1. Introduction

2. Background

3. Materials and Methods

4. Data Description and Analysis

Table 3. This table represents all collected 69 papers, where A stands for Articles and R stands for Reviews.

Table 4. Continuity of Table 3.

Table 5. Continuity of Table 3.

Table 6. Continuity of Table 3.

4.4. Article Papers

As depicted in Figure 8, the obtained 49 research papers focus on the identification, and in some cases quantification, of food-borne pathogens, be it bacteria, fungi, or yeast. The employed Machine Learning (ML) workflow mostly consists of two major steps, namely data preparation, including data acquisition, data cleaning, and data transformation; and decision making including, tuning, training, and testing of one or multiple machine learning models.

Table 7. Chemometrics and ML applications for crop-based food safety and quality in some relevant review papers.

Table 7. Chemometrics and ML applications for crop-based food safety and quality in some relevant review papers.

Ref.	Crop-food	Pre-processing steps	Decision model
[81]	Tea	Standard normal variate (SNV) and multiplica-tive scatter corrections	PCA, KNN, KPCA, ANN, HCA, BPNN, PLS, CPNN, SPA, PNN, ELM, LDA, SVM, S-LDA, LVQ, KLDA, MLP, RBF, RF.
[103]	Apple, Wolfberry, Lettuce, Pear, Green plum, Peach, Strawberry, Brassica, Jujube, Lettuce and Chives	LLE, LE, ISOMAP and MDS, SNE and t-SNE	PLSR, KNN, LDA, NB, DT, SVR, SVM, RF, LSSVM, LWR, FNN, ResNet, CNN and DNN
[76]	Grain products, forages, oil, fruits, vegetables, sugarcane seeds, coffee, tea, spices, black/green tea, grapes, apples, wheat flour, rice and barley	multivariate calibration of spectral data, standard normal variate transformation (SNV), multiplicative scatter correction (MSC), smoothing, derivative, wavelet transforms (WT), and orthogonal signal correction (OSC)	ANN, BP-ANN, GA-ANN, RBFNN, AdaBoost, SVM, LA, ELM,SLFN, LS-SVR, SVM, linear, radial basis function (RBF), normalized polynomial, sigmoid, GaussiansRBF, and string kernels
[62]	Condiments, spices and herbs	PCA, HCA, parallel factor analysis(PARAFAC), MPLS, PLS, ANOVA, t-test, straight line subtraction(SLS), constant offset elimination(COE), and minimum-maximum normalization (MMN)	ANN, kNN, PLS regression, PLS-DA, HCA, PCA, LDA, k-means cluster analysis (KM-CA) and DA
[87]	Fruits	computer vision systems	Adaptive Neuro Fuzzy Inference System (ANFIS)
[70]	Vegetables	CNN	ResNet-152, AlexNet-SVM classifier and hybrid CNN-SSAE
[58]	Apples, cucumbers, spinach and wheat	PCA, PLSR	PLSDA, ANN, LD and PCA

Figure 10. Statistics about evaluation metrics and the use of K-fold Cross Validation in the research papers.

Figure 10. Statistics about evaluation metrics and the use of K-fold Cross Validation in the research papers.

The results are best categorized by how data was gathered. However, in most cases, data acquisition stems from a chemical analytical approach, mostly spectroscopy-based approaches, resulting in structured data in the form of numerical values or unstructured data in the form of images. Thus, the results are reported following the taxonomy outlined in Section 2.1. Each subsection that follows, gathers the research papers that use the specific spectroscopic approach, and its variants if any, combined with various ML methods for food safety purposes.

4.4.1. Raman Spectroscopy

In earlier studies, Raman spectroscopy was used in combination with classical machine learning approaches to enhance food pathogens’ detection. In [57], Principle Component Analysis (PCA) was applied in combination with Linear discriminate analysis (LDA), Support Vector Machines (SVM) and a simple Artificial Neural Network (ANN) architecture for classification of Bacillus anthracis endospores and their products. Also, Raman Spectroscopy spectra was preprocessed using first derivative (D1) and Savitzky–Golay smoothing function and second $\left(2\right)-$order polynomial to enhance spectra resolution and eliminate baseline and linear slope effects, respectively [72]. The resulting signal was used as input for Partial least squares (PLS), Synergy interval partial least squares (siPLS), Ant colony optimization-siPLS (ACO-siPLS) to quantify the level of maize contamination by zearalenone. On the other hand, after applying Savitzky–Golay smoothing function on the spectral information, a stacking approach combined with K-nearest neighbors (KNN) and Support Vector Machines (SVM) was proposed in [116], to distinguish between Escherichia coli and Brucellasuis vaccine. Later studies investigated the use of complex ANN-based models to enhance classification and quantification performances. In [78], a simple PCA approach was used to categorize three genera (Arcobacter, Campylobacter and Helicobacter), then a one-dimensional Convolution Neural Network (1D-CNN) and a fully connected Artificial Neural Networks (ANN) were used to classify 18 of Arcobacter species and quantify their ratio in the bacterial mixture [78]. In another study, raw Raman spectroscopy was used as an input to fully connected ANN, Genetic Algorithm-ANN (GA-ANN), Particle Swarm Optimization-ANN (PSO-ANN) to distinguish between 12 strains of five bacteria genera, including (Escherichia, Listeria, Vibrio, Shigella, and Salmonella) [96].

In addition, in the cases where faster sampling, higher resolution and better signal-to-noise ration are needed, Fourier Transform (FT)-Raman is often used with promising results. In an older work [49], proposed a first attempt to use FT-Raman for a non-destructive characterization and differentiation of six different microorganisms, including the pathogen Escherichia coli on whole apples. PCA and Canonical Variate (CV) to plot and cluster the data in two-dimensional scatter-plot.

Furthermore, a more sensitive version of Raman spectroscopy, namely surface-enhanced Raman Spectroscopy (SERS) can be used in the cases where sensitivity, selectivity and rapid analysis is needed. In an older work [55], SERS was used to detect and discriminate among five Bacillus spores (B. cereus ATCC 13061, B. cereus ATCC 10876, B. cereus sp., B. subtilis sp., and B. stearothermophilus sp.). Standard data preparation techniques were conducted, such as normalization, binning, smoothing, and second-derivative transformation, before using PCA and Hierarchical Cluster Analysis (HCA) to cluster the data into three groups. However, a recent comparative study [79], demonstrates the benefit of using Deep learning models such as CNNs, fully convolutional network (FCN) and Principal Component Analysis Network (PCANet) to determine their abilities to measure pirimiphos-methyl in wheat extract in the two input forms of one-dimensional vector or two-dimensional matrix. As opposed to classical ML methods such as Random Forests (RF), KNN and SVM.

On the other hand, Single-cell Raman spectroscopy (SCRS) has also been used in a recent work [99] to discriminate between 23 common strains from 7 genera of foodborn bacteria (Escherichia, Listeria, Staphylococcus, Cronobacter, Vibrio, Shigella and Salmonella) at the single cell level. Kernel PCA (KPCA) was used for nonlinear feature extractino followed by a Decision Tree (DT) algorithm with promising results.

In addition, Low Resolution Raman spectroscopy (LRRS) also been used in combination with SVM Discriminate Analysis to rapidly identify harmful cyanobacterial species and quantify their presence, demonstrating the potential of LRRS technology for real-time detection of contaminant species within microalgal bioreactors.

4.4.2. visibe/Near-Infrared Spectroscopy

Visibe/near-infrared spectroscopy (Vis/NIR) is of valuable usage for food safety, especially when a broad spectral range analysis is needed., It has been used in combination with LDA and Partial Least Square Regression (PLSR) for on-line detection of Aspergillus spp. and Fusarium spp. contamination in stored maize [86]. LDA was used for classification results of maize samples according to specie of infected fungal strain and infection level. PLSR was used for the respective determination of colony counts. Also, in [84], Vis/NIR was considered with PCA in combination with various data pre-processing techniques such as, of moving average (MA), multiplicative scatter correction (MSC), standard normal variate (SNV), first derivative (D1), second derivative (D2), savitzky-golay (SG) and their combination were considered based on PCA results. The prepared data was the input to PLS-DA algorithm, as well as three of variable selection-based variants (iPLSDA, GA-PLSDA and VIP-PLSDA) to detect contaminants in Persian leek.

On the other hand, Recent studies explored the usage of Near-Infrared Spectroscopy (NIR) coupled with computer vision in food safety applications. In [106], they used a low-cost NIR sensors (NIRONE S2 and S2.5) to acquire spectral with wavelength 1550–1950 nm and 2000–2450 nm. Standard preprocessing approaches were applied such as auto scaling, mean centring, Savitzky-Golay, Standard Normal Variate (SNV), 1st and 2nd derivatives. The objective is garlic powder contamination, especially allergen contamination such as peanut powder. Thus five classification models were used (KNN, SVM, LDA, PLS-DA and DT) to, first, detecting the presence of peanut powder in garlic powder, then identifying whether the present is high (2-20%) or low (0.01-1%). In the latter both cases, a PLSR-based regression model was developed to quantify the presence concentration. Similarly, a Deep Learning-based approach was proposed in [107] for in-line allergen classification of agri-food powders, combining domain-adversarial neural networks (DANN) and semi-supervised generative adversarial neural networks (SGANN). In addition, two DL approaches were proposed in [98,111]. Namely, two-dimensional Markov transition field -CNN (2D-MTF-CNN) and a modified version of FCN (U-net) to monitor the aflatoxin B1 (AFB1) content in maize and identify food foreign contaminants (metallic iron, polypropylene plastic, and hair) on the surface of bread, respectively.

NIR spectroscopy in the diffuse reflectance mode has been used [67] for soluble solid content and total acid content analysis of fruits. After reducing the dimension of the acquired data to the leading three principal components, Back Propagation Neural Network (BPNN) and Generalized Regression Neural Network (GRNN) were proposed and compared in predicting the values of SSC and TAC in 3 cultivars of pears.

Furthermore, earlier works [50,51] investigate the usage of Fourier Transform Infrared spectroscopy (FTIR) coupled with complex ANN methods to identify five pathogenic bacteria (Enterococcus faecium, Salmonella enteritidis, Bacillus cereus, Yersinia enterocolitis, and Shigella)[50], as well as to quantify four food pathogens (E. coli O26, Salmonella typhimurium, Yersinia enterocolitis, and Shigella boydii) [51]. In both works, Probabilistic Neural Networks (PNNs) were developed and tested. FTIR has been used for aflatoxin contamination detection in figs [60]. Forward feature selection (FFS) method was used to reduce features in spectra space, followed by three linear classifers, namely Linear Discriminant Classifier (LDC), Logarithmic Linear Classifier (LOGLC) and Quadratic Discriminant Classifier (QDC). Also, it was coupled with smoothing and standard normal variate (SNV) for noise removal, followed by SVM and PLSDA to characterize and differentiate between Bacillus subtilis and Escherichia coli cell suspensions, in food spoilage context [90]. The work [71] have also showed the benefits of using FTIR combined with five classification approaches, namely Adaptive boosting (AdaBoost), Random Forests (RF), SVM, Multilayer perceptrons (MLPs) for the automated classification of contaminated maize. In a latter study [110], FTIR spectroscopy-based IR biotyper system was used to successfully classifying a total of 958 characterized Salmonella enterica isolates (25 serogroups and 138 serovars). PCA and LDA were applied for visualization porpuses, followed by SVM and ANNs for classification. Also, an earlier attempt to combine FTIR photoacoustic spectroscopy (FTIR-PAS) with unsupervised analysis (PCA and canonical variate analysis) was explored in [48] to identify various bacteria (Lactobacillus casei, Bacillus cereus, and Escherichia coli), fungi (Aspergillus niger and Fusarium verticilliodes) and yeast (Saccharomyces cerevisiae) on apple surface, with promising results. However, to the knowledge of the authors, not subsequent research was conducted using this technique.

4.4.3. Time-Domain Spectroscopy (THz–TDS)

Time-domain spectroscopy (THz–TDS) system can also be used in conjunction with ML approaches for food safety. Due to its spectral range, sensitivity and chemical specificity, it is an appealing alternative for data acquisition. In [102], they proposed a novel metamaterial sensor to analyse multi-resonance dips in spectra obtained using time-domain spectroscopy (THz–TDS) coupled with Mean Shift (MS) to investigate the presence of Carbendazim’s residue in crops. Also, Soybean oil contamination by aflatoxin B1 (AFB1) was investigated using the same spectroscopic method [74]. Student Stochastic Neighborhood Embedding (t-SNE) Dimensionality Reduction (DR) methods were applied, followed by Back Propagation Neural Network (BPNN), Least Squares SVM (LS-SVM) and RF for classification purposes. As opposed to identification and classification problems, time-domain spectroscopy (THz–TDS) systems was used in tandem Multiple Linear Regressions (MLR), PLS and LS-SVM for measuring benzoic acid (BA) additive in wheat flour [75]. In a recent study [104], used TPS systems with Singular value decomposition (SVD), Non-negative matrix factorization (NMF), Self-modeling mixture analysis (SMMA) and Support vector machine for regression (SVR), as preventative measure. That is to identify and quantify the right components of preservatives (sorbic acid, potassium sorbate and sodium benzoate) to precisely enhance antimicrobial effect for merchandise safety.

4.4.4. Fluorescence Spectroscopy

Fluorescence spectroscopy, which focuses on the measurement of the emitted light (fluorescence) from a sample after it has been excited by an external energy source, can also be used to acquire data for food contamination analysis. A recent work [85], presents a methodology for the analysis of fluorescence spectra of slurred almonds under 375 nm wavelength excitation for optical detection of Aflatoxins B in grained almonds. This application is different than conventional classification framework, in the sense that sample labels for contaminated or not contaminated are generated based on multiple threshold values, thus a single sample could have a vector of labels corresponding to each threshold value. This is refereed to as multi-expert learning [117]. In this context, Support vector Machines (SVM) was used with majority vote. On the other hand, other techniques of analyzing materials have been used, particularly, based on the interaction of microwaves with samples. Unlike spectroscopy, Microwave Sensing Systems operates in the microwave frequency range, typically from hundreds of MHz to tens of GHz. Recently, a microwave sensing approach coupled with ANNs for food safety has been proposed in [97], exploiting the dielectric contrast between the potential intrusion and the surrounding matter of packaged food. In addition, nuclear magnetic resonance (NMR) spectroscopy, which is a prominent analytical approach, was applied in a recent work [92] to distinguish between pathogenic and non-pathogenic, using PCA and ANNs.

4.4.5. Nuclear Magnetic Resonance (NMR)

Nuclear Magnetic Resonance (NMR) can be of great importance in food safety context due to its ability to provide detailed molecular information in non-destructive manner. However, compared to the above categories, NMR is somewhat less used in the literature. Only one study [92] explored the use of NMR spectra in combination with Artificial Neural Networks to distinguish between 10 different microbial strains such as Bacillus, Salmonella and Yersinia, among others in food based on metabolite profiles. For this type of data, prior preparation is necessary, like scaling spectra to the internal concentration standard (TSP), removing noise bins, standardization, and PCA for visualization. The proposed ANNs model, with hidden layers of 800 neurons, ReLu functions, and two dense layers, was compared with two classical Machine Learning algorithms (RF and SVM) with slight differences in performance.

4.4.6. Hyper-Spectral Imaging

Optical spectroscopic techniques have been recently exploited for food safety as an advanced promising tool. Due to the enhanced spectral resolution and improved spacial information Hyper-spectral imaging, combined with AI tools, is increasingly appealing for food safety application. The first application was as early as 2002 [47], where hyperspectral imaging was used to characterize spectral features, and multispectral imaging combined with PCA for detection of defects on three apple cultivars, namely Golden Delicious, Red Delicious, and Gala. Recently, an ANN-based method using FTIR-hyperspectral data was proposed in 2018, for rapid and cost effective diagnosis of pathogenic bacteria [68]. Also, In [83] active thermography and infrared camera were used to capture thermal images for analysis using a multi-view learning-based autoencoder (MVAE) for defect detection.

On the other hand, a study used Visible and NIR (VNIR) hyperspectral imaging to determine the presence of viral particles in a fluid suspension as well as on a surface upon complete evaporation of its water content [93]. In contrast with the previous studies which proved the effectiveness of using HSI to detect the presence of fungi or bacteria, detecting the presence of virus, which is two orders magnitude bellow bellow fungi and bacteria, can be crucial to prevent the spread of plant diseases. The acquired VNIR-HSI data was used in combination with PLSDR and FFNN to detect the presence of viruses in addition to the analysis of averaged spectra for quantifcation of the viral load [93].

4.4.7. Comparative Studies

In the light of recent developments and applications of Machine learning in food safety, comparative studies are of great importance to understand and assess the viability of the techniques. In [108], a thorough comparative study was conducted using four different Hyper-spectral imaging techniques (Fluorescence, VNIR, SWIR and Raman) combined with five classification approaches (LDA, LSVM, QDA, and QSVM), in addition to four simple pre-processing techniques. On the, the study in [115] provides a comparative assessment of spectroscopy-based techniques and machine learning approaches for evaluating the microbiological spoilage of ready-to eat leafy vegetables (baby spinach and rocket). In this study Fourier-transform infrared (FTIR), near-infrared (NIR), visible (VIS) spectroscopy and multispectral imaging (MSI) were used, with only two ML algorithms (SVR and PLSR).

4.4.8. Electro-Analytical Methods

The data used in [80] is gathered using the daily inspection of food safety obtained from the Analysis and Testing Institute of one province in China, which include information about manufacturers information, origin information, product information, production date, inspection items, inspection results, among others. The aim of this study is to: first build a AHP-ELM model to distinguish between three types of food safety risks, namely heavy metal pollution, chemical contaminant pollution and pathogenic bacteria pollution. Then, constructing a AHP-ELM-based model for food safety warning. In an earlier study [54], Microelectrode arrays (MEAs) obtained from Multichannel Systems GmBH were used to measure electrical activity of cortical networks grown in a controlled environment (in vitro). The MEAs measure the electrical spikes of Lyophilized Botulism toxin (BoNT A) group for further statistical analysis in contrast with a controlled group without toxins. Furthermore, the use of cortical networks as a biosensor for botulinum toxin offers several advantages. First, the networks can be grown in a controlled environment, allowing for reproducible experiments. Second, the networks can be easily manipulated and modified to study different aspects of toxin detection. Third, the electrical signals from the network can be recorded non-invasively, minimizing the potential harm to the tissue. This approach provides a promising tool for potential applications in toxin detection in food safety research.

On the other hand, few studies explore the potential for real time monitoring sensing system to provide early means to assess food safety [69,80]. A brief study [69] proposed a real time environment monitoring sensing system to monitor stored grain condition, and potentially increase its shelf-life. At first, sensors record the values of temperature, moisture content, $C{O}_2$ among others, and store the data in Ardinuo data logger periodically. Consequently, the stored data is communicated to a web server using WI-FI. Second, pre-processing techniques are applied in the microprocessor to reduce the inevitable noise generated by the different environment sensors. This is due to long term drifts, temporary electrical errors and effects of nearby sensors. Finally, a classification approach can be used to distinguish between 4 classes namely, no spoilage, early spoilage, severe spoilage and early insect infestation. A more recent study [80] proposed an edge IoT and machine learning based approach for food quality monitoring system to avoid food waste, which reaches 50% for root crops, fruits, and vegetables. First, three sensors are in place to gather environmental data, namely gas, temperature and humidity sensors, after which any missing entry is replaced with the median value of the feature. Then, Four classification algorithms are considered to categorize the results into three classes (fresh, semi-fresh, and spoiled), namely linear SVM, RBF-SVM, logistic regression and Random Forests (RF). To ensure real-time monitoring, the results are communicated to the user through an android application.

5. Research Gaps and Challenges

6. Conclusions and Future Work

References

1. Garcia, S.N.; Osburn, B.I.; Jay-Russell, M.T. One health for food safety, food security, and sustainable food production. Frontiers in Sustainable Food Systems 2020, p. 1.
2. Hargreaves, S.M.; Rosenfeld, D.L.; Moreira, A.V.B.; Zandonadi, R.P. Plant-based and vegetarian diets: An overview and definition of these dietary patterns. European journal of nutrition 2023, 62, 1109–1121. [Google Scholar] [CrossRef] [PubMed]
3. Matthews, P.J.; Ghanem, M.E. Perception gaps that may explain the status of taro (Colocasia esculenta) as an “orphan crop”. Plants, People, Planet 2021, 3, 99–112. [Google Scholar] [CrossRef]
4. Neufeld, L.M.; Hendriks, S.; Hugas, M. Healthy Diet: A Definition for the United Nations Food Systems Summit 2021. A Paper from the Scientific Group of the UN Food Systems Summit 2021. [Google Scholar]
5. FAO. Thinking about the future of food safety – A foresight report, 2022. [CrossRef]
6. Kamala, K.; Kumar, V.P. Food products and food contamination. In Microbial Contamination and Food Degradation; Elsevier, 2018; pp. 1–19.
7. Bintsis, T. Microbial pollution and food safety. AIMS microbiology 2018, 4, 377. [Google Scholar] [CrossRef] [PubMed]
8. Turek, C.; Stintzing, F.C. Stability of essential oils: a review. Comprehensive reviews in food science and food safety 2013, 12, 40–53. [Google Scholar] [CrossRef]
9. Clapp, J.; Moseley, W.G.; Burlingame, B.; Termine, P. The case for a six-dimensional food security framework. Food Policy 2021, p. 102164.
10. Chatterjee, A.; Abraham, J. Microbial contamination, prevention, and early detection in food industry. In Microbial Contamination and Food Degradation; Elsevier, 2018; pp. 21–47.
11. Chitrakar, B.; Zhang, M.; Bhandari, B. Improvement strategies of food supply chain through novel food processing technologies during COVID-19 pandemic. Food Control 2021, 125, 108010. [Google Scholar] [CrossRef]
12. Surampalli, R.Y.; Zhang, T.C.; Goyal, M.K.; Brar, S.K.; Tyagi, R. Sustainability: Fundamentals and applications; John Wiley & Sons, 2020.
13. Teena, M.; Manickavasagan, A.; Mothershaw, A.; El Hadi, S.; Jayas, D. Potential of machine vision techniques for detecting fecal and microbial contamination of food products: a review. Food and Bioprocess Technology 2013, 6, 1621–1634. [Google Scholar] [CrossRef]
14. Craig, A.P.; Franca, A.S.; Irudayaraj, J. Surface-enhanced Raman spectroscopy applied to food safety. Annual review of food science and technology 2013, 4, 369–380. [Google Scholar] [CrossRef] [PubMed]
15. Brousseau, J.L.; Vidon, S.; Leblanc, R. Investigation of the chemical nature of two-dimensional polymerized octadecyltrimethoxysilane Langmuir films by inelastic electron tunneling spectroscopy. The Journal of chemical physics 1998, 108, 7391–7396. [Google Scholar] [CrossRef]
16. Ojanen, P.; Mäkiranta, P.; Penttilä, T.; Minkkinen, K. Do logging residue piles trigger extra decomposition of soil organic matter? Forest Ecology and Management 2017, 405, 367–380. [Google Scholar] [CrossRef]
17. Świeca, M.; Sęczyk, Ł.; Gawlik-Dziki, U.; Dziki, D. Bread enriched with quinoa leaves–The influence of protein–phenolics interactions on the nutritional and antioxidant quality. Food chemistry 2014, 162, 54–62. [CrossRef]
18. Aghayee, S.; Benadiba, C.; Notz, J.; Kasas, S.; Dietler, G.; Longo, G. Combination of fluorescence microscopy and nanomotion detection to characterize bacteria. Journal of Molecular Recognition 2013, 26, 590–595. [Google Scholar] [CrossRef]
19. Guo, R.; McGoverin, C.; Swift, S.; Vanholsbeeck, F. A rapid and low-cost estimation of bacteria counts in solution using fluorescence spectroscopy. Analytical and bioanalytical chemistry 2017, 409, 3959–3967. [Google Scholar] [CrossRef]
20. Christensen, J.; Becker, E.M.; Frederiksen, C. Fluorescence spectroscopy and PARAFAC in the analysis of yogurt. Chemometrics and Intelligent Laboratory Systems 2005, 75, 201–208. [Google Scholar] [CrossRef]
21. Gismondi, A.; De Rossi, S.; Canuti, L.; Novelli, S.; Di Marco, G.; Fattorini, L.; Canini, A. From Robinia pseudoacacia L. nectar to Acacia monofloral honey: Biochemical changes and variation of biological properties. Journal of the Science of Food and Agriculture 2018, 98, 4312–4322. [Google Scholar] [CrossRef]
22. Su, W.H.; He, H.J.; Sun, D.W. Non-destructive and rapid evaluation of staple foods quality by using spectroscopic techniques: a review. Critical reviews in food science and nutrition 2017, 57, 1039–1051. [Google Scholar] [CrossRef] [PubMed]
23. Grundas, S.; Stępniewski, A. Advances in agrophysical research; BoD–Books on Demand, 2013.
24. Kim, H.K.; Choi, Y.H.; Verpoorte, R. NMR-based metabolomic analysis of plants. Nature protocols 2010, 5, 536–549. [Google Scholar] [CrossRef] [PubMed]
25. Lindgren, F.; Rännar, S. Alternative partial least-squares (PLS) algorithms. 3D QSAR in Drug Design: Recent Advances 1998, pp. 105–113.
26. Tan, W.K.; Husin, Z.; Yasruddin, M.L.; Ismail, M.A.H. Recent technology for food and beverage quality assessment: a review. Journal of Food Science and Technology 2022, pp. 1–14.
27. Wang, K.; Pu, H.; Sun, D.W. Emerging spectroscopic and spectral imaging techniques for the rapid detection of microorganisms: An overview. Comprehensive reviews in food science and food safety 2018, 17, 256–273. [Google Scholar] [CrossRef]
28. Wang, Y.; Ravindranath, S.; Irudayaraj, J. Separation and detection of multiple pathogens in a food matrix by magnetic SERS nanoprobes. Analytical and bioanalytical chemistry 2011, 399, 1271–1278. [Google Scholar] [CrossRef]
29. Liu, Y.; Pu, H.; Sun, D.W. Hyperspectral imaging technique for evaluating food quality and safety during various processes: A review of recent applications. Trends in food science & technology 2017, 69, 25–35. [Google Scholar]
30. Jiang, Y.; Li, G.; Ge, H.; Wang, F.; Li, L.; Chen, X.; Lu, M.; Zhang, Y. Machine learning and application in terahertz technology: A review on achievements and future challenges. IEEE Access 2022, 10, 53761–53776. [Google Scholar] [CrossRef]
31. Wang, H.P.; Chen, P.; Dai, J.W.; Liu, D.; Li, J.Y.; Xu, Y.P.; Chu, X.L. Recent advances of chemometric calibration methods in modern spectroscopy: Algorithms, strategy, and related issues. TrAC Trends in Analytical Chemistry 2022, p. 116648.
32. Al-Awadhi, M.A.; Deshmukh, R.R. A Review on Modern Analytical Methods for Detecting and Quantifying Adulteration in Honey. 2021 International Conference of Modern Trends in Information and Communication Technology Industry (MTICTI). IEEE, 2021, pp. 1–6.
33. Wu, Q.; Xie, L.; Xu, H. Determination of toxigenic fungi and aflatoxins in nuts and dried fruits using imaging and spectroscopic techniques. Food chemistry 2018, 252, 228–242. [Google Scholar] [CrossRef] [PubMed]
34. Xing, F.; Yao, H.; Liu, Y.; Dai, X.; Brown, R.L.; Bhatnagar, D. Recent developments and applications of hyperspectral imaging for rapid detection of mycotoxins and mycotoxigenic fungi in food products. Critical reviews in food science and nutrition 2019, 59, 173–180. [Google Scholar] [CrossRef] [PubMed]
35. Zhang, X.; Yang, J.; Lin, T.; Ying, Y. Food and agro-product quality evaluation based on spectroscopy and deep learning: A review. Trends in Food Science & Technology 2021, 112, 431–441. [Google Scholar]
36. An, D.; Zhang, L.; Liu, Z.; Liu, J.; Wei, Y. Advances in infrared spectroscopy and hyperspectral imaging combined with artificial intelligence for the detection of cereals quality. Critical Reviews in Food Science and Nutrition 2022, pp. 1–31.
37. Buzura, L.; Budileanu, M.L.; Potarniche, A.; Galatus, R. Python based portable system for fast characterisation of foods based on spectral analysis. 2021 IEEE 27th International Symposium for Design and Technology in Electronic Packaging (SIITME). IEEE, 2021, pp. 275–280.
38. Pan, T.; Wu, C.; Chen, Q. Sparse Reconstruction Using Block Sparse Bayesian Learning With Fast Marginalized Likelihood Maximization for Near-Infrared Spectroscopy. IEEE Transactions on Instrumentation and Measurement 2021, 71, 1–10. [Google Scholar] [CrossRef]
39. Nouri, H.; Guermazi, M.; Kallel, A.Y.; Hao, W.; Kanoun, O. Meat Freshness Assessment based on Impedance Spectroscopy and Distribution of Relaxation Times (DRT). 2022 International Workshop on Impedance Spectroscopy (IWIS). IEEE, 2022, pp. 41–45.
40. Wei, X.; Zhu, S.; Zhou, S.; Zheng, W.; Li, S. Identification of soybean origin by terahertz spectroscopy and chemometrics. IEEE Access 2020, 8, 184988–184996. [Google Scholar] [CrossRef]
41. Fengou, L.C.; Mporas, I.; Spyrelli, E.; Lianou, A.; Nychas, G.J. Estimation of the microbiological quality of meat using rapid and non-invasive spectroscopic sensors. IEEE Access 2020, 8, 106614–106628. [Google Scholar] [CrossRef]
42. Shen, J.; Li, M.; Li, Z.; Zhang, Z.; Zhang, X. Single convolutional neural network model for multiple preprocessing of Raman spectra. Vibrational Spectroscopy 2022, 121, 103391. [Google Scholar] [CrossRef]
43. Trigoso, T.C.; Cruz, J.O.; Miñano, H.A.; Silupu, W.C. Application of machine learning in the discrimination of citrus fruit juices: Uses of dielectric spectroscopy. 2020 IEEE Engineering International Research Conference (EIRCON). IEEE, 2020, pp. 1–4.
44. Suter, G.W. Review papers are important and worth writing. Environmental Toxicology and Chemistry 2013, 32, 1929–1930. [Google Scholar] [CrossRef]
45. Palmatier, R.W.; Houston, M.B.; Hulland, J. Review articles: Purpose, process, and structure, 2018.
46. Snyder, H. Literature review as a research methodology: An overview and guidelines. Journal of business research 2019, 104, 333–339. [Google Scholar] [CrossRef]
47. Mehl, P.; Chao, K.; Kim, M.; Chen, Y. Detection of defects on selected apple cultivars using hyperspectral and multispectral image analysis. Applied engineering in agriculture 2002, 18, 219. [Google Scholar]
48. Irudayaraj, J.; Yang, H.; Sakhamuri, S. Differentiation and detection of microorganisms using Fourier transform infrared photoacoustic spectroscopy. Journal of Molecular Structure 2002, 606, 181–188. [Google Scholar] [CrossRef]
49. Yang, H.; Irudayaraj, J. Rapid detection of foodborne microorganisms on food surface using Fourier transform Raman spectroscopy. Journal of Molecular Structure 2003, 646, 35–43. [Google Scholar] [CrossRef]
50. Gupta, M.J.; Irudayaraj, J.M.; Debroy, C.; Schmilovitch, Z.; Mizrach, A. Differentiation of food pathogens using FTIR and artificial neural networks. Transactions of the ASAE 2005, 48, 1889–1892. [Google Scholar] [CrossRef]
51. Gupta, M.J.; Irudayaraj, J.M.; Schmilovitch, Z.; Mizrach, A. Identification and quantification of foodborne pathogens in different food matrices using FTIR spectroscopy and artificial neural networks. Transactions of the ASABE 2006, 49, 1249–1255. [Google Scholar] [CrossRef]
52. Huang, Y.; Kangas, L.J.; Rasco, B.A. Applications of artificial neural networks (ANNs) in food science. Critical reviews in food science and nutrition 2007, 47, 113–126. [Google Scholar] [CrossRef]
53. Berrueta, L.A.; Alonso-Salces, R.M.; Héberger, K. Supervised pattern recognition in food analysis. Journal of chromatography A 2007, 1158, 196–214. [Google Scholar] [CrossRef]
54. Scarlatos, A.; Cadotte, A.; DeMarse, T.; Welt, B. Cortical networks grown on microelectrode arrays as a biosensor for botulinum toxin. Journal of Food Science 2008, 73, E129–E136. [Google Scholar] [CrossRef] [PubMed]
55. He, L.; Liu, Y.; Lin, M.; Mustapha, A.; Wang, Y. Detecting single Bacillus spores by surface enhanced Raman spectroscopy. Sensing and Instrumentation for Food Quality and Safety 2008, 2, 247–253. [Google Scholar] [CrossRef]
56. Siripatrawan, U. Self-organizing algorithm for classification of packaged fresh vegetable potentially contaminated with foodborne pathogens. Sensors and Actuators B: Chemical 2008, 128, 435–441. [Google Scholar] [CrossRef]
57. Stockel, S.; Schumacher, W.; Meisel, S.; Elschner, M.; Rosch, P.; Popp, J. Raman spectroscopy-compatible inactivation method for pathogenic endospores. Applied and environmental microbiology 2010, 76, 2895–2907. [Google Scholar] [CrossRef] [PubMed]
58. Feng, Y.Z.; Sun, D.W. Application of hyperspectral imaging in food safety inspection and control: a review. Critical reviews in food science and nutrition 2012, 52, 1039–1058. [Google Scholar] [CrossRef]
59. Shapaval, V.; Schmitt, J.; Møretrø, T.; Suso, H.; Skaar, I.; Åsli, A.; Lillehaug, D.; Kohler, A. Characterization of food spoilage fungi by FTIR spectroscopy. Journal of applied microbiology 2013, 114, 788–796. [Google Scholar] [CrossRef] [PubMed]
60. Güneş, A.; Kalkan, H.; Durmuş, E.; Bütükcan, M.B. Detection of aflatoxin contaminated figs using Near-Infrared (NIR) reflectance spectroscopy. 2013 International Conference on Electronics, Computer and Computation (ICECCO). IEEE, 2013, pp. 123–126.
61. Qin, J.; Chao, K.; Kim, M.S.; Lu, R.; Burks, T.F. Hyperspectral and multispectral imaging for evaluating food safety and quality. Journal of Food Engineering 2013, 118, 157–171. [Google Scholar] [CrossRef]
62. Reinholds, I.; Bartkevics, V.; Silvis, I.C.; van Ruth, S.M.; Esslinger, S. Analytical techniques combined with chemometrics for authentication and determination of contaminants in condiments: A review. Journal of Food Composition and Analysis 2015, 44, 56–72. [Google Scholar] [CrossRef]
63. Ma, J.; Sun, D.W.; Qu, J.H.; Liu, D.; Pu, H.; Gao, W.H.; Zeng, X.A. Applications of computer vision for assessing quality of agri-food products: a review of recent research advances. Critical reviews in food science and nutrition 2016, 56, 113–127. [Google Scholar] [CrossRef]
64. Ropodi, A.; Panagou, E.; Nychas, G.J. Data mining derived from food analyses using non-invasive/non-destructive analytical techniques; determination of food authenticity, quality & safety in tandem with computer science disciplines. Trends in Food Science & Technology 2016, 50, 11–25. [Google Scholar]
65. ElMasry, G.M.; Nakauchi, S. Image analysis operations applied to hyperspectral images for non-invasive sensing of food quality–A comprehensive review. Biosystems engineering 2016, 142, 53–82. [Google Scholar] [CrossRef]
66. Geng, Z.; Zhao, S.; Zhu, Q.; Han, Y.; Xu, Y.; He, Y. Early warning modeling and application based on analytic hierarchy process integrated extreme learning machine. 2017 Intelligent Systems Conference (IntelliSys). IEEE, 2017, pp. 738–743.
67. Shen, Y.; Tian, J.; Li, L.; Wu, Y.; Li, L. Feasibility of non-destructive internal quality analysis of pears by using near-infrared diffuse reflectance spectroscopy. 2017 9th International Conference on Modelling, Identification and Control (ICMIC). IEEE, 2017, pp. 31–36.
68. Lasch, P.; Stämmler, M.; Zhang, M.; Baranska, M.; Bosch, A.; Majzner, K. FT-IR hyperspectral imaging and artificial neural network analysis for identification of pathogenic bacteria. Analytical chemistry 2018, 90, 8896–8904. [Google Scholar] [CrossRef]
69. Kaushik, R.; Singhai, J. An approach for the development of a sensing system to monitor contamination in stored grain. 2019 6th International Conference on Signal Processing and Integrated Networks (SPIN). IEEE, 2019, pp. 880–884.
70. Zhou, L.; Zhang, C.; Liu, F.; Qiu, Z.; He, Y. Application of deep learning in food: a review. Comprehensive reviews in food science and food safety 2019, 18, 1793–1811. [Google Scholar] [CrossRef]
71. Öner, T.; Thiam, P.; Kos, G.; Krska, R.; Schwenker, F.; Mizaikoff, B. Machine learning algorithms for the automated classification of contaminated maize at regulatory limits via infrared attenuated total reflection spectroscopy. World Mycotoxin Journal 2019, 12, 113–122. [Google Scholar] [CrossRef]
72. Guo, Z.; Wang, M.; Wu, J.; Tao, F.; Chen, Q.; Wang, Q.; Ouyang, Q.; Shi, J.; Zou, X. Quantitative assessment of zearalenone in maize using multivariate algorithms coupled to Raman spectroscopy. Food chemistry 2019, 286, 282–288. [Google Scholar] [CrossRef]
73. Wan-dan, Z.; Ru-jin, S.; Cheng-wei, W.; Qian-xue, L.; Zhi-ping, X. Raman Spectroscopy Classification of Foodborne Pathogenic Bacteria Based on PCA-Stacking Model. 2019 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS). IEEE, 2019, pp. 304–307.
74. Liu, W.; Zhao, P.; Wu, C.; Liu, C.; Yang, J.; Zheng, L. Rapid determination of aflatoxin B1 concentration in soybean oil using terahertz spectroscopy with chemometric methods. Food Chemistry 2019, 293, 213–219. [Google Scholar] [CrossRef]
75. Sun, X.; Zhu, K.; Liu, J.; Hu, J.; Jiang, X.; Liu, Y.; Gong, Z. Terahertz spectroscopy determination of benzoic acid additive in wheat flour by machine learning. Journal of Infrared, Millimeter, and Terahertz Waves 2019, 40, 466–475. [Google Scholar] [CrossRef]
76. Zareef, M.; Chen, Q.; Hassan, M.M.; Arslan, M.; Hashim, M.M.; Ahmad, W.; Kutsanedzie, F.Y.; Agyekum, A.A. An overview on the applications of typical non-linear algorithms coupled with NIR spectroscopy in food analysis. Food Engineering Reviews 2020, 12, 173–190. [Google Scholar] [CrossRef]
77. Le, B.T. Application of deep learning and near infrared spectroscopy in cereal analysis. Vibrational Spectroscopy 2020, 106, 103009. [Google Scholar] [CrossRef]
78. Wang, K.; Chen, L.; Ma, X.; Ma, L.; Chou, K.C.; Cao, Y.; Khan, I.U.; Gölz, G.; Lu, X. Arcobacter identification and species determination using Raman spectroscopy combined with neural networks. Applied and environmental microbiology 2020, 86, e00924–20. [Google Scholar] [CrossRef]
79. Weng, S.; Yuan, H.; Zhang, X.; Li, P.; Zheng, L.; Zhao, J.; Huang, L. Deep learning networks for the recognition and quantitation of surface-enhanced Raman spectroscopy. Analyst 2020, 145, 4827–4835. [Google Scholar] [CrossRef] [PubMed]
80. Sahu, B.; Tiwari, A.; Raheja, J.; Kumar, S. Development of Machine Learning & Edge IoT Based Non-destructive Food Quality Monitoring System using Raspberry Pi. 2020 IEEE International Conference on Computing, Power and Communication Technologies (GUCON). IEEE, 2020, pp. 449–455.
81. Yu, X.L.; Sun, D.W.; He, Y. Emerging techniques for determining the quality and safety of tea products: A review. Comprehensive Reviews in Food Science and Food Safety 2020, 19, 2613–2638. [Google Scholar] [CrossRef]
82. Nturambirwe, J.F.I.; Opara, U.L. Machine learning applications to non-destructive defect detection in horticultural products. Biosystems engineering 2020, 189, 60–83. [Google Scholar] [CrossRef]
83. Wu, H.; Zheng, K.; Sfarra, S.; Liu, Y.; Yao, Y. Multiview learning for subsurface defect detection in composite products: A challenge on thermographic data analysis. IEEE Transactions on Industrial Informatics 2020, 16, 5996–6003. [Google Scholar] [CrossRef]
84. Shen, F.; Huang, Y.; Jiang, X.; Fang, Y.; Li, P.; Liu, Q.; Hu, Q.; Liu, X. On-line prediction of hazardous fungal contamination in stored maize by integrating Vis/NIR spectroscopy and computer vision. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 2020, 229, 118012. [Google Scholar] [CrossRef] [PubMed]
85. Bertani, F.; Businaro, L.; Gambacorta, L.; Mencattini, A.; Brenda, D.; Di Giuseppe, D.; De Ninno, A.; Solfrizzo, M.; Martinelli, E.; Gerardino, A. Optical detection of aflatoxins B in grained almonds using fluorescence spectroscopy and machine learning algorithms. Food Control 2020, 112, 107073. [Google Scholar] [CrossRef]
86. Rahi, S.; Mobli, H.; Jamshidi, B.; Azizi, A.; Sharifi, M. Achieving a robust Vis/NIR model for microbial contamination detection of Persian leek by spectral analysis based on genetic, iPLS algorithms and VIP scores. Postharvest Biology and Technology 2021, 175, 111413. [Google Scholar] [CrossRef]
87. Mavani, N.R.; Ali, J.M.; Othman, S.; Hussain, M.; Hashim, H.; Rahman, N.A. Application of artificial intelligence in food industry—A guideline. Food Engineering Reviews 2022, 14, 134–175. [Google Scholar] [CrossRef]
88. Ge, H.; Lv, M.; Lu, X.; Jiang, Y.; Wu, G.; Li, G.; Li, L.; Li, Z.; Zhang, Y. Applications of THz spectral imaging in the detection of agricultural products. Photonics. Multidisciplinary Digital Publishing Institute, 2021, Vol. 8, p. 518.
89. Rivola, M.; Ibba, P.; Lugli, P.; Petti, L. Bioimpedance data statistical modelling for food quality classification and prediction. 2021 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 2021, pp. 1–5.
90. Xu, J.L.; Herrero-Langreo, A.; Lamba, S.; Ferone, M.; Scannell, A.G.; Caponigro, V.; Gowen, A.A. Characterisation and classification of foodborne bacteria using reflectance FTIR microscopic imaging. Molecules 2021, 26, 6318. [Google Scholar] [CrossRef] [PubMed]
91. Magnus, I.; Virte, M.; Thienpont, H.; Smeesters, L. Combining optical spectroscopy and machine learning to improve food classification. Food Control 2021, 130, 108342. [Google Scholar] [CrossRef]
92. Wang, D.; Greenwood, P.; Klein, M.S. Deep Learning for Rapid Identification of Microbes Using Metabolomics Profiles. Metabolites 2021, 11, 863. [Google Scholar] [CrossRef] [PubMed]
93. Gomez-Gonzalez, E.; Fernandez-Muñoz, B.; Barriga-Rivera, A.; Navas-Garcia, J.M.; Fernandez-Lizaranzu, I.; Munoz-Gonzalez, F.J.; Parrilla-Giraldez, R.; Requena-Lancharro, D.; Guerrero-Claro, M.; Gil-Gamboa, P.; others. Hyperspectral image processing for the identification and quantification of lentiviral particles in fluid samples. Scientific Reports 2021, 11, 1–12.
94. Guo, Z.; Guo, C.; Sun, L.; Zuo, M.; Chen, Q.; El-Seedi, H.R.; Zou, X. Identification of the apple spoilage causative fungi and prediction of the spoilage degree using electronic nose. Journal of Food Process Engineering 2021, 44, e13816. [Google Scholar] [CrossRef]
95. Li, H.; Hassan, M.M.; Wang, J.; Wei, W.; Zou, M.; Ouyang, Q.; Chen, Q. Investigation of nonlinear relationship of surface enhanced Raman scattering signal for robust prediction of thiabendazole in apple. Food chemistry 2021, 339, 127843. [Google Scholar] [CrossRef] [PubMed]
96. Vakilian, K.A. Metaheuristic Optimization to Improve Machine Learning in Raman Spectroscopic-based Detection of Foodborne Pathogens. 2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS). IEEE, 2021, pp. 1–5.
97. Ricci, M.; Vasquez, J.A.T.; Turvani, G.; Sirena, I.; Casu, M.R.; Vipiana, F. Microwave Sensing for Food Safety: a Neural Network Implementation. 2021 IEEE Conference on Antenna Measurements & Applications (CAMA). IEEE, 2021, pp. 444–447.
98. Yin, J.; Hameed, S.; Xie, L.; Ying, Y. Non-destructive detection of foreign contaminants in toast bread with near infrared spectroscopy and computer vision techniques. Journal of Food Measurement and Characterization 2021, 15, 189–198. [Google Scholar] [CrossRef]
99. Yan, S.; Wang, S.; Qiu, J.; Li, M.; Li, D.; Xu, D.; Li, D.; Liu, Q. Raman spectroscopy combined with machine learning for rapid detection of food-borne pathogens at the single-cell level. Talanta 2021, 226, 122195. [Google Scholar] [CrossRef] [PubMed]
100. Zareef, M.; Arslan, M.; Hassan, M.M.; Ahmad, W.; Ali, S.; Li, H.; Ouyang, Q.; Wu, X.; Hashim, M.M.; Chen, Q. Recent advances in assessing qualitative and quantitative aspects of cereals using nondestructive techniques: A review. Trends in Food Science & Technology 2021, 116, 815–828. [Google Scholar]
101. Nie, P.; Qu, F.; Lin, L.; He, Y.; Feng, X.; Yang, L.; Gao, H.; Zhao, L.; Huang, L. Trace identification and visualization of multiple benzimidazole pesticide residues on toona sinensis leaves using terahertz imaging combined with deep learning. International Journal of Molecular Sciences 2021, 22, 3425. [Google Scholar] [CrossRef] [PubMed]
102. Yang, R.; Li, Y.; Zheng, J.; Qiu, J.; Song, J.; Xu, F.; Qin, B. A Novel Method for Carbendazim High-Sensitivity Detection Based on the Combination of Metamaterial Sensor and Machine Learning. Materials 2022, 15, 6093. [Google Scholar] [CrossRef] [PubMed]
103. Kang, Z.; Zhao, Y.; Chen, L.; Guo, Y.; Mu, Q.; Wang, S. Advances in Machine Learning and Hyperspectral Imaging in the Food Supply Chain. Food Engineering Reviews 2022, 14, 596–616. [Google Scholar] [CrossRef]
104. Yan, H.; Fan, W.; Chen, X.; Wang, H.; Qin, C.; Jiang, X. Component spectra extraction and quantitative analysis for preservative mixtures by combining terahertz spectroscopy and machine learning. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 2022, 271, 120908. [Google Scholar] [CrossRef]
105. Zhang, C.; Zhao, W.; Dong, L. Design of Food Safety Supervision System in the Background of Big Data. 2022 International Conference on Artificial Intelligence in Everything (AIE). IEEE, 2022, pp. 413–418.
106. Rady, A.; Watson, N. Detection and quantification of peanut contamination in garlic powder using NIR sensors and machine learning. Journal of Food Composition and Analysis 2022, 114, 104820. [Google Scholar] [CrossRef]
107. Bowler, A.L.; Ozturk, S.; Rady, A.; Watson, N. Domain Adaptation for In-Line Allergen Classification of Agri-Food Powders Using Near-Infrared Spectroscopy. Sensors 2022, 22, 7239. [Google Scholar] [CrossRef]
108. Kim, Y.K.; Baek, I.; Lee, K.M.; Qin, J.; Kim, G.; Shin, B.K.; Chan, D.E.; Herrman, T.J.; Cho, S.k.; Kim, M.S. Investigation of reflectance, fluorescence, and Raman hyperspectral imaging techniques for rapid detection of aflatoxins in ground maize. Food Control 2022, 132, 108479. [Google Scholar] [CrossRef]
109. Adejimi, O.E.; Ignat, T.; Sadhasivam, G.; Zakin, V.; Schmilovitch, Z.; Shapiro, O.H. Low-Resolution Raman Spectroscopy for the detection of contaminant species in algal bioreactors. Science of The Total Environment 2022, 809, 151138. [Google Scholar] [CrossRef] [PubMed]
110. Cordovana, M.; Mauder, N.; Join-Lambert, O.; Gravey, F.; LeHello, S.; Auzou, M.; Pitti, M.; Zoppi, S.; Buhl, M.; Steinmann, J.; others. Machine learning-based typing of Salmonella enterica O-serogroups by the Fourier-Transform Infrared (FTIR) Spectroscopy-based IR Biotyper system. Journal of microbiological methods 2022, 201, 106564.
111. Wang, B.; Deng, J.; Jiang, H. Markov Transition Field Combined with Convolutional Neural Network Improved the Predictive Performance of Near-Infrared Spectroscopy Models for Determination of Aflatoxin B1 in Maize. Foods 2022, 11, 2210. [Google Scholar] [CrossRef] [PubMed]
112. Aviara, N.A.; Liberty, J.T.; Olatunbosun, O.S.; Shoyombo, H.A.; Oyeniyi, S.K. Potential application of hyperspectral imaging in food grain quality inspection, evaluation and control during bulk storage. Journal of Agriculture and Food Research 2022, p. 100288.
113. Pampoukis, G.; Lytou, A.E.; Argyri, A.A.; Panagou, E.Z.; Nychas, G.J.E. Recent advances and applications of rapid microbial assessment from a food safety perspective. Sensors 2022, 22, 2800. [Google Scholar] [CrossRef]
114. Hussain, M.; Zou, J.; Zhang, H.; Zhang, R.; Chen, Z.; Tang, Y. Recent Progress in Spectroscopic Methods for the Detection of Foodborne Pathogenic Bacteria. Biosensors 2022, 12, 869. [Google Scholar] [CrossRef] [PubMed]
115. Manthou, E.; Karnavas, A.; Fengou, L.C.; Bakali, A.; Lianou, A.; Tsakanikas, P.; Nychas, G.J.E. Spectroscopy and imaging technologies coupled with machine learning for the assessment of the microbiological spoilage associated to ready-to-eat leafy vegetables. International Journal of Food Microbiology 2022, 361, 109458. [Google Scholar] [CrossRef]
116. Shi, R.; Xia, F.; Zeng, W.; Qu, H. Raman spectroscopic classification of foodborne pathogenic bacteria based on PCA-Stacking model. Laser & Optoelectronics Progress 2019, 56, 043003. [Google Scholar]
117. Umaquinga-Criollo, A.C.; Tamayo-Quintero, J.D.; Moreno-García, M.N.; Aalaila, Y.; Peluffo-Ordóñez, D.H. Developments on Support Vector Machines for Multiple-Expert Learning. Intelligent Data Engineering and Automated Learning–IDEAL 2021: 22nd International Conference, IDEAL 2021, Manchester, UK, November 25–27, 2021, Proceedings 22. Springer, 2021, pp. 587–598.