Application of artificial neural network in food classification

Key components, formation pathways, affecting factors, and emerging analytical strategies for edible mushrooms aroma: A review

Aroma is one of the decisive factors affecting the quality and consumer acceptance of edible mushrooms. This review summarized the key components and formation pathways of edible mushroom aroma. It also elaborated on the affecting factors and emerging analytical strategies of edible mushroom aroma. A total of 1308 volatile organic compounds identified in edible mushrooms, 61 were key components. The formation of these compounds is closely related to fatty acid metabolism, amino acid metabolism, lentinic acid metabolism, and terpenoid metabolism. The aroma profiles of edible mushrooms were affected by genetic background, preharvest factors, and preservation methods. Molecular sensory science and omics techniques are emerging analytical strategies to reveal aroma information of edible mushrooms. This review would provide valuable data and insights for future research on edible mushroom aroma.

Modeling and Optimization of Triticale Wort Production Using an Artificial Neural Network and a Genetic Algorithm

Triticale grain, a wheat-rye hybrid, has been reported to comply very well with the requirements for modern brewing adjuncts. In this study, two triticale varieties, in both unmalted and malted forms, were investigated at various ratios in the grist, applying different mashing regimes and concentrations of the commercial enzyme Shearzyme® 500 L with the aim of evaluating their impact on wort production. In order to capture the complex relationships between the input (triticale ratio, enzyme ratio, mashing regime, and triticale variety) and output variables (wort extract content, wort viscosity, and free amino nitrogen (FAN) content in wort), the study aimed to implement the use of artificial neural networks (ANNs) to model the mashing process. Also, a genetic algorithm (GA) was integrated to minimize a specified multi-objective function, optimizing the mashing process represented by the ANN model. Among the solutions on the Pareto front, one notable set of solutions was found with objective function values of 0.0949, 0.0131, and 1.6812 for the three conflicting objectives, respectively. These values represent a trade-off that optimally balances the different aspects of the optimization problem. The optimized input variables had values of 23%, 9%, 1, and 3 for the respective input variables of triticale ratio, enzyme ratio, mashing regime, and triticale variety. The results derived from the ANN model, applying the GA-optimized input values, were 8.65% w/w for wort extract content, 1.52 mPa·s for wort viscosity, and 148.32 mg/L for FAN content in wort. Comparatively, the results conducted from the real laboratory mashing were 8.63% w/w for wort extract content, 1.51 mPa·s for wort viscosity, and 148.88 mg/L for FAN content in wort applying same input values. The presented data from the optimization process using the GA and the subsequent experimental verification on the real mashing process have demonstrated the practical applicability of the proposed approach which confirms the potential to enhance the quality and efficiency of triticale wort production.

Modelling Polyphenol Extraction through Ultrasound-Assisted Extraction by Machine Learning in Olea europaea Leaves

The study of the phenolic compounds present in olive leaves (Olea europaea) is of great interest due to their health benefits. In this research, different machine learning algorithms such as RF, SVM, and ANN, with temperature, time, and volume as input variables, were developed to model the extract yield and the total phenolic content (TPC) from experimental data reported in the literature. In terms of extract yield, the neural network-based ANNZ-L model presents the lowest root mean square error (RMSE) value in the validation phase (9.44 mg/g DL), which corresponds with a mean absolute percentage error (MAPE) of 3.7%. On the other hand, the best model to determine the TPC value was the neural network-based model ANNR, with an RMSE of 0.89 mg GAE/g DL in the validation phase (MAPE of 2.9%). Both models obtain, for the test phase, MAPE values of 4.9 and 3.5%, respectively. This affirms that ANN models would be good modelling tools to determine the extract yield and TPC value of the ultrasound-assisted extraction (UAE) process of olive leaves under different temperatures, times, and solvents.

Development of a Low-Cost Artificial Vision System as an Alternative for the Automatic Classification of Persian Lemon: Prototype Test Simulation

In the present research work, an algorithm of artificial neural network (ANN) has been developed based on the processing of digital images of Persian lemons with the aim of optimizing the quality control of the product. For this purpose, the physical properties (weight, thickness of the peel, diameter, length, and color) of 90 lemons selected from the company Esperanza de San José Ornelas SPR de RL (Jalisco, Mexico) were studied, which were divided into three groups (Category "extra", Category I, and Category II) according to their characteristics. The parameters of weight (26.50 ± 3.00 g), diameter/length (0.92 ± 0.08) and thickness of the peel (1.50 ± 0.29 mm) did not present significant differences between groups. On the other hand, the color (determined by the RGB and HSV models) presents statistically significant changes between groups. Due to the above, the proposed ANN correctly classifies 96.60% of the data obtained for each of the groups studied. Once the ANN was trained, its application was tested in an automatic classification process. For this purpose, a prototype based on the operation of a stepper motor was simulated using Simulink from Matlab, which is connected to three ideal switches powered by three variable pulse generators that receive the information from an ANN and provide the corresponding signal for the motor to turn to a specific position. Manual classification is a process that requires expert personnel and is prone to human error. The scientific development presented shows an alternative for the automation of the process using low-cost computational tools as a potential alternative.

Artificial-Neural-Network-Driven Innovations in Time-Varying Process Diagnosis of Low-K Oxide Deposition

To address the challenges in real-time process diagnosis within the semiconductor manufacturing industry, this paper presents a novel machine learning approach for analyzing the time-varying 10th harmonics during the deposition of low-k oxide (SiOF) on a 600 Å undoped silicate glass thin liner using a high-density plasma chemical vapor deposition system. The 10th harmonics, which are high-frequency components 10 times the fundamental frequency, are generated in the plasma sheath because of their nonlinear nature. An artificial neural network with a three-hidden-layer architecture was applied and optimized using k-fold cross-validation to analyze the harmonics generated in the plasma sheath during the deposition process. The model exhibited a binary cross-entropy loss of 0.1277 and achieved an accuracy of 0.9461. This approach enables the accurate prediction of process performance, resulting in significant cost reduction and enhancement of semiconductor manufacturing processes. This model has the potential to improve defect control and yield, thereby benefiting the semiconductor industry. Despite the limitations imposed by the limited dataset, the model demonstrated promising results, and further performance improvements are anticipated with the inclusion of additional data in future studies.

Neural network in food analytics

Neural network (i.e. deep learning, NN)-based data analysis techniques have been listed as a pivotal opportunity to protect the integrity and safety of the global food supply chain and forecast $11.2 billion in agriculture markets. As a general-purpose data analytic tool, NN has been applied in several areas of food science, such as food recognition, food supply chain security and omics analysis, and so on. Therefore, given the rapid emergence of NN applications in food safety, this review aims to provide a comprehensive overview of the NN application in food analysis for the first time, focusing on domain-specific applications in food analysis by introducing fundamental methodology, reviewing recent and notable progress, and discussing challenges and potential pitfalls. NN demonstrated that it has a bright future through effective collaboration between food specialist and the broader community in the food field, for example, superiority in food recognition, sensory evaluation, pattern recognition of spectroscopy and chromatography. However, major challenges impeded NN extension including void in the food scientist-friendly interface software package, incomprehensible model behavior, multi-source heterogeneous data, and so on. The breakthrough from other fields proved NN has the potential to offer a revolution in the immediate future.

Artificial Neural Networks for Predicting Food Antiradical Potential

Using an artificial neural network (ANN), the values of the antiradical potential of 1315 items of food and agricultural raw materials were calculated. We used an ANN with the structure of a “multilayer perceptron” (MLP) and with the hyberbolic tangent (Tanh) as an activation function. Values reported in the United States Food and Nutrient Database for Dietary Studies (FNDDS) were taken as input to the analysis. When training the ANN, 60 parameters were used, such as the content of plastic substances, food calories, the amount of mineral components, vitamins, the composition of fatty acids and additional substances presented in this database. The analysis revealed correlations, namely, a direct relationship between the value of the antiradical potential (ARP) of food and the concentration of dietary fiber (r = 0.539) and a negative correlation between the value of ARP and the total calorie content of food (r = −0.432) at a significance level of p < 0.001 for both values. The average ARP value for 10 product groups within the 95% CI (confidence interval) was ≈23–28 equivalents (in terms of ascorbic acid) per 1 g of dry matter. The study also evaluated the range of average values of the daily recommended intake of food components (according to Food and Agriculture Organization—FAO, World Health Organization—WHO, Russia and the USA), which within the 95% CI, amounted to 23.41–28.98 equivalents per 1 g of dry weight. Based on the results of the study, it was found that the predicted ARP values depend not only on the type of raw materials and the method of their processing, but also on a number of other environmental and technological factors that make it difficult to obtain accurate values.

Rapid quantification of dissolved solids and bioactives in dried root vegetable extracts using near infrared spectroscopy

Artificial neural networks (ANN) were developed for prediction of total dissolved solids, polyphenol content and antioxidant capacity of root vegetables (celery, fennel, carrot, yellow carrot, purple carrot and parsley) extracts prepared from the (i) fresh vegetables, (ii) vegetables dried conventionally at 50 °C and 70 °C, and (iii) the lyophilised vegetables. Two types of solvents were used: organic solvents (acetone mixtures and methanol mixtures) and water. Near-infrared (NIR) spectra were recorded for all samples. Principal Component Analysis (PCA) of the pre-treated spectra using Savitzky-Golay smoothing showed specific grouping of samples in two clusters (1st: extracts prepared using methanol mixtures and water as the solvents; 2nd: extracts prepared using acetone mixtures as the solvents) for all four types of extracts. Furthermore, obtained results showed that the developed ANN models can reliably be used for prediction of total dissolved solids, polyphenol content and antioxidant capacity of dried root vegetable extracts in relation to the recorded NIR spectra.

Liquid chromatographic methods coupled to chemometrics: a short review to present the key workflow for the investigation of wine phenolic composition as it is affected by environmental factors

The guarantee of wine authenticity arises great concern because of its nutritional and economic importance. Phenolic fingerprints have been used as a source of chemical information for various authentication issues, including botanical and geographical origin, as well as vintage age. The local environment affects wine production and especially its phenolic metabolites. Integrated analytical methodologies combined with chemometrics can be applied in wine fingerprinting studies for the determination and establishment of phenolic markers that contain comprehensive and standardized information about the wine profile and how it can be affected by various environmental factors. This review summarizes all the recent trends in the generation of chemometric models that have been developed for treating chromatographic data and have been used for the investigation of critical wine authenticity issues, revealing phenolic markers responsible for the botanical, geographical, and vintage age classification of wines. Overall, the current review suggests that chromatographic methodologies are promising and powerful techniques that can be used for the accurate determination of phenolic compounds in difficult matrices like wine, highlighting the advantages of the applications of supervised chemometric tools over unsupervised for the construction of prediction models that have been successfully used for the classification based on their territorial and botanical origin.

The role of convolutional neural networks in scanning probe microscopy: a review

Progress in computing capabilities has enhanced science in many ways. In recent years, various branches of machine learning have been the key facilitators in forging new paths, ranging from categorizing big data to instrumental control, from materials design through image analysis. Deep learning has the ability to identify abstract characteristics embedded within a data set, subsequently using that association to categorize, identify, and isolate subsets of the data. Scanning probe microscopy measures multimodal surface properties, combining morphology with electronic, mechanical, and other characteristics. In this review, we focus on a subset of deep learning algorithms, that is, convolutional neural networks, and how it is transforming the acquisition and analysis of scanning probe data.

Flavor of rapeseed oil: An overview of odorants, analytical techniques, and impact of treatment

As one of the three major vegetable oils in the world, rapeseed oil is appreciated for its high nutritional value and characteristic flavor. Flavor is an essential attribute, determining rapeseed oil quality and consumer acceptance. The present manuscript provides a systematic literature review of recent advances and knowledge on the flavor of rapeseed oil, which focuses on aroma-active as well as off-flavor compounds, flavor analysis techniques (i.e., extraction, qualitative, quantitative, sensory, and chemometric methods), and effects of treatments (storage, dehulling, roasting, microwave, flavoring with herbs, refining, and oil heating) on flavor from sensory and molecular perspectives. One hundred thirty-seven odorants found in rapeseed oil from literature are listed and possible formation pathways of some key aroma-active compounds are also proposed. Future flavor analysis techniques will evolve toward time-saving, portability, real-time monitoring, and visualization, which aims to obtain a "complete" flavor profile of rapeseed oil. The changes of volatile compounds in rapeseed oil under different treatments are summarized in this view. Studies to elucidate the influence of different treatments on the formation of aroma-active compounds are needed to get a deeper understanding of factors leading to the variations of rapeseed oil flavor.

Differentiation between Fresh and Frozen-Thawed Meat using Rapid Evaporative Ionization Mass Spectrometry: The Case of Beef Muscle

An intelligent surgical knife (iKnife) coupled with rapid evaporative ionization mass spectrometry (REIMS) was employed for the lipidomic profiling of fresh and frozen-thawed beef muscle. The data were obtained by REIMS and then processed using multivariate statistical analysis methods including principal component analysis-linear discriminant analysis (PCA-LDA) and orthogonal partial least-squares discriminant analysis (OPLS-DA). The discrimination of fresh and frozen-thawed meat has been achieved, and the real-time identification accuracy was 92-100%. Changes in the composition and content of fatty acids and phospholipids were statistically analyzed by OPLS-DA, and the ions of m/z 279.2317, m/z 681.4830, and m/z 697.4882 were selected as differential compounds/metabolites. The developed method was also successfully applied in the discrimination of fresh and frozen-thawed meat samples. These results showed that REIMS as a high-throughput, rapid, and real-time mass spectrometry detection technology can be used for the identification of fresh and frozen-thawed meat samples.

Development of ANN models based on combined UV-vis-NIR spectra for rapid quantification of physical and chemical properties of industrial hemp extracts

OBJECTIVES

The aim of this study was to develop artificial neural network (ANNs) models for prediction of physical (total dissolved solids, extraction yield) and chemical (total polyphenolic content, antioxidant activity) properties of industrial hemp extracts, prepared by two different extraction methods (solid-liquid extraction and microwave-assisted extraction) based on combined UV-VIS-NIR spectra. Spectral data were gathered for 46 samples per extraction method.

RESULTS

The PCA analysis ensured efficient separation of the samples based on the amount of ethanol in extraction solvent using NIR spectra for both conventional and microwave-assisted extraction.

CONCLUSIONS

Results showed that reliable ANN models (R² >0.7000) for describing physical, chemical, and simultaneously physical and chemical characteristics can be developed based on combined UV-VIS-NIR spectra of industrial hemp extracts without spectra pre-processing.

Using Neural Networks to Obtain Indirect Information about the State Variables in an Alcoholic Fermentation Process

This work provides a manual design space exploration regarding the structure, type, and inputs of a multilayer neural network (NN) to obtain indirect information about the state variables in the alcoholic fermentation process. The main benefit of our application is to help experts reduce the time needed for making the relevant measurements and to increase the lifecycles of sensors in bioreactors. The novelty of this research is the flexibility of the developed application, the use of a great number of variables, and the comparative presentation of the results obtained with different NNs (feedback vs. feed-forward) and different learning algorithms (Back-Propagation vs. Levenberg–Marquardt). The simulation results show that the feedback neural network outperformed the feed-forward neural network. The NN configuration is relatively flexible (with hidden layers and a number of nodes on each of them), but the number of input and output nodes depends on the fermentation process parameters. After laborious simulations, we determined that using pH and CO2 as inputs reduces the prediction errors of the NN. Thus, besides the most commonly used process parameters like fermentation temperature, time, the initial concentration of the substrate, the substrate concentration, and the biomass concentration, by adding pH and CO2, we obtained the optimum number of input nodes for the network. The optimal configuration in our case was obtained after 1500 iterations using a NN with one hidden layer and 12 neurons on it, seven neurons on the input layer, and one neuron as the output. If properly trained and validated, this model can be used in future research to accurately predict steady-state and dynamic alcoholic fermentation process behaviour and thereby improve process control performance.

High-Throughput Phenotyping Approach for Screening Major Carotenoids of Tomato by Handheld Raman Spectroscopy Using Chemometric Methods

Our objective was to develop a rapid technique for the non-invasive profiling and quantification of major tomato carotenoids using handheld Raman spectroscopy combined with pattern recognition techniques. A total of 106 samples with varying carotenoid profiles were provided by the Ohio State University Tomato Breeding and Genetics program and Lipman Family Farms (Naples, FL, USA). Non-destructive measurement from the surface of tomatoes was performed by a handheld Raman spectrometer equipped with a 1064 nm excitation laser, and data analysis was performed using soft independent modelling of class analogy (SIMCA)), artificial neural network (ANN), and partial least squares regression (PLSR) for classification and quantification purposes. High-performance liquid chromatography (HPLC) and UV/visible spectrophotometry were used for profiling and quantification of major carotenoids. Seven groups were identified based on their carotenoid profile, and supervised classification by SIMCA and ANN clustered samples with 93% and 100% accuracy based on a validation test data, respectively. All-trans-lycopene and β-carotene levels were measured with a UV-visible spectrophotometer, and prediction models were developed using PLSR and ANN. Regression models developed with Raman spectra provided excellent prediction performance by ANN (r_pre = 0.9, SEP = 1.1 mg/100 g) and PLSR (r_pre = 0.87, SEP = 2.4 mg/100 g) for non-invasive determination of all-trans-lycopene in fruits. Although the number of samples were limited for β-carotene quantification, PLSR modeling showed promising results (r_cv = 0.99, SECV = 0.28 mg/100 g). Non-destructive evaluation of tomato carotenoids can be useful for tomato breeders as a simple and rapid tool for developing new varieties with novel profiles and for separating orange varieties with distinct carotenoids (high in β-carotene and high in cis-lycopene).

Comparison of Chemometric Problems in Food Analysis Using Non-Linear Methods

Food analysis is a challenging analytical problem, often addressed using sophisticated laboratory methods that produce large data sets. Linear and non-linear multivariate methods can be used to process these types of datasets and to answer questions such as whether product origin is accurately labeled or whether a product is safe to eat. In this review, we present the application of non-linear methods such as artificial neural networks, support vector machines, self-organizing maps, and multi-layer artificial neural networks in the field of chemometrics related to food analysis. We discuss criteria to determine when non-linear methods are better suited for use instead of traditional methods. The principles of algorithms are described, and examples are presented for solving the problems of exploratory analysis, classification, and prediction.

Deep Learning Techniques to Improve the Performance of Olive Oil Classification

The olive oil assessment involves the use of a standardized sensory analysis according to the “panel test” method. However, there is an important interest to design novel strategies based on the use of Gas Chromatography (GC) coupled to mass spectrometry (MS), or ion mobility spectrometry (IMS) together with a chemometric data treatment for olive oil classification. It is an essential task in an attempt to get the most robust model over time and, both to avoid fraud in the price and to know whether it is suitable for consumption or not. The aim of this paper is to combine chemical techniques and Deep Learning approaches to automatically classify olive oil samples from two different harvests in their three corresponding classes: extra virgin olive oil (EVOO), virgin olive oil (VOO), and lampante olive oil (LOO). Our Deep Learning model is built with 701 samples, which were obtained from two olive oil campaigns (2014–2015 and 2015–2016). The data from the two harvests are built from the selection of specific olive oil markers from the whole spectral fingerprint obtained with GC-IMS method. In order to obtain the best results we have configured the parameters of our model according to the nature of the data. The results obtained show that a deep learning approach applied to data obtained from chemical instrumental techniques is a good method when classifying oil samples in their corresponding categories, with higher success rates than those obtained in previous works.

Application of electronic nose as a non-invasive technique for odor fingerprinting and detection of bacterial foodborne pathogens: a review

Food safety issues across the global food supply chain have become paramount in promoting public health safety and commercial success of global food industries. As food regulations and consumer expectations continue to advance around the world, notwithstanding the latest technology, detection tools, regulations and consumer education on food safety and quality, there is still an upsurge of foodborne disease outbreaks across the globe. The development of the Electronic nose as a noninvasive technique suitable for detecting volatile compounds have been applied for food safety and quality analysis. Application of E-nose for pathogen detection has been successful and superior to conventional methods. E-nose offers a method that is noninvasive, fast and requires little or no sample preparation, thus making it ideal for use as an online monitoring tool. This manuscript presents an in-depth review of the application of electronic nose (E-nose) for food safety, with emphasis on classification and detection of foodborne pathogens. We summarise recent data and publications on foodborne pathogen detection (2006-2018) and by E-nose together with their methodologies and pattern recognition tools employed. E-nose instrumentation, sensing technologies and pattern recognition models are also summarised and future trends and challenges, as well as research perspectives, are discussed.

Assessment of lipid peroxidation and artificial neural network models in early Alzheimer Disease diagnosis

OBJECTIVE

Lipid peroxidation constitutes a molecular mechanism involved in early Alzheimer Disease (AD) stages, and artificial neural network (ANN) analysis is a promising non-linear regression model, characterized by its high flexibility and utility in clinical diagnosis. ANN simulates neuron learning procedures and it could provide good diagnostic performances in this complex and heterogeneous disease compared with linear regression analysis.

DESIGN AND METHODS

In our study, a new set of lipid peroxidation compounds were determined in urine and plasma samples from patients diagnosed with early Alzheimer Disease (n = 70) and healthy controls (n = 26) by means of ultra-performance liquid chromatography coupled with tandem mass-spectrometry. Then, a model based on ANN was developed to classify groups of participants.

RESULTS

The diagnostic performances obtained using an ANN model for each biological matrix were compared with the corresponding linear regression model based on partial least squares (PLS), and with the non-linear (radial and polynomial) support vector machine (SVM) models. Better accuracy, in terms of receiver operating characteristic-area under curve (ROC-AUC), was obtained for the ANN models (ROC-AUC 0.882 in plasma and 0.839 in urine) than for PLS and SVM models.

CONCLUSION

Lipid peroxidation and ANN constitute a useful approach to establish a reliable diagnosis when the prognosis is complex, multidimensional and non-linear.

Prediction of benzo[a]pyrene content of smoked sausage using back-propagation artificial neural network

BACKGROUND

Benzo[a]pyrene (BaP), a potent mutagen and carcinogen, is reported to be present in processed meat products and, in particular, in smoked meat. However, few methods exist for predictive determination of the BaP content of smoked meats such as sausage. In this study, an artificial neural network (ANN) model based on the back-propagation (BP) algorithm was used to predict the BaP content of smoked sausage.

RESULTS

The results showed that the BP network based on the Levenberg-Marquardt algorithm was the best suited for creating a nonlinear map between the input and output parameters. The optimal network structure was 3-7-1 and the learning rate was 0.6. This BP-ANN model allowed for accurate predictions, with the correlation coefficients (R) for the experimentally determined training, validation, test and global data sets being 0.94, 0.96, 0.95 and 0.95 respectively. The validation performance was 0.013, suggesting that the proposed BP-ANN may be used to predictively detect the BaP content of smoked meat products.

CONCLUSION

An effective predictive model was constructed for estimation of the BaP content of smoked sausage using ANN modeling techniques, which shows potential to predict the BaP content in smoked sausage. © 2017 Society of Chemical Industry.

Application of self-organising maps towards segmentation of soybean samples by determination of amino acids concentration

Soybeans are widely used both for human nutrition and animal feed, since they are an important source of protein, and they also provide components such as phytosterols, isoflavones, and amino acids. In this study, were determined the concentrations of the amino acids lysine, histidine, arginine, asparagine, glutamic acid, glycine, alanine, valine, isoleucine, leucine, tyrosine, phenylalanine present in 14 samples of conventional soybeans and 6 transgenic, cultivated in two cities of the state of Paraná, Londrina and Ponta Grossa. The results were tabulated and presented to a self-organising map for segmentation according planting regions and conventional or transgenic varieties. A network with 7000 training epochs and a 10 × 10 topology was used, and it proved appropriate in the segmentation of the samples using the data analysed. The weight maps provided by the network, showed that all the amino acids were important in targeting the samples, especially isoleucine. Three clusters were formed, one with only Ponta Grossa samples (including transgenic (PGT) and common (PGC)), a second group with Londrina transgenic (LT) samples and the third with Londrina common (LC) samples.

Evaluation of extra virgin olive oil stability by artificial neural network

The stability of extra virgin olive oil in polyethylene terephthalate bottles and tinplate cans stored for 6 months under dark and light conditions was evaluated. The following analyses were carried out: free fatty acids, peroxide value, specific extinction at 232 and 270 nm, chlorophyll, L(∗)C(∗)h color, total phenolic compounds, tocopherols and squalene. The physicochemical changes were evaluated by artificial neural network (ANN) modeling with respect to light exposure conditions and packaging material. The optimized ANN structure consists of 11 input neurons, 18 hidden neurons and 5 output neurons using hyperbolic tangent and softmax activation functions in hidden and output layers, respectively. The five output neurons correspond to five possible classifications according to packaging material (PET amber, PET transparent and tinplate can) and light exposure (dark and light storage). The predicted physicochemical changes agreed very well with the experimental data showing high classification accuracy for test (>90%) and training set (>85). Sensitivity analysis showed that free fatty acid content, peroxide value, L(∗)Cab(∗)hab(∗) color parameters, tocopherol and chlorophyll contents were the physicochemical attributes with the most discriminative power.

Predictive analysis of beer quality by correlating sensory evaluation with higher alcohol and ester production using multivariate statistics methods

Sensory evaluation is regarded as a necessary procedure to ensure a reproducible quality of beer. Meanwhile, high-throughput analytical methods provide a powerful tool to analyse various flavour compounds, such as higher alcohol and ester. In this study, the relationship between flavour compounds and sensory evaluation was established by non-linear models such as partial least squares (PLS), genetic algorithm back-propagation neural network (GA-BP), support vector machine (SVM). It was shown that SVM with a Radial Basis Function (RBF) had a better performance of prediction accuracy for both calibration set (94.3%) and validation set (96.2%) than other models. Relatively lower prediction abilities were observed for GA-BP (52.1%) and PLS (31.7%). In addition, the kernel function of SVM played an essential role of model training when the prediction accuracy of SVM with polynomial kernel function was 32.9%. As a powerful multivariate statistics method, SVM holds great potential to assess beer quality.

A new kernel discriminant analysis framework for electronic nose recognition

Electronic nose (e-Nose) technology based on metal oxide semiconductor gas sensor array is widely studied for detection of gas components. This paper proposes a new discriminant analysis framework (NDA) for dimension reduction and e-Nose recognition. In a NDA, the between-class and the within-class Laplacian scatter matrix are designed from sample to sample, respectively, to characterize the between-class separability and the within-class compactness by seeking for discriminant matrix to simultaneously maximize the between-class Laplacian scatter and minimize the within-class Laplacian scatter. In terms of the linear separability in high dimensional kernel mapping space and the dimension reduction of principal component analysis (PCA), an effective kernel PCA plus NDA method (KNDA) is proposed for rapid detection of gas mixture components by an e-Nose. The NDA framework is derived in this paper as well as the specific implementations of the proposed KNDA method in training and recognition process. The KNDA is examined on the e-Nose datasets of six kinds of gas components, and compared with state of the art e-Nose classification methods. Experimental results demonstrate that the proposed KNDA method shows the best performance with average recognition rate and total recognition rate as 94.14% and 95.06% which leads to a promising feature extraction and multi-class recognition in e-Nose.

Single laboratory method validation comparing MS3 with FI/MS fingerprinting, and quantitation strategies for the accurate determination of ochratoxins in beer

The current mycotoxin safety concerns demand the availability of reliable and selective control systems to measure the content of mycotoxins present in daily food. To address this, we report a prospective analytical tool involving the application of a flow injection mass spectrometry (FI/MS) tandem artificial neural network (ANN) strategy to predict the amount of ochratoxin A and B (OTA and OTB) in beer. Triple stage mass spectrometry (MS3) aided by chromatographic separation was applied as a reference method for comparison. 0.1% formic acid and methanol were used to convert ochratoxins into their respective ions under negative MS polarity. For experiments involving MS3, ochratoxins were separated by reversed-phase liquid chromatography in a 6 min run, ionised using electrospray ionisation, and detected by tandem mass spectrometry. Analyte-specific mass-to-charge ratios were used to perform quantitation in MS3 mode. For experiments involving FI/MS, no chromatographic separation was performed. Approximately 2% of the mass spectra was used for model construction. ANN models representing each ochratoxin were individually trained and validated using three sets of matrix-matched and matrix-free calibration curves at nine concentration levels of 2.5, 10, 25, 50, 100, 200, 300, 400 and 500 μg/l. Quintuplicate analyses were made in FI/ MS mode providing a total of 270 spectra for both OTA and OTB. Single measurement was made for each sample in MS3 mode. A root-mean-square error value of <1% was reported for both ochratoxin models in beer. Limits of quantitation were determined to be 0.2 μg/kg for both MS3 and FI/MS mode. Recovery assessment was performed over two days using beer blanks (n=6) spiked at three concentration levels of 5, 100 and 200 μg/kg. Extraction using acetonitrile provided excellent recovery ranges of 88 to 102% for both MS techniques. Relative standard deviations of 10% or better were achieved for interday spike recovery experiments. The successful utilisation of FI/MS without performing chromatographic separation implies the availability of a new analytical tool relevant to the field of mycotoxin analysis, possibly offering analyte specificity exceeding the capability of MS3 through chemometry.

A flow-injection mass spectrometry fingerprinting scaffold for feature selection and quantitation of Cordyceps and Ganoderma extracts in beverage: a predictive artificial neural network modelling strategy

Flow-injection mass spectrometry (FI/MS) represents a powerful analytical tool for the quality assessment of herbal formula in dietary supplements. In this study, we described a scaffold (proof-of-concept) adapted from spectroscopy to quantify Cordyceps sinensis and Ganoderma lucidum in a popular Cordyceps sinensis /Ganoderma lucidum -enriched health beverage by utilizing flow-injection/mass spectrometry/artificial neural network (FI/MS/ANN) model fingerprinting method with feature selection capability. Equal proportion of 0.1% formic acid and methanol (v/v) were used to convert extracts of Cordyceps sinensis and Ganoderma lucidum into their respective ions under positive MS polarity condition. No chromatographic separation was performed. The principal m/z values of Cordyceps sinensis and Ganoderma lucidum were identified as: 104.2, 116.2, 120.2, 175.2, 236.3, 248.3, 266.3, 366.6 and 498.6; 439.7, 469.7, 511.7, 551.6, 623.6, 637.7 and 653.6, respectively. ANN models representing Cordyceps sinensis and Ganoderma lucidum were individually trained and validated using three independent sets of matrix-free and matrix-matched calibration curves at concentration levels of 2, 20, 50, 100, 200 and 400 μg mL^-1. Five repeat analyses provided a total of 180 spectra for herbal extracts of Cordyceps sinensis and Ganoderma lucidum. Root-mean-square-deviation (RMSE) were highly satisfactory at <4% for both training and validation models. Correlation coefficient (r²) values of between 0.9994 and 0.9997 were reported. Matrix blanks comprised of complex mixture of Lingzhi fermentation solution and collagen. Recovery assessment was performed over two days using six sets of matrix blank (n = 6) spiked at three concentration levels of approximately 83, 166 and 333 mg kg^-1. Extraction using acetonitrile provided good overall recovery range of 92-118%. A quantitation limit of 0.2 mg L^-1 was reported for both Cordyceps sinensis and Ganoderma lucidum. Intra-day and inter-day RMSE values of 7% or better were achieved. Application of the scaffold in a high-throughput routine environment would imply a significant reduction in effort and time, since the option of having a model driven analytical solution is now available.