Beer fermentation: monitoring of process parameters by FT-NIR and multivariate data analysis

Multipoint monitor of beer fermentation

This short communication is devoted to a fully-mechanized flow analysis system for the control of beer fermentation process. The developed system is based on microsolenoid flow controlling devices (valves and pumps) and a flow-through optoelectronic detector. All these components are powered and controlled by a Adruino-compatible microprocessor platform that creates an integrated, compact, and robust analytical tool. Multiplication of sample aspiration ports of the analytical system allows for simultaneous monitoring of several independently performed fermentation processes, as well as a single process at the different places of fermentation tank. To demonstrate its practical utility, the developed system has been applied for online and real-time monitoring of yeast propagation and distribution in beer worts in the course of various fermentation processes. Potentially, this flow analysis system can be easily expanded to the form of multianalyte monitor equipped with optoelectronic sensors and biosensors for the determination of other parameters and analytes.

The Prediction of Quality Parameters of Craft Beer with FT-MIR and Chemometrics

Beer is one of the oldest and most known alcoholic beverages whose organoleptic characteristics are the attributes that the consumer seeks, which is why it is essential to ensure proper quality control of the final product. Fourier transform mid-infrared (FT-MIR) spectroscopy coupled with multivariate analysis can be an alternative to traditional methods to predict quality parameters in craft beer. This study aims to develop prediction models based on FT-MIR spectroscopy to simultaneously quantify quality parameters (color, specific gravity, alcohol volume, bitterness, turbidity, pH, and total acidity) in craft beer. Additionally, principal component analysis (PCA) was applied, and it was possible to classify craft beer samples according to their style. Partial least squares (PLS1) developed the best predictive model by obtaining higher R2c (0.9999) values and lower standard error of calibration (SEC: 0.01-0.11) and standard error of prediction (SEP: 0.01-0.14) values in comparison to the models developed with the other algorithms. Specific gravity could not be predicted due to the low variability in the values. Validation and prediction with external samples confirmed the predictive capacity of the developed model. By making a comparison to traditional techniques, FT-MIR coupled with multivariate analysis has a higher advantage, since it is rapid (approximately 6 min), efficient, cheap, and eco-friendly because it does not require the use of solvents or reagents, representing an alternative to simultaneously analyzing quality parameters in craft beer.

Towards the Optimization of Microwave-Assisted Extraction and the Assessment of Chemical Profile, Antioxidant and Antimicrobial Activity of Wine Lees Extracts

Wine lees, a sub-exploited byproduct of vinification, is considered a rich source of bioactive compounds, such as (poly)phenols, anthocyanins and tannins. Thus, the effective and rapid recovery of these biomolecules and the assessment of the bioactive properties of wine lees extracts is of utmost importance. Towards this direction, microwave-assisted extraction (MAE) factors (i.e., extraction time, microwave power and solvent/material ratio) were optimized using experimental design models in order to maximize the (poly)phenolic yield of the extracts. After optimizing the MAE process, the total phenolic content (TPC) as well as the antiradical, antioxidant and antimicrobial activity of the extracts were evaluated. Furthermore, Fourier transform infrared spectroscopy (FTIR) was employed to investigate the chemical profile of wine lees extracts. Red varieties exhibited higher biological activity than white varieties. The geographical origin and fermentation stage were also considered as critical factors. The white variety Moschofilero presented the highest antioxidant, antiradical and antimicrobial activity, while Merlot and Agiorgitiko samples showed noteworthy activities among red varieties. Moreover, IR spectra confirmed the presence of sugars, amino acids, organic acids and aromatic compounds. Thus, an efficient, rapid and eco-friendly process was proposed for further valorization of wine lees extracts.

Sensors and Instruments for Brix Measurement: A Review

Quality assessment of fruits, vegetables, or beverages involves classifying the products according to the quality traits such as, appearance, texture, flavor, sugar content. The measurement of sugar content, or Brix, as it is commonly known, is an essential part of the quality analysis of the agricultural products and alcoholic beverages. The Brix monitoring of fruit and vegetables by destructive methods includes sensory assessment involving sensory panels, instruments such as refractometer, hydrometer, and liquid chromatography. However, these techniques are manual, time-consuming, and most importantly, the fruits or vegetables are damaged during testing. On the other hand, the traditional sample-based methods involve manual sample collection of the liquid from the tank in fruit/vegetable juice making and in wineries or breweries. Labour ineffectiveness can be a significant drawback of such methods. This review presents recent developments in different destructive and nondestructive Brix measurement techniques focused on fruits, vegetables, and beverages. It is concluded that while there exist a variety of methods and instruments for Brix measurement, traits such as promptness and low cost of analysis, minimal sample preparation, and environmental friendliness are still among the prime requirements of the industry.

A Study on the Applicability of Thermodynamic Sensors in Fermentation Processes in Selected Foods

This study focuses on the use of thermodynamic sensors (TDS) in baking, brewing, and yogurt production at home. Using thermodynamic sensors, a change in the temperature flow between the two sensor elements during fermentation was observed for the final mixture (complete recipe for pizza dough production), showing the possibility of distinguishing some phases of the fermentation process. Even during the fermentation process in the preparation of wort and yogurt with non-traditional additives, the sensors were able to indicate significant parts of the process, including the end of the process. The research article also mentions as a new idea the use of trivial regulation at home in food production to determine the course of the fermentation process. The results presented in this article show the possibility of using TDS for more accurate characterization and adjustment of the production process of selected foods in the basic phase, which will be further applicable in the food industry, with the potential to reduce the cost of food production processes that involve a fermentation process.

Simultaneous Monitoring of the Evolution of Chemical Parameters in the Fermentation Process of Pineapple Fruit Wine Using the Liquid Probe for Near-Infrared Coupled with Chemometrics

This study used Fourier transform-near-infrared (FT-NIR) spectroscopy equipped with the liquid probe in combination with an efficient wavelength selection method named searching combination moving window partial least squares (SCMWPLS) for the determination of ethanol, total soluble solids, total acidity, and total volatile acid contents in pineapple fruit wine fermentation using Saccharomyces cerevisiae var. burgundy. Two fermentation batches were produced, and the NIR spectral data of the calibration samples in the wavenumber range of 11,536-3952 cm-1 were obtained over ten days of the fermentation period. SCMWPLS coupled with second derivatives searched and optimized spectral intervals containing useful information for building calibration models of four parameters. All models were validated by test samples obtained from an independent fermentation batch. The SCMWPLS models showed better predictions (the lowest value of prediction error and the highest value of residual predictive deviation) with acceptable statistical results (under confidence limits) among the results achieved by using the whole region. The results of this study demonstrated that FT-NIR spectroscopy using a liquid probe coupled with SCMWPLS could select the optimized wavelength regions while reducing spectral points and increasing accuracy for simultaneously monitoring the evolution of four chemical parameters in pineapple fruit wine fermentation.

Domain Adaptation and Federated Learning for Ultrasonic Monitoring of Beer Fermentation

Beer fermentation processes are traditionally monitored through sampling and off-line wort density measurements. In-line and on-line sensors would provide real-time data on the fermentation progress whilst minimising human involvement, enabling identification of lagging fermentations or prediction of ethanol production end points. Ultrasonic sensors have previously been used for in-line and on-line fermentation monitoring and are increasingly being combined with machine learning models to interpret the sensor measurements. However, fermentation processes typically last many days and so impose a significant time investment to collect data from a sufficient number of batches for machine learning model training. This expenditure of effort must be multiplied if different fermentation processes must be monitored, such as varying formulations in craft breweries. In this work, three methodologies are evaluated to use previously collected ultrasonic sensor data from laboratory scale fermentations to improve machine learning model accuracy on an industrial scale fermentation process. These methodologies include training models on both domains simultaneously, training models in a federated learning strategy to preserve data privacy, and fine-tuning the best performing models on the industrial scale data. All methodologies provided increased prediction accuracy compared with training based solely on the industrial fermentation data. The federated learning methodology performed best, achieving higher accuracy for 14 out of 16 machine learning tasks compared with the base case model.

A Metabolomic Approach to Beer Characterization

The consumers’ interest towards beer consumption has been on the rise during the past decade: new approaches and ingredients get tested, expanding the traditional recipe for brewing beer. As a consequence, the field of “beeromics” has also been constantly growing, as well as the demand for quick and exhaustive analytical methods. In this study, we propose a combination of nuclear magnetic resonance (NMR) spectroscopy and chemometrics to characterize beer. ¹H-NMR spectra were collected and then analyzed using chemometric tools. An interval-based approach was applied to extract chemical features from the spectra to build a dataset of resolved relative concentrations. One aim of this work was to compare the results obtained using the full spectrum and the resolved approach: with a reasonable amount of time needed to obtain the resolved dataset, we show that the resolved information is comparable with the full spectrum information, but interpretability is greatly improved.

Moderate Beer Consumption Modifies Tumoral Growth Parameters and Pyrrolidone Carboxypeptidase Type-I and Type-II Specific Activities in the Hypothalamus-Pituitary-Mammary Gland Axis in an Animal Model of Breast Cancer

AIMS

To determine the effect of moderate alcoholic and nonalcoholic beer consumption on tumoral growth parameters, the histopathology, pyrrolidone carboxypeptidase type I (Pcp I), and type II (Pcp II) specific activities in the hypothalamus-pituitary-mammary gland axis, and the circulating levels of estradiol (E₂) and progesterone (P₄) in rats with N-methyl-N-nitrosourea (NMU) induced mammary tumors.

MATERIAL AND METHODS

Food and drink intake, weight gain and tumor growth parameters were collected. The malignant phenotype of the tumor was performed using the Scarff-Bloom-Richardson grading method. Pcp specific activities were fluorometrically analyzed using pyroglutamyl-β-naphthylamide as substrate. Circulating steroid hormones were determined.

RESULTS

Differences were found in tumoral parameters, depending on the drink. Animals that were given alcohol-containing beer (A/C) beer to drink showed the lowest values of hypothalamic Pcp I, in association with the lowest levels of circulating E₂. The significant decrease in Pcp I activity in all NMU-treated groups suggest a clear role of the Pcp I in the tumoral process, and A/C beer interferes with it.

DISCUSSION

Moderate consumption of alcoholic beer would have beneficial effects against mammary tumors through the modification of the endocrine status mediated by GnRH due to changes on Pcp I and II activities at different levels.

Insights into chemical and sensorial aspects to understand and manage beer aging using chemometrics

Beer chemical instability remains, at present, the main challenge in maintaining beer quality. Although not fully understood, after decades of research, significant progress has been made in identifying "aging compounds," their origin, and formation pathways. However, as the nature of aging relies on beer manufacturing aspects such as raw materials, process variables, and storage conditions, the chemical profile differs among beers. Current research points to the impact of nonoxidative reactions on beer quality. The effect of Maillard and Maillard intermediates on the final beer quality has become the focus of beer aging research, as prevention of oxidation can only sustain beer quality to some extent. On the other hand, few studies have focused on tracing a profile of whose compound is sensory relevant to specific types of beer. In this matter, the incorporation of "chemometrics," a class of multivariate statistic procedures, has helped brewing scientists achieve specific correlations between the sensory profile and chemical data. The use of chemometrics as exploratory data analysis, discrimination techniques, and multivariate calibration techniques has made the qualitatively and quantitatively translation of sensory perception of aging into manageable chemical and analytical parameters. However, despite their vast potential, these techniques are rarely employed in beer aging studies. This review discusses the chemical and sensorial bases of beer aging. It focuses on how chemometrics can be used to their full potential, with future perspectives and research to be incorporated in the field, enabling a deeper and more specific understanding of the beer aging picture.

Application of Detrended Fluctuation Analysis and Yield Stability Index to Evaluate Near Infrared Spectra of Green and Roasted Coffee Samples

Coffee quality, and therefore its price, is determined by coffee species and varieties, geographic location, the method used to process green coffee beans, and particularly the care taken during coffee production. Determination of coffee quality is often done by the nondestructive and fast near infrared spectroscopy (NIRS), which provides a huge amount of data about the samples. NIRS data require sophisticated, multivariate data analysis methods, such as principal component analysis, or linear discriminant analysis. Since the obtained data are a set of spectra, they can also be analyzed by signal processing methods. In the present study, the applications of two novel methods, detrended fluctuation analysis (DFA) and yield stability index (YSI), is introduced on NIR spectra of different roasting levels of coffee samples. Fourteen green coffee samples from all over the world have been roasted on three different levels and their NIR spectra were analyzed. DFA successfully differentiated the green samples from the roasted ones, however, the joint analysis of all samples was not able to differentiate the roasting levels. On the other hand, DFA successfully differentiated the roasting levels on samples level, which was strengthened by a 100% accurate agglomerative hierarchical clustering. YSI was first used in NIR signal processing and was able to detect that a light roast is the most stable among all roasting levels. Future research should focus on the application of DFA in terms of the analysis of the effects of other transformation methods of the spectra.

A Digital Approach to Model Quality and Sensory Traits of Beers Fermented under Sonication Based on Chemical Fingerprinting

The development of digital tools based on artificial intelligence can produce affordable and accurate methodologies to assess quality traits and sensory analysis of beers. These new and emerging technologies can also assess new products in a near real-time fashion through virtual simulations before the brewing process. This research was based on the development of specific digital tools (four models) to assess quality traits and sensory profiles of beers produced using sonication and traditional brewing techniques. Results showed that models developed using supervised machine learning (ML) regression algorithms based on near-infrared spectroscopy (NIR) were highly accurate in the estimation of physicochemical parameters (Model 1; R = 0.94; b = 0.91). Outputs from Model 1 were then used as inputs to obtain estimations of the intensity of sensory descriptors (Model 2; R = 0.99; b = 0.98), liking of sensory attributes (Model 3; R = 0.97; b = 0.99), and the classification of fermentation treatments using supervised classification ML algorithms (Model 4; 96% accuracy). These new digital tools can aid craft brewing companies for product development at lower costs and maintain specific quality traits and sensory profiles, creating original styles of beers to get positioned in the market.

Detecting Low Concentrations of Nitrogen-Based Adulterants in Whey Protein Powder Using Benchtop and Handheld NIR Spectrometers and the Feasibility of Scanning through Plastic Bag

Nitrogen-rich adulterants in protein powders present sensitivity challenges to conventional combustion methods of protein determination which can be overcome by near Infrared spectroscopy (NIRS). NIRS is a rapid analytical method with high sensitivity and non-invasive advantages. This study developed robust models using benchtop and handheld spectrometers to predict low concentrations of urea, glycine, taurine, and melamine in whey protein powder (WPP). Effectiveness of scanning samples through optical glass and polyethylene bags was also tested for the handheld NIRS. WPP was adulterated up to six concentration levels from 0.5% to 3% w/w. The two spectrometers were used to obtain three datasets of 819 diffuse reflectance spectra each that were pretreated before linear discriminant analysis (LDA) and regression (PLSR). Pretreatment was effective and revealed important absorption bands that could be correlated with the chemical properties of the mixtures. Benchtop NIR spectrometer showed the best results in LDA and PLSR but handheld NIR spectrometers showed comparatively good results. There were high prediction accuracies and low errors attesting to the robustness of the developed PLSR models using independent test set validation. Both the plastic bag and optical glass gave good results with accuracies depending on the adulterant of interest and can be used for field applications.

The Brewing Industry and the Opportunities for Real-Time Quality Analysis Using Infrared Spectroscopy

Brewing is an ancient process which started in the middle east over 10,000 years ago. The style of beer varies across the globe but modern brewing is very much the same regardless of the style. While there are thousands of compounds in beer, current methods of analysis rely mostly on the content of only several important processing parameters such as gravity, bitterness, or alcohol. Near infrared and mid infrared spectroscopy offer opportunities to predict dozens to hundreds of compounds simultaneously at different stages of the brewing process. Importantly, this is an opportunity to move deeper into quality through measuring wort and beer composition, rather than just content. This includes measuring individual sugars and amino acids prior to fermentation, rather than total °Plato or free amino acids content. Portable devices and in-line probes, coupled with more complex algorithms can provide real time measurements, allowing brewers more control of the process, resulting in more consistent quality, reduced production costs and greater confidence for the future.

Comparison of algorithms for wavelength variables selection from near-infrared (NIR) spectra for quantitative monitoring of yeast (Saccharomyces cerevisiae) cultivations

Rapid monitoring with near-infrared (NIR) spectroscopy of Saccharomyces cerevisiae cultivations was implemented to monitor yeast concentrations. The measurement of one spectrum by using of FT-NIR spectrometer can obtain 1557 wavelength variables. To distinguish which wavelength variables of the collected FT-NIR spectra carry important and relevant information regarding the yeast concentrations, there are three different variables selection approaches, namely genetic algorithm (GA), competitive adaptive reweighted sampling (CARS), and variable combination population analysis (VCPA), were compared in this study. The selected wavelength variables from each method were evaluated using partial least squares (PLS) models to seek the most significant variable combinations for predicting the yeast concentrations. Experimental results showed that the VCPA-PLS model with the best predictive performance was found when using ten principal components (PCs) based on selected eleven characteristic wavelength variables by VCPA algorithm. And the predictive performance indicators of the model were as follows: the root mean square error of prediction (RMSEP) was 0.0680, the coefficient of determination (R_p²) was 0.9924, and the ratio performance deviation (RPD) was 11.8625 in the validation process. Based on the results, it is promising to develop a specific inexpensive NIR sensor for the yeast cultivation process using several light-emitting diodes.

Beer Molecules and Its Sensory and Biological Properties: A Review

The production and consumption of beer plays a significant role in the social, political, and economic activities of many societies. During brewing fermentation step, many volatile and phenolic compounds are produced. They bring several organoleptic characteristics to beer and also provide an identity for regional producers. In this review, the beer compounds synthesis, and their role in the chemical and sensory properties of craft beers, and potential health benefits are described. This review also describes the importance of fermentation for the brewing process, since alcohol and many volatile esters are produced and metabolized in this step, thus requiring strict control. Phenolic compounds are also present in beer and are important for human health since it was proved that many of them have antitumor and antioxidant activities, which provides valuable data for moderate dietary beer inclusion studies.

Monitoring alcohol concentration and residual glucose in solid state fermentation of ethanol using FT-NIR spectroscopy and L1-PLS regression

This study aimed to investigate the potential of FT-NIR spectroscopy technique combined with chemometrics method, which employed to monitor time-related changes of alcohol concentration and residual glucose during solid state fermentation (SSF) of ethanol. Characteristic wavelength variables were firstly selected by use of L1-norm regularization approach. Then, the partial least squares (PLS) regression model was finally developed using the variables selected by L1-norm regularization method to quantitative determine alcohol concentration and residual glucose in SSF of ethanol. Compared with the best results of full-spectrum PLS, the L1-PLS model obtained better results as follows: RMSECV = 1.0392 g/L, R_c = 0.9911, RMSEP = 1.0910 g/L, R_p = 0.9917 for alcohol concentration; RMSECV = 1.7002 g/L, R_c = 0.9880, RMSEP = 2.1859 g/L, R_p = 0.9896 for residual glucose. The overall results sufficiently demonstrate that FT-NIR spectroscopy technique coupled with appropriate chemometrics method is a promising tool for monitoring the process of SSF of ethanol.

On the Characterization and Correlation of Compositional, Antioxidant and Colour Profile of Common and Balsamic Vinegars

Commercially available common and balsamic vinegars were examined, using a combination of spectrophotometric, chromatographic, colorimetric and spectroscopic methods. Total phenolic content, antioxidant activity, radical scavenging capacity, phenolic profile, colour parameters, Fourier Transform Infrared (FT-IR) absorbance spectra and Nuclear Magnetic Resonance (¹H NMR) spectra were comparatively studied. The main scope was the assessment of vinegar antioxidant and metabolic profiles and the identification of the most appropriate features influencing their type and subtypes. Red grape balsamic vinegars exhibited the strongest antioxidant profile. High total phenolic content and radical scavenging-antioxidant activity of vinegars was strongly correlated with high hue-angle and colour density values and low lightness and a* values. FT-IR spectra analysis confirmed the presence of organic acids and carbohydrates and, in combination with Gas Chromatography-Mass Spectrometry (GC-MS), the occurrence of phenolic compounds. NMR spectroscopy enabled the identification of 27 characteristic metabolites in each type of vinegar. The combination of all applied techniques provides critical information on compositional differences among the vinegars and could serve as an application tool for similar fermentation products.

Near-infrared spectroscopy-based analysis to study sensory parameters on pork loins as affected by cooking methods and conditions

BACKGROUND

The main objectives of this study were to evaluate the use of near infrared spectroscopy (NIRS) to classify pork loins under different methods and cooking conditions, and to predict sensory attributes of this product.

RESULTS

Samples were oven cooked at two temperatures (150 and 180 °C) for different times (45, 60 and 75 min) and confit cooked for different times (120, 180 and 240 min). All cooked loin samples were subjected to a Quantitative Descriptive Analysis by a trained panel. For classification, principal component analysis was performed based on the NIRS database, showing a good discrimination between loins samples subjected to different cooking conditions. Regarding prediction, a data mining technique (multiple linear regression) was applied on a database constructed with data from NIRS and sensory analysis.

CONCLUSION

The correlation coefficient and the mean absolute error obtained suggest that the calculated prediction equations of this study are valid to predict the changes in the sensory attributes depending on the cooking method and conditions used for pork loins. © 2018 Society of Chemical Industry.

Fourier Transform Near-Infrared Spectroscopy and Chemometrics To Predict Zygosacchromyces rouxii in Apple and Kiwi Fruit Juices

This study investigated the capability of near-infrared spectroscopy (NIRS) to predict the concentration of Zygosaccharomyces rouxii in apple and kiwi fruit juices. The yeast was inoculated in fresh kiwi fruit juice ( n = 68), reconstituted kiwi juice ( n = 85), and reconstituted apple juice ( n = 64), followed by NIR spectra collection and plate counting. A principal component analysis indicated direct orthogonal signal correction preprocessing was suitable to separate spectral samples. Parameter optimization algorithms increased the performance of support vector machine regression models developed in a single variety juice system and a multiple variety juice system. Single variety juice models achieved accurate prediction of Z. rouxii concentrations, with the limit of quantification at 3 to 15 CFU/mL ( R² = 0.997 to 0.999), and the method was also feasible for Hanseniaspora uvarum and Candida tropicalis. The best multiple variety juice model obtained had a limit of quantification of 237 CFU/mL ( R² = 0.961) for Z. rouxii. A Bland-Altman analysis indicated good agreement between the support vector machine regression model and the plate counting method. It suggests that NIRS can be a high-throughput method for prediction of Z. rouxii counts in kiwi fruit and apple juices.

Herbal distillates: A new era of grape marc distillates with enriched antioxidant profile

Grape marc distillates are traditional alcoholic beverages, produced mostly in the Mediterranean countries. The present study proposes the enrichment of a Greek traditional grape marc distillate (tsikoudia) with selected herbs to enhance its natural antioxidants and functional properties. Total phenolic content, the antiradical and antioxidant activities, as well as the phenolic and sugar profiles using NMR and FT-IR spectroscopy were evaluated. The enrichment of distillates with Syzygium aromaticum L., Jasminum officinale L. and Eucalyptus globulus Labill. exhibited the highest total phenolic content as well as the highest antioxidant and antiradical activities, whereas the lowest values were observed with Hippophae rhamnoides L. and Lycium Barbarum Mill. The implementation of NMR and FT-IR spectroscopies attested to the presence of phenolic compounds and of specific carbohydrates in herbal distillates, postulating their migration from selected herbal species to tsikoudia and probably contributing to their organoleptic characteristics. The target of this approach leads to new added-value distillates with enhanced characteristics.

Assessment of beer quality based on foamability and chemical composition using computer vision algorithms, near infrared spectroscopy and machine learning algorithms

BACKGROUND

Beer quality is mainly defined by its colour, foamability and foam stability, which are influenced by the chemical composition of the product such as proteins, carbohydrates, pH and alcohol. Traditional methods to assess specific chemical compounds are usually time-consuming and costly. This study used rapid methods to evaluate 15 foam and colour-related parameters using a robotic pourer (RoboBEER) and chemical fingerprinting using near infrared spectroscopy (NIR) from six replicates of 21 beers from three types of fermentation. Results from NIR were used to create partial least squares regression (PLS) and artificial neural networks (ANN) models to predict four chemometrics such as pH, alcohol, Brix and maximum volume of foam.

RESULTS

The ANN method was able to create more accurate models (R²  = 0.95) compared to PLS. Principal components analysis using RoboBEER parameters and NIR overtones related to protein explained 67% of total data variability. Additionally, a sub-space discriminant model using the absorbance values from NIR wavelengths resulted in the successful classification of 85% of beers according to fermentation type.

CONCLUSION

The method proposed showed to be a rapid system based on NIR spectroscopy and RoboBEER outputs of foamability that can be used to infer the quality, production method and chemical parameters of beer with minimal laboratory equipment. © 2017 Society of Chemical Industry.

Non-destructive analysis of sensory traits of dry-cured loins by MRI-computer vision techniques and data mining

BACKGROUND

Magnetic resonance imaging (MRI) combined with computer vision techniques have been proposed as an alternative or complementary technique to determine the quality parameters of food in a non-destructive way. The aim of this work was to analyze the sensory attributes of dry-cured loins using this technique. For that, different MRI acquisition sequences (spin echo, gradient echo and turbo 3D), algorithms for MRI analysis (GLCM, NGLDM, GLRLM and GLCM-NGLDM-GLRLM) and predictive data mining techniques (multiple linear regression and isotonic regression) were tested.

RESULTS

The correlation coefficient (R) and mean absolute error (MAE) were used to validate the prediction results. The combination of spin echo, GLCM and isotonic regression produced the most accurate results. In addition, the MRI data from dry-cured loins seems to be more suitable than the data from fresh loins.

CONCLUSIONS

The application of predictive data mining techniques on computational texture features from the MRI data of loins enables the determination of the sensory traits of dry-cured loins in a non-destructive way. © 2016 Society of Chemical Industry.