A Machine Learning Method for the Quantitative Detection of Adulterated Meat Using a MOS-Based E-Nose

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.

Intelligent Grading of Green Cardamom Using Data Fusion of Electronic Nose and Computer Vision Methods

In this research, the intelligent quality grading of green cardamom was carried out using electronic nose (e-nose) and computer vision (CV) methods along with machine learning (ML) approaches. Cardamom samples were analyzed in three grades including Grade 1 (healthy and green), Grade 2 (healthy with yellow color), and Grade 3 (immature and shriveled) for capsules and Grade 1 (Black), Grade 2 (Brown), and Grade 3 (Yellow and red) for seeds. Three ML algorithms including Decision Tree (DT), Bayesian Network (BN), and Support Vector Machine (SVM) were used to classify the quality grades. Results showed that the correlation-based feature selection (CFS) algorithm decreased the number of input features and increased the classification performance. For classifying cardamom capsule samples based on the visual features, the CFS-BN model was the best classifier, with the root mean squared error (RMSE) and accuracy of 0.1408 and 96.67%, respectively. The RMSE and accuracy of this model for classifying cardamom seeds based on image features were 0.1220 and 96.67%, respectively. In classifying cardamom seeds using e-nose data, the CFS-DT model was the best classifier with RMSE and accuracy of 0.2093 and 93.33%, respectively. The CFS-BN model was the best for classifying cardamom capsules with an RMSE of 0.1126 and an accuracy of 96.67%. The fusion of e-nose and CV data increased the model performance compared to the separate use of e-nose and CV datasets. The accuracy of the CFS-BN model using the combination of CV and e-nose data was 100% during both the calibration and evaluation stages. It can be concluded that data fusion of e-nose and CV methods can be effectively used to develop an intelligent, accurate, reliable, fast, and non-destructive system for quality grading of cardamom capsules and seeds.

Digitalization of Colorimetric Sensor Technologies for Food Safety

Colorimetric sensors play a crucial role in promoting on-site testing, enabling the detection and/or quantification of various analytes based on changes in color. These sensors offer several advantages, such as simplicity, cost-effectiveness, and visual readouts, making them suitable for a wide range of applications, including food safety and monitoring. A critical component in portable colorimetric sensors involves their integration with color models for effective analysis and interpretation of output signals. The most commonly used models include CIELAB (Commission Internationale de l'Eclairage), RGB (Red, Green, Blue), and HSV (Hue, Saturation, Value). This review outlines the use of color models via digitalization in sensing applications within the food safety and monitoring field. Additionally, challenges, future directions, and considerations are discussed, highlighting a significant gap in integrating a comparative analysis toward determining the color model that results in the highest sensor performance. The aim of this review is to underline the potential of this integration in mitigating the global impact of food spoilage and contamination on health and the economy, proposing a multidisciplinary approach to harness the full capabilities of colorimetric sensors in ensuring food safety.

Portable and miniature sensors in supply chain for food authentication: a review

Food fraud, a pervasive issue in the global food industry, poses significant challenges to consumer health, trust, and economic stability, costing an estimated $10-15 billion annually. Therefore, there is a rising demand for developing portable and miniature sensors that facilitate food authentication throughout the supply chain. This review explores the recent advancements and applications of portable and miniature sensors, including portable/miniature near-infrared (NIR) spectroscopy, e-nose and colorimetric sensors based on nanozyme for food authentication within the supply chain. After briefly presenting the architecture and mechanism, this review discusses the application of these portable and miniature sensors in food authentication, addressing the challenges and opportunities in integrating and deploying these sensors to ensure authenticity. This review reveals the enhanced utility of portable/miniature NIR spectroscopy, e-nose, and nanozyme-based colorimetric sensors in ensuring food authenticity and enabling informed decision-making throughout the food supply chain.

Electronic Noses: From Gas-Sensitive Components and Practical Applications to Data Processing

Artificial olfaction, also known as an electronic nose, is a gas identification device that replicates the human olfactory organ. This system integrates sensor arrays to detect gases, data acquisition for signal processing, and data analysis for precise identification, enabling it to assess gases both qualitatively and quantitatively in complex settings. This article provides a brief overview of the research progress in electronic nose technology, which is divided into three main elements, focusing on gas-sensitive materials, electronic nose applications, and data analysis methods. Furthermore, the review explores both traditional MOS materials and the newer porous materials like MOFs for gas sensors, summarizing the applications of electronic noses across diverse fields including disease diagnosis, environmental monitoring, food safety, and agricultural production. Additionally, it covers electronic nose pattern recognition and signal drift suppression algorithms. Ultimately, the summary identifies challenges faced by current systems and offers innovative solutions for future advancements. Overall, this endeavor forges a solid foundation and establishes a conceptual framework for ongoing research in the field.

Geographical traceability of soybean: An electronic nose coupled with an effective deep learning method

The quality of soybeans is correlated with their geographical origin. It is a common phenomenon to replace low-quality soybeans from substandard origins with superior ones. This paper proposes the adaptive convolutional kernel channel attention network (AKCA-Net) combined with an electronic nose (e-nose) to achieve soybean quality traceability. First, the e-nose system is used to collect soybean gas information from different origins. Second, depending on the characteristics of the gas information, we propose the adaptive convolutional kernel channel attention (AKCA) module, which focuses on key gas channel features adaptively. Finally, the AKCA-Net is proposed, which is capable of modeling deep gas channel interdependency efficiently, realizing high-precision recognition of soybean quality. In comparative experiments with other attention mechanisms, AKCA-Net demonstrated superior performance, achieving an accuracy of 98.21%, precision of 98.57%, and recall of 98.60%. In conclusion, the combination of the AKCA-Net and e-nose provides an effective strategy for soybean quality traceability.

Raman spectroscopy coupled with chemometrics for identification of adulteration and fraud in muscle foods: a review

Muscle foods, valued for their significant nutrient content such as high-quality protein, vitamins, and minerals, are vulnerable to adulteration and fraud, stemming from dishonest vendor practices and insufficient market oversight. Traditional analytical methods, often limited to laboratory-scale., may not effectively detect adulteration and fraud in complex applications. Raman spectroscopy (RS), encompassing techniques like Surface-enhanced RS (SERS), Dispersive RS (DRS), Fourier transform RS (FTRS), Resonance Raman spectroscopy (RRS), and Spatially offset RS (SORS) combined with chemometrics, presents a potent approach for both qualitative and quantitative analysis of muscle food adulteration. This technology is characterized by its efficiency, rapidity, and noninvasive nature. This paper systematically summarizes and comparatively analyzes RS technology principles, emphasizing its practicality and efficacy in detecting muscle food adulteration and fraud when combined with chemometrics. The paper also discusses the existing challenges and future prospects in this field, providing essential insights for reviews and scientific research in related fields.

Predicting the quality attributes related to geographical growing regions in red-fleshed kiwifruit by data fusion of electronic nose and computer vision systems

The ability of a data fusion system composed of a computer vision system (CVS) and an electronic nose (e-nose) was evaluated to predict key physiochemical attributes and distinguish red-fleshed kiwifruit produced in three distinct regions in northern Iran. Color and morphological features from whole and middle-cut kiwifruits, along with the maximum responses of the 13 metal oxide semiconductor (MOS) sensors of an e-nose system, were used as inputs to the data fusion system. Principal component analysis (PCA) revealed that the first two principal components (PCs) extracted from the e-nose features could effectively differentiate kiwifruit samples from different regions. The PCA-SVM algorithm achieved a 93.33% classification rate for kiwifruits from three regions based on data from individual e-nose and CVS. Data fusion increased the classification rate of the SVM model to 100% and improved the performance of Support Vector Regression (SVR) for predicting physiochemical indices of kiwifruits compared to individual systems. The data fusion-based PCA-SVR models achieved validation R2 values ranging from 90.17% for the Brix-Acid Ratio (BAR) to 98.57% for pH prediction. These results demonstrate the high potential of fusing artificial visual and olfactory systems for quality monitoring and identifying the geographical growing regions of kiwifruits.

Synergetic application of thermal imaging and CCD imaging techniques to detect mutton adulteration based on data-level fusion and deep residual network

To improve the performance of single thermal imaging and single CCD imaging in detecting unknown adulterated meat samples, these two imaging techniques combined with a deep residual network were synergistically applied to detect mutton adulteration. Considering the importance of spatial and detailed information in improving stability and accuracy, three data-level fusion methods, namely, colour image stitching, grey image stitching and grey channel stacking, were proposed for the fusion of thermal images and CCD images. Classification and prediction models were further developed based on fusion images. The results showed that the models with colour image stitching achieved the best performance. For the external validation set, the accuracy of the best classification model in discriminating five categories was 99.30%. In predicting pork proportions, the R2, RMSE, RPD and RER of the best prediction model were 0.9717, 0.0238, 7.8696 and 21.28, respectively. The best prediction model for duck proportions had a R2 of 0.9616, RMSE of 0.0277, RPD of 5.1015, and RER of 14.44. Therefore, the synergetic application of thermal imaging and CCD imaging can provide a novel and promising tool to detect mutton adulteration and the quality of other food items.

Beef Quality Classification with Reduced E-Nose Data Features According to Beef Cut Types

Ensuring safe food supplies has recently become a serious problem all over the world. Controlling the quality, spoilage, and standing time for products with a short shelf life is a quite difficult problem. However, electronic noses can make all these controls possible. In this study, which aims to develop a different approach to the solution of this problem, electronic nose data obtained from 12 different beef cuts were classified. In the dataset, there are four classes (1: excellent, 2: good, 3: acceptable, and 4: spoiled) indicating beef quality. The classifications were performed separately for each cut and all cut shapes. The ANOVA method was used to determine the active features in the dataset with data for 12 features. The same classification processes were carried out by using the three active features selected by the ANOVA method. Three different machine learning methods, Artificial Neural Network, K Nearest Neighbor, and Logistic Regression, which are frequently used in the literature, were used in classifications. In the experimental studies, a classification accuracy of 100% was obtained as a result of the classification performed with ANN using the data obtained by combining all the tables in the dataset.

The Impact of Wet Fermentation on Coffee Quality Traits and Volatile Compounds Using Digital Technologies

Fermentation is critical for developing coffee’s physicochemical properties. This study aimed to assess the differences in quality traits between fermented and unfermented coffee with four grinding sizes of coffee powder using multiple digital technologies. A total of N = 2 coffee treatments—(i) dry processing and (ii) wet fermentation—with grinding levels (250, 350, 550, and 750 µm) were analysed using near-infrared spectrometry (NIR), electronic nose (e-nose), and headspace/gas chromatography–mass spectrometry (HS-SPME-GC-MS) coupled with machine learning (ML) modelling. Most overtones detected by NIR were within the ranges of 1700–2000 nm and 2200–2396 nm, while the enhanced peak responses of fermented coffee were lower. The overall voltage of nine e-nose sensors obtained from fermented coffee (250 µm) was significantly higher. There were two ML classification models to classify processing and brewing methods using NIR (Model 1) and e-nose (Model 2) values as inputs that were highly accurate (93.9% and 91.2%, respectively). Highly precise ML regression Model 3 and Model 4 based on the same inputs for NIR (R = 0.96) and e-nose (R = 0.99) were developed, respectively, to assess 14 volatile aromatic compounds obtained by GC-MS. Fermented coffee showed higher 2-methylpyrazine (2.20 ng/mL) and furfuryl acetate (2.36 ng/mL) content, which induces a stronger fruity aroma. This proposed rapid, reliable, and low-cost method was shown to be effective in distinguishing coffee postharvest processing methods and evaluating their volatile compounds, which has the potential to be applied for coffee differentiation and quality assurance and control.

Investigating Changes in pH and Soluble Solids Content of Potato during the Storage by Electronic Nose and Vis/NIR Spectroscopy

Potato is an important agricultural product, ranked as the fourth most common product in the human diet. Potato can be consumed in various forms. As customers expect safe and high-quality products, precise and rapid determination of the quality and composition of potatoes is of crucial significance. The quality of potatoes may alter during the storage period due to various phenomena. Soluble solids content (SSC) and pH are among the quality parameters experiencing alteration during the storage process. This study is thus aimed to assess the variations in SSC and pH during the storage of potatoes using an electronic nose and Vis/NIR spectroscopic techniques with the help of prediction models including partial least squares (PLS), multiple linear regression (MLR), principal component regression (PCR), support vector regression (SVR) and an artificial neural network (ANN). The variations in the SSC and pH are ascending and significant. The results also indicate that the SVR model in the electronic nose has the highest prediction accuracy for the SSC and pH (81, and 92%, respectively). The artificial neural network also managed to predict the SSC and pH at accuracies of 83 and 94%, respectively. SVR method shows the lowest accuracy in Vis/NIR spectroscopy while the PLS model exhibits the best performance in the prediction of the SSC and pH with respective precision of 89 and 93% through the median filter method. The accuracy of the ANN was 85 and 90% in the prediction of the SSC and pH, respectively.

Relative quantification of pork and beef in meat products using global and species-specific peptide markers for the authentication of meat composition

We used global and species-specific peptide markers for a relative quantitative determination of pork and beef in raw and processed meat products made of the two meat species. Four groups of products were prepared (i.e., minced raw meats, sausages, raw and fried burgers) in order to represent products with different extents of food processing. In each group, the products varied in the pork/beef proportions. All products were analysed by multiple reaction monitoring mass spectrometry (MRM-MS) for the presence/concentration of pork- and beef-specific peptide markers, as well as global markers - peptides widely distributed in muscle tissue. The combined MRM-MS analysis of pork-specific peptide HPGDFGADAQGAMSK, beef-specific peptide VLGFHG and global marker LFDLR offered the most reliable validation of declared pork/beef compositions across the whole range of meat products. Our work suggests that a simultaneous analysis of global and species-specific peptide markers can be used for composition authentication in commercial pork/beef products.

Rapid Assessment of Rice Quality Traits Using Low-Cost Digital Technologies

Aroma and other physicochemical parameters are important attributes influencing consumer perception and acceptance of rice. However, current methods using multiple instruments and laboratory analysis make these assessments costly and time-consuming. Therefore, this study aimed to assess rice quality traits of 17 commercial rice types using a low-cost electronic nose and portable near-infrared spectrometer coupled with machine learning (ML). Specifically, artificial neural networks (ANN) were used to classify the type of rice and predict rice quality traits (aromas, color, texture, and pH of cooked rice) as targets. The ML models developed showed that the chemometrics obtained from both sensor technologies successfully classified the rice (Model 1: 98.7%; Model 2: 98.6%) and predicted the peak area of aromas obtained by gas chromatography-mass spectroscopy found in raw (Model 3: R = 0.95; Model 6: R = 0.95) and cooked rice (Model 4: R = 0.98; Model 7: R = 0.96). Furthermore, a high R = 0.98 was obtained for Model 5 to estimate the color, texture, and pH of cooked rice. The proposed method is rapid, low-cost, reliable, and may help the rice industry increase high-quality rice production and accelerate the adoption of digital technologies and artificial intelligence to support the rice value chain.