature concerning AI technologies in food safety from 2012 to 2022 by CiteSpace. In this review, we used bibliometric methods to describe the development of AI in food safety, including performance analysis, science mapping, and network analysis by CiteSpace. Among the 1855 selected articles, China and the United States contributed the most literature, and the Chinese Academy of Sciences released the largest number of relevant articles. Among all the journals in this field, PLoS ONE and Computers and Electronics in Agriculture ranked first and second in terms of annual publications and co-citation frequency. The present character, hot spots, and future research trends of AI technologies in food safety research were determined. Furthermore, based on our analyses, we provide researchers, practitioners, and policymakers with the big picture of research on AI in food safety across the whole process, from precision agriculture to precision nutrition, through 28 enlightening articles.

Applications of imaging systems for the assessment of quality characteristics of bread and other baked goods: A review

One of the most widely researched topics in the food industry is bread quality analysis. Different techniques have been developed to assess the quality characteristics of bakery products. However, in the last few decades, the advancement in sensor and computational technologies has increased the use of computer vision to analyze food quality (e.g., bakery products). Despite a large number of publications on the application of imaging methods in the bakery industry, comprehensive reviews detailing the use of conventional analytical techniques and imaging methods for the quality analysis of baked goods are limited. Therefore, this review aims to critically analyze the conventional methods and explore the potential of imaging techniques for the quality assessment of baked products. This review provides an in-depth assessment of the different conventional techniques used for the quality analysis of baked goods which include methods to record the physical characteristics of bread and analyze its quality, sensory-based methods, nutritional-based methods, and the use of dough rheological data for end-product quality prediction. Furthermore, an overview of the image processing stages is presented herein. We also discuss, comprehensively, the applications of imaging techniques for assessing the quality of bread and other baked goods. These applications include studying and predicting baked goods' quality characteristics (color, texture, size, and shape) and classifying them based on these features. The limitations of both conventional techniques (e.g., destructive, laborious, error-prone, and expensive) and imaging methods (e.g., illumination, humidity, and noise) and the future direction of the use of imaging methods for quality analysis of bakery products are discussed.