Feasibility study on Raman spectra-based deep learning models for monitoring the contamination degree and level of aflatoxin B1 in edible oil

Detection of Mycotoxin Contamination in Foods Using Artificial Intelligence: A Review

Mycotoxin contamination of foods is a major concern for food safety and public health worldwide. The contamination of agricultural commodities employed by humankind with mycotoxins (toxic secondary metabolites of fungi) is a major risk to the health of the human population. Common methods for mycotoxin detection include chromatographic separation, often combined with mass spectrometry (accurate but time-consuming to prepare the sample and requiring skilled technicians). Artificial intelligence (AI) has been introduced as a new technique for mycotoxin detection in food, providing high credibility and accuracy. This review article provides an overview of recent studies on the use of AI methods for the discovery of mycotoxins in food. The new approach demonstrated that a variety of AI technologies could be correlated. Deep learning models, machine learning algorithms, and neural networks were implemented to analyze elaborate datasets from different analytical platforms. In addition, this review focuses on the advancement of AI to work concomitantly with smart sensing technologies or other non-conventional techniques such as spectroscopy, biosensors, and imaging techniques for rapid and less damaging mycotoxin detection. We question the requirement for large and diverse datasets to train AI models, discuss the standardization of analytical methodologies, and discuss avenues for regulatory approval of AI-based approaches, among other top-of-mind issues in this domain. In addition, this research provides some interesting use cases and real commercial applications where AI has been able to outperform other traditional methods in terms of sensitivity, specificity, and time required. This review aims to provide insights for future directions in AI-enabled mycotoxin detection by incorporating the latest research results and stressing the necessity of multidisciplinary collaboration among food scientists, engineers, and computer scientists. Ultimately, the use of AI could revolutionize systems monitoring mycotoxins, improving food safety and safeguarding global public health.

A multi-verse optimizer-based CNN-BiLSTM pixel-level detection model for peanut aflatoxins

Peanuts are highly susceptible to contamination by aflatoxins, posing a significant threat to human health. This study aims to enhance the accuracy of pixel-level aflatoxin detection in hyperspectral images using an optimized deep learning method. This study developed a CNN-BiLSTM fusion model optimized by the Multi-Verse Optimizer (MVO) algorithm, specifically designed to detect aflatoxins with high precision. The optimized CNN-BiLSTM model was fine-tuned using aflatoxin spectral data at varying concentrations. The results indicate that the fine-tuned MVO-CNN-BiLSTM model achieved the best performance, with a validation accuracy of 94.92 % and a recall rate of 95.59 %. The accuracy of this model is 6.93 % and 3.6 % higher than machine learning methods such as SVM and AdaBoost, respectively. Additionally, it is 4.18 % and 3.08 % higher than deep learning methods such as CNN and the CNN-LSTM fusion model, respectively. This method enhances pixel-level aflatoxin detection accuracy, supporting the development of online detection devices.

Microwave detection technique combined with deep learning algorithm facilitates quantitative analysis of heavy metal Pb residues in edible oils

The heavy metal content in edible oils is intricately associated with their suitability for human consumption. In this study, standard soybean oil was used as a sample to quantify the specified concentration of heavy metals using microwave sensing technique. In addition, an attention-based deep residual neural network model was developed as an alternative to traditional modeling methods for predicting heavy metals in edible oils. In the process of microwave data processing, this work continued to discuss the impact of depth on convolutional neural networks. The results demonstrated that the proposed attention-based residual network model outperforms all other deep learning models in all metrics. The performance of this model was characterized by a coefficient of determination (R2) of 0.9605, a relative prediction deviation (RPD) of 5.0479, and a root mean square error (RMSE) of 3.1654 mg/kg. The research findings indicate that the combination of microwave detection technology and chemometrics holds significant potential for assessing heavy metal levels in edible oils.

Raman Hyperspectral Imaging as a Potential Tool for Rapid and Nondestructive Identification of Aflatoxin Contamination in Corn Kernels

The potential of Raman hyperspectral imaging with a 785 nm excitation line laser was examined for the detection of aflatoxin contamination in corn kernels. Nine-hundred kernels were artificially inoculated in the laboratory, with 300 kernels each inoculated with AF13 (aflatoxigenic) fungus, AF36 (nonaflatoxigenic) fungus, and sterile distilled water (control). One-hundred kernels from each treatment were subsequently incubated for 3, 5, and 8 days. The mean spectra of single kernels were extracted from the endosperm side and the embryo area of the germ side, and local Raman peaks were identified based upon the calculated reference spectra of aflatoxin-negative and -positive categories separately. The principal component analysis-linear discriminant analysis models were established using different types of variable inputs including original full spectra, preprocessed full spectra, and identified local peaks over kernel endosperm-side, germ-side, and both sides. The results of the established discriminant models showed that the germ-side spectra performed better than the endosperm-side spectra. Based upon the 20 ppb-threshold, the best mean prediction accuracy of 82.6% was achieved for the aflatoxin-negative category using the original spectra in the combined form of both kernel sides, and the best mean prediction accuracy of 86.7% was obtained for the -positive category using the preprocessed germ-side spectra. Based upon the 100 ppb-threshold, the best mean prediction accuracies of 85.0% and 89.6% were achieved for the aflatoxin-negative and -positive categories separately, using the same type of variable inputs for the 20 ppb-threshold. In terms of overall prediction accuracy, the models established upon the original spectra in the combined form of both kernel sides achieved the best predictive performance, regardless of the threshold. The mean overall prediction accuracies of 81.8% and 84.5% were achieved with the 20 ppb- and 100 ppb-thresholds, respectively.

Integrating transformer-based machine learning with SERS technology for the analysis of hazardous pesticides in spinach

This study introduces an innovative strategy for the rapid and accurate identification of pesticide residues in agricultural products by combining surface-enhanced Raman spectroscopy (SERS) with a state-of-the-art transformer model, termed SERSFormer. Gold-silver core-shell nanoparticles were synthesized and served as high-performance SERS substrates, which possess well-defined structures, uniform dispersion, and a core-shell composition with an average diameter of 21.44 ± 4.02 nm, as characterized by TEM-EDS. SERSFormer employs sophisticated, task-specific data processing techniques and CNN embedders, powered by an architecture features weight-shared multi-head self-attention transformer encoder layers. The SERSFormer model demonstrated exceptional proficiency in qualitative analysis, successfully classifying six categories, including five pesticides (coumaphos, oxamyl, carbophenothion, thiabendazole, and phosmet) and a control group of spinach data, with 98.4% accuracy. For quantitative analysis, the model accurately predicted pesticide concentrations with a mean absolute error of 0.966, a mean squared error of 1.826, and an R2 score of 0.849. This novel approach, which combines SERS with machine learning and is supported by robust transformer models, showcases the potential for real-time pesticide detection to improve food safety in the agricultural and food industries.

Rapid discrimination and ratio quantification of mixed antibiotics in aqueous solution through integrative analysis of SERS spectra via CNN combined with NN-EN model

INTRODUCTION

Abusing antibiotic residues in the natural environment has become a severe public health and ecological environmental problem. The side effects of its biochemical and physiological consequences are severe. To avoid antibiotic contamination in water, implementing universal and rapid antibiotic residue detection technology is critical to maintaining antibiotic safety in aquatic environments. Surface-enhanced Raman spectroscopy (SERS) provides a powerful tool for identifying small molecular components with high sensitivity and selectivity. However, it remains a challenge to identify pure antibiotics from SERS spectra due to coexisting components in the mixture.

OBJECTIVES

In this study, an intelligent analysis model for the SERS spectrum based on a deep learning algorithm was proposed for rapid identification of the antibiotic components in the mixture and quantitative determination of the ratios of these components.

METHODS

We established a water environment system containing three antibiotic residues of ciprofloxacin, doxycycline, and levofloxacin. To facilitate qualitative and quantitative analysis of the SERS spectra antibiotic mixture datasets, we developed a computational framework integrating a convolutional neural network (CNN) and a non-negative elastic network (NN-EN) method.

RESULTS

The experimental results demonstrate that the CNN model has a recognition accuracy of 98.68%, and the interpretation analysis of Shapley Additive exPlanations (SHAP) shows that our model can specifically focus on the characteristic peak distribution. In contrast, the NN-EN model can accurately quantify each component's ratio in the mixture.

CONCLUSION

Integrating the SERS technique assisted by the CNN combined with the NN-EN model exhibits great potential for rapid identification and high-precision quantification of antibiotic residues in aquatic environments.

Revealing the adulteration of sesame oil products by portable Raman spectrometer and 1D CNN vector regression: A comparative study with chemometrics and colorimetry

Identification and quantification of sesame oil products are crucial due to the existing problems of adulteration with lower-priced oils and false labeling of sesame proportions. In this study, 1D CNN models were established to achieve discrimination of oil types and multiple quantification of adulteration using portable Raman spectrometer. An improved data augmentation method involving discarding transformations that alter peak positions was proposed, and synchronously injecting noise during geometric transformations. Furthermore, a novel neural network structure was introduced incorporating vector regression to accurately predict each component simultaneously. The proposed method has achieved higher accuracy in detecting multi-component adulteration compared with chemometrics (100 % accuracy in classifying different oils; R2 over 0.99 and RMSE within 2 % in predicting unknown adulterated samples). Finally, commercially available sesame oil products were tested and compared with gas chromatography and colorimetric methods, demonstrating the effectiveness of our proposed model in achieving higher detection accuracy at low-concentration adulteration.

A Review of Recent Advances for the Detection of Biological, Chemical, and Physical Hazards in Foodstuffs Using Spectral Imaging Techniques

Traditional methods for detecting foodstuff hazards are time-consuming, inefficient, and destructive. Spectral imaging techniques have been proven to overcome these disadvantages in detecting foodstuff hazards. Compared with traditional methods, spectral imaging could also increase the throughput and frequency of detection. This study reviewed the techniques used to detect biological, chemical, and physical hazards in foodstuffs including ultraviolet, visible and near-infrared (UV-Vis-NIR) spectroscopy, terahertz (THz) spectroscopy, hyperspectral imaging, and Raman spectroscopy. The advantages and disadvantages of these techniques were discussed and compared. The latest studies regarding machine learning algorithms for detecting foodstuff hazards were also summarized. It can be found that spectral imaging techniques are useful in the detection of foodstuff hazards. Thus, this review provides updated information regarding the spectral imaging techniques that can be used by food industries and as a foundation for further studies.

Rapid qualitative detection of titanium dioxide adulteration in persimmon icing using portable Raman spectrometer and Machine learning

Persimmon icing is the white crystalline powder that adheres to the surface of persimmon cakes when the sugar in the persimmon spills over during processing, which is considered the essence of persimmon. Titanium dioxide is a food additive that is commonly added to the surface of persimmon cakes to impersonate high-quality persimmon cakes. However, excessive titanium dioxide can be harmful to humans, so a quick method is needed to identify persimmon cakes as adulterated. Raman spectroscopy with distinctive advantages of water-insensitivity, real-time, field-deployable, label-free, and fingerprinting-identification has been rapidly developed and used in food quality assurance and safety monitoring. In this study, we investigated Raman spectroscopy integrated with machine learning to assess titanium dioxide adulteration in dried persimmon icing. The adaptive iterative reweighting partial least squares (air-PLS) algorithm as an effective algorithm was used to remove fluorescent background signals in raw Raman spectroscopy. Principal components analysis (PCA) was employed to analyze the spectral data and determine the class memberships, and results showed that 99.9% of information could be explained by PC-1 and PC-2. Compared with extreme learning machine (ELM), support vector machine (SVM), back propagation artificial neural network (BP-ANN), and random forest (RF) models, one-dimensional stack auto encoder convolutional neural network (1D-SAE-CNN) could provide the highest detection accuracy of 0.9825, precision of 0.9824, recall of 0.9825, and f1-score of 0.9824. This study shows that Raman spectroscopy coupled with 1D-SAE-CNN is a promising method to detect titanium dioxide adulteration in persimmon icing.

Raman spectroscopy: Principles and recent applications in food safety

Food contaminant is a significant issue because of the adverse effects on human health and economy. Traditional detection methods such as liquid chromatography-mass spectroscopy for detecting food contaminants are expensive and time-consuming, and require highly-trained personnel and complicated sample pretreatment. Raman spectroscopy is an advanced analytical technique in a manner of non-destructive, rapid, cost-effective, and ultrasensitive sensing various hazards in agri-foods. In this chapter, we summarized the principle of Raman spectroscopy and surface enhanced Raman spectroscopy, the methods to process Raman spectra, the recent applications of Raman/SERS (surface-enhanced Raman spectroscopy) in detecting chemical contaminants (e.g., pesticides, antibiotics, mycotoxins, heavy metals, and food adulterants) and microbiological hazards (e.g., Salmonella, Campylobacter, Shiga toxigenic E. coli, Listeria, and Staphylococcus aureus) in foods.

Recent Progress on Techniques in the Detection of Aflatoxin B1 in Edible Oil: A Mini Review

Contamination of agricultural products and foods by aflatoxin B1 (AFB1) is becoming a serious global problem, and the presence of AFB1 in edible oil is frequent and has become inevitable, especially in underdeveloped countries and regions. As AFB1 results from a possible degradation of aflatoxins and the interaction of the resulting toxic compound with food components, it could cause chronic disease or severe cancers, increasing morbidity and mortality. Therefore, rapid and reliable detection methods are essential for checking AFB1 occurrence in foodstuffs to ensure food safety. Recently, new biosensor technologies have become a research hotspot due to their characteristics of speed and accuracy. This review describes various technologies such as chromatographic and spectroscopic techniques, ELISA techniques, and biosensing techniques, along with their advantages and weaknesses, for AFB1 control in edible oil and provides new insight into AFB1 detection for future work. Although compared with other technologies, biosensor technology involves the cross integration of multiple technologies, such as spectral technology and new nano materials, and has great potential, some challenges regarding their stability, cost, etc., need further studies.