Detection of Pesticide Residue Level in Grape Using Hyperspectral Imaging with Machine Learning

Machine learning: An effective tool for monitoring and ensuring food safety, quality, and nutrition

The domains of food safety, quality, and nutrition are inundated with complex datasets. Machine learning (ML) has emerged as a powerful tool in food science, offering fast, accessible, and effective solutions compared with conventional methods. This review outlines the applications of ML in safeguarding food safety, enhancing quality, and unraveling nutrition intricacies. The review encompasses the prediction of food contaminants, classification of food grades, detection of adulterants, and analysis of food nutrients and their correlations with nutritional diseases. Additionally, ML methods are highlighted to elucidate the relationships between gut microbiota, dietary patterns, and disease pathology, thereby positioning gut microbiota as potential biomarkers for disease intervention through dietary regulation. This study provides a valuable reference for future research on applications of ML to the field of food science.

Machine learning-integrated surface-enhanced Raman spectroscopy analysis of multicomponent dye mixtures

Surface-enhanced Raman spectroscopy (SERS) is broadly used in the detection and analysis of materials with its fingerprint-like specificity and high sensitivity. However, resembling signals of analytes highly affect the identification and assignment of spectra, which has become a long-term issue to be solved. In this study, various models of machine learning are utilized and compared to support data analysis of complex SERS spectra. Silver-coated gold core-shell nanocubes (Au@AgNCs) are optimized as SERS substrates for the detection of four common dyes - methylene blue (MB), crystal violet (CV), rhodamine B (RhB) and malachite green (MG). Independent principal component analysis (ICA) was utilized to isolate the signals from the SERS spectra of the dye mixtures, and the isolated signals were further classified by commonly used classification models including K Nearest Neighbors (KNN), Support Vector Machines (SVM), Random Forests (RF), and Convolutional Neural Networks (CNN). The results show that the CNN model achieved an accuracy of 98% in the classification of single dyes and an accuracy of 97% in the classification of dye mixtures, which is significantly better than other models. Based on these findings, we propose ICA combined with CNN-assisted SERS spectroscopy as an effective analytical tool for analyzing dye mixtures.

Progress in machine learning-supported electronic nose and hyperspectral imaging technologies for food safety assessment: A review

The growing concern over food safety, driven by threats such as food contaminations and adulterations has prompted the adoption of advanced technologies like electronic nose (e-nose) and hyperspectral imaging (HSI), which are increasingly enhanced by machine learning innovations. This paper aims to provide a comprehensive review on food safety, by combining insights from both e-nose and HSI technologies alongside machine learning algorithms. First, the basic principles of e-nose, HSI, and machine learning, with particular emphasis on artificial neural network (ANN) and deep learning (DL) are briefly discussed. The review then examines how machine learning enhances the performance of e-nose and HSI, followed by an exploration of recent applications in detecting food hazards, including drug residues, microbial contaminants, pesticide residues, toxins, and adulterants. Subsequently, key limitations encountered in the applications of machine learning, e-nose and HSI, along with future perspectives on the potential advancements of these technologies are highlighted. E-nose and HSI technologies have shown their great potential for applications in food safety assessment through machine learning assistance. Despite this, their use is primarily limited to laboratory environments, restricting their real-world applications. Additionally, the lack of standardized protocols hampers their acceptance and the reproducibility of tests in food safety assessments. Thus, further research is essential to address these limitations and enhance the effectiveness of e-nose and HSI technologies in practical applications. Ultimately, this paper offers a detailed understanding of both technologies, highlighting the pivotal role of machine learning and presenting insights into their innovative applications within food safety evaluation.

Unraveling the complexity of organophosphorus pesticides: Ecological risks, biochemical pathways and the promise of machine learning

Organophosphorus pesticides (OPPs) are widely used in agriculture but pose significant ecological and human health risks due to their persistence and toxicity in the environment. While microbial degradation offers a promising solution, gaps remain in understanding the enzymatic mechanisms, degradation pathways, and ecological impacts of OPP transformation products. This review aims to bridge these gaps by integrating traditional microbial degradation research with emerging machine learning (ML) technologies. We hypothesize that ML can enhance OPP degradation studies by improving the efficiency of enzyme discovery, pathway prediction, and ecological risk assessment. Through a comprehensive analysis of microbial degradation mechanisms, environmental factors, and ML applications, we propose a novel framework that combines biochemical insights with data-driven approaches. Our review highlights the potential of ML to optimize microbial strain screening, predict degradation pathways, and identify key active sites, offering innovative strategies for sustainable pesticide management. By integrating traditional research with cutting-edge ML technologies, this work contributes to the journal's scope by promoting eco-friendly solutions for environmental protection and pesticide pollution control.

A pesticide residue detection model for food based on NIR and SERS

This paper presents a multivariate calibration model based on Near Infrared Spectroscopy (NIR) and Surface Enhanced Raman Spectroscopy (SERS) techniques, aiming to achieve efficient and accurate detection of pesticide residues in food by integrating the spectral information from both techniques. The study utilizes the Hilbert-Schmidt Independence Criterion-based Variable Space Iterative Optimization algorithm (HSIC-VSIO) for feature variable selection, and combines it with Partial Least Squares Regression (PLSR) to build a spectral fusion quantitative model. Experimental results show that the calibration set Root Mean Square Error (RMSE1) of the NIR and SERS feature-layer fusion model is 0.160, the prediction set RMSE (RMSE2) is 0.185, the prediction set coefficient of determination (R²) is 0.988, and the Relative Percent Deviation (RPD) is 8.290. Compared to single spectral techniques, the NIR and SERS spectral feature-layer fusion method demonstrates significant superiority in detecting pesticide residues in complex matrix samples. The findings further validate the high sensitivity of SERS technology in detecting low concentrations of pesticides and show that the feature-layer fusion method effectively suppresses matrix interference, enhancing the model's generalization ability. This study provides a reliable tool for the rapid and accurate detection of pesticide residues in food and offers new insights into the application of spectral analysis technologies in the food safety field.

Rapid pesticide residues detection by portable filter-array hyperspectral imaging

The detection of pesticide residues in agricultural products is crucial for ensuring food safety. However, traditional methods are often constrained by slow processing speeds and a restricted analytical scope. This study presents a novel method that uses filter-array-based hyperspectral imaging enhanced by a dynamic filtering demosaicking algorithm, which significantly improves the speed and accuracy of detecting pesticide residues. Our approach enhances the spatial and spectral resolution of hyperspectral images, thereby providing a rapid and cost-effective alternative to conventional methods with an image integration time of 20 ms. Tested on both synthetic datasets and real agricultural samples, this technology demonstrates superior performance under high noise conditions and exceptional precision in spectral reconstruction at critical color edges. The practicality of this system is demonstrated by integrating a hyperspectral microfilter array with a smartphone's imaging sensor, thereby showcasing the feasibility of deploying this advanced detection technology in everyday portable devices for quick and convenient monitoring of pesticide residues.

Machine learning for predicting the prognosis of patients with thymoma and thymic carcinoma

Background

Thymoma and thymic carcinoma are the most common tumors of the anterior mediastinum. However, there are little research on applying machine learning (ML) approaches to the prognostic prediction of thymoma and thymic carcinoma. The study aims to develop predictive models utilizing ML techniques to accurately forecast the 5-year survival of patients with thymoma and thymic carcinoma.

Methods

Patients with malignant thymic neoplasms were identified in the Surveillance, Epidemiology, and End Results (SEER) 17 database, and their demographic and clinicopathological characteristics were collected. ML classifiers, including elastic net regularized logistic regression, random forest (RF), non-linear support vector machine (SVM), extreme gradient boosting (XGBoost) machine, and categorical boosting (CatBoost) were trained. The hyper-parameter of the algorithms was optimized by a grid search with five repeats of 10-fold cross-validation. Ensemble models were built based on the three algorithms with the highest area under the receiver operator characteristic (ROC) curve (AUC) in the validation set. The best model among the single models and ensemble model was selected as the final model. Calibration curve and decision curve were adopted to evaluate the calibration performance and clinical utility. For comparison, we constructed a baseline model consisting of age and Masaoka stages using logistic regression.

Results

After data cleaning, 1,363 patients and 841 patients were included in the overall survival (OS) dataset and disease-specific survival (DSS) dataset, respectively. CatBoost [AUC: 0.755; 95% confidence interval (CI): 0.698-0.811] had the best performance in the OS prediction for the original dataset. The ensemble model achieved the highest prognostic efficiency for the original dataset, with an AUC of 0.833 (95% CI: 0.765-0.901). Calibration showed favorable goodness of fit and was further verified with the Hosmer-Lemeshow test (CatBoost: χ2=12.63, P=0.13; ensemble model: χ2=7.61, P=0.47). The decision curve showed that the final model provided a high net benefit. The model could significantly distinguish the prognosis of patients (all P values <0.001). Finally, World Health Organization (WHO) histological classification, Masaoka stage, and age were the variables that significantly contributed to the models' prediction of OS and DSS.

Conclusions

We trained ML-based predictive models that could accurately predict the 5-year OS and DSS of patients with thymoma and thymic carcinoma.

Non-destructive analysis of Ganoderma lucidum composition using hyperspectral imaging and machine learning

Background

Ganoderma lucidum is a widely used medicinal fungus whose quality is influenced by various factors, making traditional chemical detection methods complex and economically challenging. This study addresses the need for fast, noninvasive testing methods by combining hyperspectral imaging with machine learning to predict polysaccharide and ergosterol levels in Ganoderma lucidum cap and powder.

Methods

Hyperspectral images in the visible near-infrared (385-1009 nm) and short-wave infrared (899-1695 nm) ranges were collected, with ergosterol measured by high-performance liquid chromatography and polysaccharides assessed via the phenol-sulfuric acid method. Three machine learning models-a feedforward neural network, an extreme learning machine, and a decision tree-were tested.

Results

Notably, the extreme learning machine model, optimized by a genetic algorithm with voting, provided superior predictions, achieving R 2 values of 0.96 and 0.97 for polysaccharides and ergosterol, respectively.

Conclusion

This integration of hyperspectral imaging and machine learning offers a novel, nondestructive approach to assessing Ganoderma lucidum quality.

A green and efficient method for detecting nicosulfuron residues in field maize using hyperspectral imaging and deep learning

Accurate and rapid detection of nicosulfuron herbicide residues in field-grown maize is essential for implementing chemical remediation and optimizing spraying strategies. However, current detection methods are costly and time-consuming. This study analyzed residue levels in six maize varieties-both resistant and sensitive types-under two herbicide concentrations, categorizing residues into low, medium, and high levels. We developed the HerbiResNet model to predict and classify herbicide residues in maize leaves using spectral data. The model achieved a coefficient of determination (R²) of 0.88 for residue prediction and an accuracy of 0.87 for residue level classification on the test set, significantly outperforming traditional regression models (SVR, PLSR) and classical neural networks (MLP, AlexNet). Additionally, we explored combining spectral technology with deep learning, revealing strong correlations between specific spectral bands (around 550 nm, 680 nm, 750 nm, and 1000 nm) and herbicide residues as well as physiological changes in maize. This provides a solid theoretical foundation for the broader application of spectral technology in agriculture. Overall, the HerbiResNet model demonstrates substantial potential for precision agriculture and sustainable agricultural practices.

Unravelling patterns of food tolerance to pesticide residues via non-negative matrix factorization

Gaining knowledge about the maximum residue limits (MALs) of pesticides on fresh or processed foods is critical to the process of pre-harvest cultivation, post-harvest processing and storage, and the downstream safety surveillance of food commodities. In this study, we explore the available MALs of 643 pesticides on 128 foods via non-negative matrix factorization (NMF) and hierarchical clustering to gain insights into the patterns of how similar pesticides exhibit similar MALs profiles on foods. Meanwhile, NMF predicts the MALs for untested foods via the implicitly-learnt patterns without conducting in vivo testing that potentially violates ethic regulations. Clustering results show that foods with closer NMF weights commonly exhibit closer residue tolerance profiles, and pesticides with closer MALs profiles exhibit higher structural similarities. These patterns help food experts to assess the MALs of pesticides concerned on untested foods, and the determination of MRLs on foods has its mechanistic basis. Using the reverse process of NMF decomposition, we provide the predicted MALs for 24.31% pesticide-food pairs, and NMF achieves 0.9 R2 on more than 75.78% foods in terms of recreating the experimental MALs values. Only 8.6% foods achieve less than 0.7 R2. These predicted MALs are supposed to provide practical or theoretical reference to benefit the surveillance of pesticide applications and food safety control.

An innovative variant based on generative adversarial network (GAN): Regression GAN combined with hyperspectral imaging to predict pesticide residue content of Hami melon

The rapid and non-destructive detection of pesticide residues in Hami melons plays substantial importance in protecting consumer health. However, the investment of time and resources needed to procure sample data poses a challenge, often resulting in limited data set and consequently leading insufficient accuracy of the established models. In this study, an innovative variant based on generative adversarial network (GAN) was proposed, named regression GAN (RGAN). It was used to synchronically extend the visible near-infrared (VNIR) and short-wave infrared (SWIR) hyperspectral data and corresponding acetamiprid residue content data of Hami melon. The support vector regression (SVR) and partial least squares regression (PLSR) models were trained using the generated data, and subsequently validate them with real data to assess the reliability of the generated data. In addition, the generated data were added to the real data to extend the dataset. The SVR model based on SWIR-HSI data achieved the optimal performance after data augmentation, yielding the values of Rp2, RMSEP and RPD were 0.8781, 0.6962 and 2.7882, respectively. The RGAN extends the range of GAN applications from classification problems to regression problems. It serves as a valuable reference for the quantitative analysis of chemometrics.

Application of Convolutional Neural Networks and Recurrent Neural Networks in Food Safety

This review explores the application of convolutional neural networks (CNNs) and recurrent neural networks (RNNs) in food safety detection and risk prediction. This paper highlights the advantages of CNNs in image processing and feature recognition, as well as the powerful capabilities of RNNs (especially their variant LSTM) in time series data modeling. This paper also makes a comparative analysis in many aspects: Firstly, the advantages and disadvantages of traditional food safety detection and risk prediction methods are compared with deep learning technologies such as CNNs and RNNs. Secondly, the similarities and differences between CNNs and fully connected neural networks in processing image data are analyzed. Furthermore, the advantages and disadvantages of RNNs and traditional statistical modeling methods in processing time series data are discussed. Finally, the application directions of CNNs in food safety detection and RNNs in food safety risk prediction are compared. This paper also discusses combining these deep learning models with technologies such as the Internet of Things (IoT), blockchain, and federated learning to improve the accuracy and efficiency of food safety detection and risk warning. Finally, this paper mentions the limitations of RNNs and CNNs in the field of food safety, as well as the challenges in the interpretability of the model, and suggests the use of interpretable artificial intelligence (XAI) technology to improve the transparency of the model.

Non-Destructive Detection of Pesticide-Treated Baby Leaf Lettuce During Production and Post-Harvest Storage Using Visible and Near-Infrared Spectroscopy

The market demand for baby leaf lettuce is constantly increasing, while safety has become one of the most important traits in determining consumer preference driven by human health hazards concerns. In this study, the performance of visible and near-infrared (vis/NIR) spectroscopy was tested in discriminating pesticide-free against pesticide-treated lettuce plants. Two commercial fungicides (mancozeb and fosetyl-al) and two insecticides (deltamethrin and imidacloprid) were applied as spray solutions at the recommended rates on baby leaf lettuce plants. Untreated-control plants were sprayed with water. Reflectance data in the wavelength range 400-2500 nm were captured on leaf samples until harvest on the 10th day upon pesticide application, as well as after 4 and 8 days during post-harvest storage at 5 °C. In addition, biochemical components in leaf tissue were also determined during storage, such as antioxidant enzymes' activities (peroxidase [POD], catalase [CAT], and ascorbate peroxidase [APX]), along with malondialdehyde [MDA] and hydrogen peroxide [H2O2] content. Partial least square discriminant analysis (PLSDA) combined with feature-selection techniques was implemented, in order to classify baby lettuce tissue into pesticide-free or pesticide-treated ones. The genetic algorithm (GA) and the variable importance in projection (VIP) scores identified eleven distinct regions and nine specific wavelengths that exhibited the most significant effect in the detection models, with most of them in the near-infrared region of the electromagnetic spectrum. According to the results, the classification accuracy of discriminating pesticide-treated against non-treated lettuce leaves ranged from 94% to 99% in both pre-harvest and post-harvest periods. Although there were no significant differences in enzyme activities or H2O2, the MDA content in pesticide-treated tissue was greater than in untreated ones, implying that the chemical spray application probably induced a stress response in the plant that was disclosed with the reflected energy. In conclusion, vis/NIR spectroscopy appears as a promising, reliable, rapid, and non-destructive tool in distinguishing pesticide-free from pesticide-treated lettuce products.

Hyperspectral reflectance imaging for visualizing reducing sugar content, moisture, and hollow rate in red ginseng

Red ginseng (RG) has been traditionally valued in Northeast Asia for its health-enhancing properties. Recent advancements in hyperspectral imaging (HSI) offer a non-destructive, efficient, and reliable method to assess critical quality indicators of RG, such as reducing sugar content (RSC), water content (WC), and hollow rate (HR). This study developed predictive models using HSI technology to monitor these quality indicators over the spectral range of 400-1700 nm. Image features were enhanced using Principal Component Analysis (PCA) and Minimum Noise Fraction (MNF), followed by classification through Spectral Angle Mapping (SAM). The best-performing model for RSC achieved an R2 value of 0.6198 and a root mean square error (RMSE) of 0.013. For WC, the optimal model obtained an R2 value of 0.6555 and an RMSE of 0.014. The spatial distribution of RSC, WC, and HR was effectively visualized, demonstrating the potential of HSI for on-site quality control of RG. This study provides a foundation for real-time, non-invasive monitoring of RG quality, addressing industry needs for rapid and reliable assessment methods.

Recent advance in nondestructive imaging technology for detecting quality of fruits and vegetables: a review

As an integral part of daily dietary intake, the market demand for fruits and vegetables is continuously growing. However, traditional methods for assessing the quality of fruits and vegetables are prone to subjective influences, destructive to samples, and fail to comprehensively reflect internal quality, thereby resulting in various shortcomings in ensuring food safety and quality control. Over the past few decades, imaging technologies have rapidly evolved and been widely employed in nondestructive detection of fruit and vegetable quality. This paper offers a thorough overview of recent advancements in nondestructive imaging technologies for assessing the quality of fruits and vegetables, including hyperspectral imaging (HSI), fluorescence imaging (FI), magnetic resonance imaging (MRI), thermal imaging (TI), terahertz imaging, X-ray imaging (XRI), ultrasonic imaging, and microwave imaging (MWI). The principles and applications of these imaging techniques in nondestructive testing are summarized. The challenges and future trends of these technologies are discussed.

Development of a Portable Residual Chlorine Detection Device with a Combination of Microfluidic Chips and LS-BP Algorithm to Achieve Accurate Detection of Residual Chlorine in Water

Chlorine is widely used for sterilization and disinfection of water, but the presence of excess residual chlorine in water poses a substantial threat to human health. At present, there is no portable device which can achieve accurate, rapid, low-cost, and convenient detection of residual chlorine in water. Therefore, it is necessary to develop a device that can perform accurate, rapid, low-cost, and convenient detection of residual chlorine in water. In this study, a portable residual chlorine detection device was developed. A microfluidic chip was studied to achieve efficient mixing of two-phase flow. This microfluidic chip was used for rapid mixing of reagents in the portable residual chlorine detection device, reducing the consumption of reagents, detection time, and device volume. A deep learning algorithm was proposed for predicting residual chlorine concentration in water, achieving precise detection. Firstly, the microfluidic chip structure for detecting mixed reagents was optimized, and the microfluidic chip was fabricated by a 3D-printing method. Secondly, a deep learning (LS-BP) algorithm was constructed and proposed for predicting residual chlorine concentration in water, which can realize dual-channel signal reading. Thirdly, the corresponding portable residual chlorine detection device was developed, and the detection device was compared with residual chlorine detection devices and methods in other studies. The comparison results indicate that the portable residual chlorine detection device has high detection accuracy, fast detection speed, low cost, and good convenience. The excellent performance of the portable residual chlorine detection device makes it suitable for detecting residual chlorine in drinking water, swimming pool water, aquaculture and other fields.

Aptamer-based biosensors for the detection of neonicotinoid insecticides in environmental samples: A systematic review

Neonicotinoids, sometimes abbreviated as neonics, represent a class of neuro-active insecticides with chemical similarities to nicotine. Neonicotinoids are the most widely adopted group of insecticides globally since their discovery in the late 1980s. Their physiochemical properties surpass those of previously established insecticides, contributing to their popularity in various sectors such as agriculture and wood treatment. The environmental impact of neonicotinoids, often overlooked, underscores the urgency to develop tools for their detection and understanding of their behavior. Conventional methods for pesticide detection have limitations. Chromatographic techniques are sensitive but expensive, generate waste, and require complex sample preparation. Bioassays lack specificity and accuracy, making them suitable as preliminary tests in conjunction with instrumental methods. Aptamer-based biosensor is recognized as an advantageous tool for neonicotinoids detection due to its rapid response, user-friendly nature, cost-effectiveness, and suitability for on-site detection. This comprehensive review represents the inaugural in-depth analysis of advancements in aptamer-based biosensors targeting neonicotinoids such as imidacloprid, thiamethoxam, clothianidin, acetamiprid, thiacloprid, nitenpyram, and dinotefuran. Additionally, the review offers valuable insights into the critical challenges requiring prompt attention for the successful transition from research to practical field applications.

Basic research for identification and classification of organophosphorus pesticides in water based on ultraviolet-visible spectroscopy information

In this study, the goal was to develop a method for detecting and classifying organophosphorus pesticides (OPPs) in bodies of water. Sixty-five samples with different concentrations were prepared for each of the organophosphorus pesticides, namely chlorpyrifos, acephate, parathion-methyl, trichlorphon, dichlorvos, profenofos, malathion, dimethoate, fenthion, and phoxim, respectively. Firstly, the spectral data of all the samples was obtained using a UV-visible spectrometer. Secondly, five preprocessing methods, six manifold learning methods, and five machine learning algorithms were utilized to build detection models for identifying OPPs in water bodies. The findings indicate that the accuracy of machine learning models trained on data preprocessed using convolutional smoothing + first-order derivatives (SG + FD) outperforms that of models trained on data preprocessed using other methods. The backpropagation neural network (BPNN) model exhibited the highest accuracy rate at 99.95%, followed by the support vector machine (SVM) and convolutional neural network (CNN) models, both at 99.92%. The extreme learning machine (ELM) and K-nearest neighbors (KNN) models demonstrated accuracy rates of 99.84% and 99.81%, respectively. Following the application of a manifold learning algorithm to the full-wavelength data set for the purpose of dimensionality reduction, the data was then visualized in the first three dimensions. The results demonstrate that the t-distributed domain embedding (t-SNE) algorithm is superior, exhibiting dense clustering of similar clusters and clear classification of dissimilar ones. SG + FD-t-SNE-SVM ranks highest among the feature extraction models in terms of performance. The feature extraction dimension was set to 4, and the average classification accuracy was 99.98%, which slightly improved the prediction performance over the full-wavelength model. As shown in this study, the ultraviolet-visible (UV-visible) spectroscopy system combined with the t-SNE and SVM algorithms can effectively identify and classify OPPs in waterbodies.

Frontiers of machine learning in smart food safety

Integration of machine learning (ML) technologies into the realm of smart food safety represents a rapidly evolving field with significant potential to transform the management and assurance of food quality and safety. This chapter will discuss the capabilities of ML across different segments of the food supply chain, encompassing pre-harvest agricultural activities to post-harvest processes and delivery to the consumers. Three specific examples of applying cutting-edge ML to advance food science are detailed in this chapter, including its use to improve beer flavor, using natural language processing to predict food safety incidents, and leveraging social media to detect foodborne disease outbreaks. Despite advances in both theory and practice, application of ML to smart food safety still suffers from issues such as data availability, model reliability, and transparency. Solving these problems can help realize the full potential of ML in food safety. Development of ML in smart food safety is also driven by social and industry impacts. The improvement and implementation of legal policies brings both opportunities and challenges. The future of smart food safety lies in the strategic implementation of ML technologies, navigating social and industry impacts, and adapting to regulatory changes in the AI era.

Integrating Wireless Remote Sensing and Sensors for Monitoring Pesticide Pollution in Surface and Groundwater

Water constitutes an indispensable resource crucial for the sustenance of humanity, as it plays an integral role in various sectors such as agriculture, industrial processes, and domestic consumption. Even though water covers 71% of the global land surface, governments have been grappling with the challenge of ensuring the provision of safe water for domestic use. A contributing factor to this situation is the persistent contamination of available water sources rendering them unfit for human consumption. A common contaminant, pesticides are not frequently tested for despite their serious effects on biodiversity. Pesticide determination in water quality assessment is a challenging task because the procedures involved in the extraction and detection are complex. This reduces their popularity in many monitoring campaigns despite their harmful effects. If the existing methods of pesticide analysis are adapted by leveraging new technologies, then information concerning their presence in water ecosystems can be exposed. Furthermore, beyond the advantages conferred by the integration of wireless sensor networks (WSNs), the Internet of Things (IoT), Machine Learning (ML), and big data analytics, a notable outcome is the attainment of a heightened degree of granularity in the information of water ecosystems. This paper discusses methods of pesticide detection in water, emphasizing the possible use of electrochemical sensors, biosensors, and paper-based sensors in wireless sensing. It also explores the application of WSNs in water, the IoT, computing models, ML, and big data analytics, and their potential for integration as technologies useful for pesticide monitoring in water.

Integrated surface-enhanced Raman spectroscopy and convolutional neural network for quantitative and qualitative analysis of pesticide residues on pericarp

Pesticide residue poses a significant global public health concern, necessitating improved detection methods. Here, a novel platform was introduced based on surface-enhanced Raman spectroscopy (SERS) to detect ten distinct types of pesticides. Notably, the sensitivity of this approach is exemplified by detecting trace amounts of 50 pM (10 ppt) thiabendazole. The correlation between the characteristic peak intensity of coexisting pesticides and their concentrations displays an exceptional linear relationship (R2 = 0.9999), underscoring its utility for quantitative mixed pesticide detection. Additionally, qualitative analysis of five mixed pesticides was conducted leveraging distinctive peak labeling. Harnessing machine learning techniques, a model for classifying and predicting pesticides on pericarps was developed. Remarkably, the convolutional neural network achieved classification accuracy of 100 % and prediction accuracy of 99.62 %. This innovative approach accurately identifies and quantifies diverse pesticides, thus offering a feasible scheme for in-situ detection of pesticide residues. Ultimately, this strategy contributes to ensuring food safety and public health.

Identification and Classification of Coix seed Storage Years Based on Hyperspectral Imaging Technology Combined with Deep Learning

Developing a fast and non-destructive methodology to identify the storage years of Coix seed is important in safeguarding consumer well-being. This study employed the utilization of hyperspectral imaging (HSI) in conjunction with conventional machine learning techniques such as support vector machines (SVM), k-nearest neighbors (KNN), random forest (RF), extreme gradient boosting (XGBoost), as well as the deep learning method of residual neural network (ResNet), to establish identification models for Coix seed samples from different storage years. Under the fusion-based modeling approach, the model's classification accuracy surpasses that of visible to near infrared (VNIR) and short-wave infrared (SWIR) spectral modeling individually. The classification accuracy of the ResNet model and SVM exceeds that of other conventional machine learning models (KNN, RF, and XGBoost). Redundant variables were further diminished through competitive adaptive reweighted sampling feature wavelength screening, which had less impact on the model's accuracy. Upon validating the model's performance using an external validation set, the ResNet model yielded more satisfactory outcomes, exhibiting recognition accuracy exceeding 85%. In conclusion, the comprehensive results demonstrate that the integration of deep learning with HSI techniques effectively distinguishes Coix seed samples from different storage years.

Breaking boundaries: Artificial intelligence for pesticide detection and eco-friendly degradation

Pesticides are extensively used agrochemicals across the world to control pest populations. However, irrational application of pesticides leads to contamination of various components of the environment, like air, soil, water, and vegetation, all of which build up significant levels of pesticide residues. Further, these environmental contaminants fuel objectionable human toxicity and impose a greater risk to the ecosystem. Therefore, search of methodologies having potential to detect and degrade pesticides in different environmental media is currently receiving profound global attention. Beyond the conventional approaches, Artificial Intelligence (AI) coupled with machine learning and artificial neural networks are rapidly growing branches of science that enable quick data analysis and precise detection of pesticides in various environmental components. Interestingly, nanoparticle (NP)-mediated detection and degradation of pesticides could be linked to AI algorithms to achieve superior performance. NP-based sensors stand out for their operational simplicity as well as their high sensitivity and low detection limits when compared to conventional, time-consuming spectrophotometric assays. NPs coated with fluorophores or conjugated with antibody or enzyme-anchored sensors can be used through Surface-Enhanced Raman Spectrometry, fluorescence, or chemiluminescence methodologies for selective and more precise detection of pesticides. Moreover, NPs assist in the photocatalytic breakdown of various organic and inorganic pesticides. Here, AI models are ideal means to identify, classify, characterize, and even predict the data of pesticides obtained through NP sensors. The present study aims to discuss the environmental contamination and negative impacts of pesticides on the ecosystem. The article also elaborates the AI and NP-assisted approaches for detecting and degrading a wide range of pesticide residues in various environmental and agrecultural sources including fruits and vegetables. Finally, the prevailing limitations and future goals of AI-NP-assisted techniques have also been dissected.

Combining Vis-NIR and NIR Spectral Imaging Techniques with Data Fusion for Rapid and Nondestructive Multi-Quality Detection of Cherry Tomatoes

Firmness, soluble solid content (SSC) and titratable acidity (TA) are characteristic substances for evaluating the quality of cherry tomatoes. In this paper, a hyper spectral imaging (HSI) system using visible/near-infrared (Vis-NIR) and near-infrared (NIR) was proposed to detect the key qualities of cherry tomatoes. The effects of individual spectral information and fused spectral information in the detection of different qualities were compared for firmness, SSC and TA of cherry tomatoes. Data layer fusion combined with multiple machine learning methods including principal component regression (PCR), partial least squares regression (PLSR), support vector regression (SVR) and back propagation neural network (BP) is used for model training. The results show that for firmness, SSC and TA, the determination coefficient R2 of the multi-quality prediction model established by Vis-NIR spectra is higher than that of NIR spectra. The R2 of the best model obtained by SSC and TA fusion band is greater than 0.9, and that of the best model obtained by the firmness fusion band is greater than 0.85. It is better to use the spectral bands after information fusion for nondestructive quality detection of cherry tomatoes. This study shows that hyperspectral imaging technology can be used for the nondestructive detection of multiple qualities of cherry tomatoes, and the method based on the fusion of two spectra has a better prediction effect for the rapid detection of multiple qualities of cherry tomatoes compared with a single spectrum. This study can provide certain technical support for the rapid nondestructive detection of multiple qualities in other melons and fruits.

Special Issue "Advanced Spectroscopy Techniques in Food Analysis: Qualitative and Quantitative Chemometric Approaches"

The globalization of the food market has created a pressing need for food producers to meet the ever-increasing demands of consumers while ensuring adherence to stringent food safety and quality standards [...].

Detecting different pesticide residues on Hami melon surface using hyperspectral imaging combined with 1D-CNN and information fusion

Efficient, rapid, and non-destructive detection of pesticide residues in fruits and vegetables is essential for food safety. The visible/near infrared (VNIR) and short-wave infrared (SWIR) hyperspectral imaging (HSI) systems were used to detect different types of pesticide residues on the surface of Hami melon. Taking four pesticides commonly used in Hami melon as the object, the effectiveness of single-band spectral range and information fusion in the classification of different pesticides was compared. The results showed that the classification effect of pesticide residues was better by using the spectral range after information fusion. Then, a custom multi-branch one-dimensional convolutional neural network (1D-CNN) model with the attention mechanism was proposed and compared with the traditional machine learning classification model K-nearest neighbor (KNN) algorithm and random forest (RF). The traditional machine learning classification model accuracy of both models was over 80.00%. However, the classification results using the proposed 1D-CNN were more satisfactory. After the full spectrum data was fused, it was input into the 1D-CNN model, and its accuracy, precision, recall, and F1-score value were 94.00%, 94.06%, 94.00%, and 0.9396, respectively. This study showed that both VNIR and SWIR hyperspectral imaging combined with a classification model could non-destructively detect different pesticide residues on the surface of Hami melon. The classification result using the SWIR spectrum was better than that using the VNIR spectrum, and the classification result using the information fusion spectrum was better than that using SWIR. This study can provide a valuable reference for the non-destructive detection of pesticide residues on the surface of other large, thick-skinned fruits.

Hyperspectral Imaging with Machine Learning Approaches for Assessing Soluble Solids Content of Tribute Citru

Tribute Citru is a natural citrus hybrid with plenty of vitamins and nutrients. Fruits' soluble solids content (SSC) is a critical quality index. This study used hyperspectral imaging at two spectral ranges (400-1000 nm and 900-1700 nm) to determine SSC in Tribute Citru. Partial least squares regression (PLSR) and support vector regression (SVR) models were established in order to determine SSC using the spectral information of the calyx and blossom ends. The average spectra of both ends as well as their fusion was studied. The successive projections algorithm (SPA) and the correlation coefficient analysis (CCA) were used to examine the differences in characteristic wavelengths between the two ends. Most models achieved performances with the correlation coefficient of the training, validation, and testing sets over 0.6. Results showed that differences in the performances among the models using the one-sided and two-sided spectral information. No particular regulation could be found for the differences in model performances and characteristic wavelengths. The results illustrated that the sampling side was an influencing factor but not the determinant factor for SSC determination. These results would help with the development of real-world applications for citrus quality inspection without concerning the sampling sides and the spectral ranges.

Identification of Copper Metabolism Related Biomarkers, Polygenic Prediction Model, and Potential Therapeutic Agents in Alzheimer's Disease

BACKGROUND

The underlying pathogenic genes and effective therapeutic agents of Alzheimer's disease (AD) are still elusive. Meanwhile, abnormal copper metabolism is observed in AD brains of both human and mouse models.

OBJECTIVE

To investigate copper metabolism-related gene biomarkers for AD diagnosis and therapy.

METHODS

The AD datasets and copper metabolism-related genes (CMGs) were downloaded from GEO and GeneCards database, respectively. Differentially expressed CMGs (DE-CMGs) performed through Limma, functional enrichment analysis and the protein-protein interaction were used to identify candidate key genes by using CytoHubba. And these candidate key genes were utilized to construct a prediction model by logistic regression analysis for AD early diagnosis. Furthermore, ROC analysis was conducted to identify a single gene with AUC values greater than 0.7 by GSE5281. Finally, the single gene biomarker was validated by quantitative real-time polymerase chain reaction (qRT-PCR) in AD clinical samples. Additionally, immune cell infiltration in AD samples and potential therapeutic drugs targeting the identified biomarkers were further explored.

RESULTS

A polygenic prediction model for AD based on copper metabolism was established by the top 10 genes, which demonstrated good diagnostic performance (AUC values). COX11, LDHA, ATOX1, SCO1, and SOD1 were identified as blood biomarkers for AD early diagnosis. 20 agents targeting biomarkers were retrieved from DrugBank database, some of which have been proven effective for the treatment of AD.

CONCLUSIONS

The five blood biomarkers and copper metabolism-associated model can differentiate AD patients from non-demented individuals and aid in the development of new therapeutic strategies.

Application of Near-Infrared Spectroscopy and Hyperspectral Imaging Combined with Machine Learning Algorithms for Quality Inspection of Grape: A Review

Grape is a fruit rich in various vitamins, and grape quality is increasingly highly concerned with by consumers. Traditional quality inspection methods are time-consuming, laborious and destructive. Near-infrared spectroscopy (NIRS) and hyperspectral imaging (HSI) are rapid, non-destructive and accurate techniques for quality inspection and safety assessment of agricultural products, which have great potential in recent years. The review summarized the applications and achievements of NIRS and HSI for the quality inspection of grapes for the last ten years. The review introduces basic principles, signal mode, data acquisition, analysis and processing of NIRS and HSI data. Qualitative and quantitative analysis were involved and compared, respectively, based on spectral features, image features and fusion data. The advantages, disadvantages and development trends of NIRS and HSI techniques in grape quality and safety inspection are summarized and discussed. The successful application of NIRS and HSI in grape quality inspection shows that many fruit inspection tasks could be assisted with NIRS and HSI.

Discrimination of Pesticide Residue Levels on the Hami Melon Surface Using Multiscale Convolution

Pesticide residues directly or indirectly threaten the health of humans and animals. We need a rapid and nondestructive method for the safety evaluation of fruits. In this study, the feasibility of visible/near-infrared (Vis/NIR) spectroscopy technology was explored for the discrimination of pesticide residue levels on the Hami melon surface. The one-dimensional convolutional neural network (1D-CNN) model was proposed for spectral data discrimination. We compared the effect of different convolutional architectures on the model performance, including single-depth, symmetric, and asymmetric multiscale convolution. The results showed that the 1D-CNN model could discriminate the presence or absence of pesticide residues with a high accuracy above 99.00%. The multiscale convolution could significantly improve the model accuracy while reducing the modeling time. In particular, the asymmetric convolution had a better comprehensive performance. For two-level discrimination, the accuracy of lambda-cyhalothrin and beta-cypermethrin was 93.68% and 95.79%, respectively. For three-level discrimination, the accuracy of lambda-cyhalothrin and beta-cypermethrin was 86.32% and 89.47%, respectively. For four-level discrimination, the accuracy of lambda-cyhalothrin and beta-cypermethrin was 87.37% and 93.68%, respectively, and the average modeling time was 3.5 s. This finding will encourage more relevant research to use multiscale 1D-CNN as a spectral analysis strategy for the detection of pesticide residues in fruits.

Convolutional Neural Network for Object Detection in Garlic Root Cutting Equipment

Traditional manual garlic root cutting is inefficient and can cause food safety problems. To develop food processing equipment, a novel and accurate object detection method for garlic using deep learning—a convolutional neural network—is proposed in this study. The you-only-look-once (YOLO) algorithm, which is based on lightweight and transfer learning, is the most advanced computer vision method for single large object detection. To detect the bulb, the YOLOv2 model was modified using an inverted residual module and residual structure. The modified model was trained based on images of bulbs with varied brightness, surface attachment, and shape, which enabled sufficient learning of the detector. The optimum minibatches and epochs were obtained by comparing the test results of different training parameters. Research shows that IRM-YOLOv2 is superior to the SqueezeNet, ShuffleNet, and YOLOv2 models of classical neural networks, as well as the YOLOv3 and YOLOv4 algorithm models. The confidence score, average accuracy, deviation, standard deviation, detection time, and storage space of IRM-YOLOv2 were 0.98228, 99.2%, 2.819 pixels, 4.153, 0.0356 s, and 24.2 MB, respectively. In addition, this study provides an important reference for the application of the YOLO algorithm in food research.