Aging time and brand determination of pasteurized milk using a multisensor e-nose combined with a voltammetric e-tongue

Classification and Identification of Contaminants in Recyclable Containers Based on a Recursive Feature Elimination-Light Gradient Boosting Machine Algorithm Using an Electronic Nose

Establishing an excellent recycling mechanism for containers is of great importance for environmental protection, so many technical approaches applied during the whole recycling stage have become popular research issues. Among them, classification is considered a key step, but this work is mostly achieved manually in practical applications. Due to the influence of human subjectivity, the classification accuracy often varies significantly. In order to overcome this shortcoming, this paper proposes an identification method based on a Recursive Feature Elimination-Light Gradient Boosting Machine (RFE-LightGBM) algorithm using electronic nose. Firstly, odor features were extracted, and feature datasets were then constructed based on the response data of the electronic nose to the detected gases. Afterwards, a principal component analysis (PCA) and the RFE-LightGBM algorithm were applied to reduce the dimensionality of the feature datasets, and the differences between these two methods were analyzed, respectively. Finally, the differences in the classification accuracies on the three datasets (the original feature dataset, PCA dimensionality reduction dataset, and RFE-LightGBM dimensionality reduction dataset) were discussed. The results showed that the highest classification accuracy of 95% could be obtained by using the RFE-LightGBM algorithm in the classification stage of recyclable containers, compared to the original feature dataset (88.38%) and PCA dimensionality reduction dataset (92.02%).

Recent developments of e-sensing devices coupled to data processing techniques in food quality evaluation: a critical review

A greater demand for high-quality food is being driven by the growth of economic and technological advancements. In this context, consumers are currently paying special attention to organoleptic characteristics such as smell, taste, and appearance. Motivated to mimic human senses, scientists developed electronic devices such as e-noses, e-tongues, and e-eyes, to spot signals relative to different chemical substances prevalent in food systems. To interpret the information provided by the sensors' responses, multiple chemometric approaches are used depending on the aim of the study. This review based on the Web of Science database, endeavored to scrutinize three e-sensing systems coupled to chemometric approaches for food quality evaluation. A total of 122 eligible articles pertaining to the e-nose, e-tongue and e-eye devices were selected to conduct this review. Most of the performed studies used exploratory analysis based on linear factorial methods, while classification and regression techniques came in the second position. Although their applications have been less common in food science, it is to be noted that nonlinear approaches based on artificial intelligence and machine learning deployed in a big-data context have generally yielded better results for classification and regression purposes, providing new perspectives for future studies.

Juice Quality Evaluation with Multisensor Systems-A Review

E-nose and e-tongue are advanced technologies that allow for the fast and precise analysis of smells and flavours using special sensors. Both technologies are widely used, especially in the food industry, where they are implemented, e.g., for identifying ingredients and product quality, detecting contamination, and assessing their stability and shelf life. Therefore, the aim of this article is to provide a comprehensive review of the application of e-nose and e-tongue in various industries, focusing in particular on the use of these technologies in the fruit and vegetable juice industry. For this purpose, an analysis of research carried out worldwide over the last five years, concerning the possibility of using the considered multisensory systems to test the quality and taste and aroma profiles of juices is included. In addition, the review contains a brief characterization of these innovative devices through information such as their origin, mode of operation, types, advantages and disadvantages, challenges and perspectives, as well as the possibility of their applications in other industries besides the juice industry.

Effect of a Dairy Cow's Feeding System on the Flavor of Raw Milk: Indoor Feeding or Grazing

The flavor of fresh, raw milk is considered to be the key to maintaining the quality of dairy products, and is very crucial in affecting a consumer's choice. To better understand the differences in flavor of fresh milk between feeding patterns, we conducted the following study. Twelve Holstein cows reared in pure grazing mode and twelve reared intensively in medium to large farms were selected from the Xinjiang Uygur Autonomous Regions at the same time, and the flavor of their raw milk was analyzed. Aroma profiles and taste attributes were assessed by electronic nose and electronic tongue, respectively, and volatile flavor compounds were characterized and quantified by Headspace-Solid Phase Microextraction/Gas Chromatography-Mass Spectrometry. Thirteen volatile compounds were identified in the indoor feeding pattern and 12 in the grazing; most of them overlapped. W1S, W2S and W5S were the main contributing sensors of the electronic nose for the overall assessment of the aroma profile. Raw milk from grazing had more intense astringency, bitterness, sourness and richness in taste compared to indoor feeding. Different dietary conditions may contribute to a variety of aroma profiles. Oxime-, methoxy-phenyl-, octadecanoic acid, furfural and dodecanoic acid were the key volatile flavor compounds of grazing. Meanwhile, raw milk from indoor feeding patterns was unique in 2-nonanone, heptanoic acid and n-decanoic acid. All three detection techniques were valid and feasible for differentiating raw milk in both feeding patterns, and the compounds were significantly correlated with the key sensors by correlation analysis. This study is promising for the future use of metabolic sources of volatile organic compounds to track and monitor animal feeding systems.

Characterization of selected Chinese soybean paste based on flavor profiles using HS-SPME-GC/MS, E-nose and E-tongue combined with chemometrics

Headspace solid-phase microextraction gas chromatography-mass spectrometry (HS-SPME-GC/MS) with electronic nose (E-nose) and electronic tongue (E-tongue) was applied for flavor characterization of traditional Chinese fermented soybean paste. Considering geographical distribution and market representation, twelve kinds of samples were selected to investigate the feasibility. A total of 57 volatile organic compounds (VOCs) were identified, of which 8 volatiles were found in all samples. Linear discrimination analysis (LDA) of fusion data exhibited a high discriminant accuracy of 97.22%. Compared with partial least squares regression (PLSR), support vector machine regression (SVR) analysis exhibited a more satisfying performance on predicting the content of esters, total acids, reducing sugar, salinity and amino acid nitrogen, of which correlation coefficients for prediction (Rp) were about 0.803, 0.949, 0.960, 0.896, 0.923 respectively. This study suggests that intelligent sensing technologies combined with chemometrics can be a promising tool for flavor characterization of fermented soybean paste or other food matrixes.

Analysis of Milk Using a Portable Potentiometric Electronic Tongue Based on Five Polymeric Membrane Sensors

A portable potentiometric electronic tongue (PE-tongue) was developed and applied to evaluate the quality of milk with different fat content (skimmed, semi-skimmed, and whole) and with different nutritional content (classic, calcium-enriched, lactose-free, folic acid–enriched, and enriched in sterols of vegetal origin). The system consisted of a simplified array of five sensors based on PVC membranes, coupled to a data logger. The five sensors were selected from a larger set of 20 sensors by applying the genetic algorithm (GA) to the responses to compounds usually found in milk including salts (KCl, CaCl₂, and NaCl), sugars (lactose, glucose, and galactose), and organic acids (citric acid and lactic acid). Principal component analysis (PCA) and support vector machine (SVM) results indicated that the PE-tongue consisting of a five-electrode array could successfully discriminate and classify milk samples according to their nutritional content. The PE-tongue provided similar discrimination capability to that of a more complex system formed by a 20-sensor array. SVM regression models were used to predict the physicochemical parameters classically used in milk quality control (acidity, density, %proteins, %lactose, and %fat). The prediction results were excellent and similar to those obtained with a much more complex array consisting of 20 sensors. Moreover, the SVM method confirmed that spoilage of unsealed milk could be correctly identified with the simplified system and the increase in acidity could be accurately predicted. The results obtained demonstrate the possibility of using the simplified PE-tongue to predict milk quality and provide information on the chemical composition of milk using a simple and portable system.

Milk Source Identification and Milk Quality Estimation Using an Electronic Nose and Machine Learning Techniques

In this study, an electronic nose (E-nose) consisting of seven metal oxide semiconductor sensors is developed to identify milk sources (dairy farms) and to estimate the content of milk fat and protein which are the indicators of milk quality. The developed E-nose is a low cost and non-destructive device. For milk source identification, the features based on milk odor features from E-nose, composition features (Dairy Herd Improvement, DHI analytical data) from DHI analysis and fusion features are analyzed by principal component analysis (PCA) and linear discriminant analysis (LDA) for dimension reduction and then three machine learning algorithms, logistic regression (LR), support vector machine (SVM), and random forest (RF), are used to construct the classification model of milk source (dairy farm) identification. The results show that the SVM model based on the fusion features after LDA has the best performance with the accuracy of 95%. Estimation model of the content of milk fat and protein from E-nose features using gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and random forest (RF) are constructed. The results show that the RF models give the best performance (R² = 0.9399 for milk fat; R² = 0.9301 for milk protein) and indicate that the proposed method in this study can improve the estimation accuracy of milk fat and protein, which provides a technical basis for predicting the quality of milk.

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.

Rapid methods and sensors for milk quality monitoring and spoilage detection

Monitoring of food quality, in particular, milk quality, is critical in order to maintain food safety and human health. To guarantee quality and safety of milk products and at the same time deliver those as soon as possible, rapid analysis methods as well as sensitive, reliable, cost-effective, easy-to-use devices and systems for process control and milk spoilage detection are needed. In this paper, we review different rapid methods, sensors and commercial systems for milk spoilage and microorganism detection. The main focus lies on chemical sensors and biosensors for detection/monitoring of the well-known indicators associated with bacterial growth and milk spoilage such as changes in pH value, conductivity/impedance, adenosine triphosphate level, concentration of dissolved oxygen and produced CO₂. These sensors offer several advantages, like high sensitivity, fast response time, minimal sample preparation, miniaturization and ability for real-time monitoring of milk spoilage. In addition, electronic-nose- and electronic-tongue systems for the detection of characteristic volatile and non-volatile compounds related to microbial growth and milk spoilage are described. Finally, wireless sensors and color indicators for intelligent packaging are discussed.

Distinguishment, identification and aroma compound quantification of Portuguese olive oils based on physicochemical attributes, HS-GC/MS analysis and voltammetric electronic tongue

BACKGROUND

In this paper, various extra-virgin and virgin olive oils samples from different Portuguese markets were studied. For this purpose, a voltammetric electronic tongue (VE-tongue), consisting of two kinds of working electrode within the array, together with physicochemical analysis and headspace gas chromatography coupled with mass spectrometry (HS-GC-MS), were applied. In addition, preliminary considerations of relationships between physicochemical parameters and multisensory system were reported.

RESULTS

The physicochemical parameters exhibit significant differences among the analyzed olive oil samples that define its qualities. Regarding the aroma profile, 14 volatile compounds were characterized using HS-GC-MS; among these, hex-2-enal, hexanal, acetic acid, hex-3-ene-1-ol acetate and hex-3-en-1-ol were semi-quantitatively detected as the main aroma compounds in the analyzed samples. Moreover, pattern recognition methods demonstrate the discrimination power of the proposed VE-tongue system. The results reveal the VE-tongue's ability to classify olive oil samples and to identify unknown samples based of built models. In addition, the correlation between VE-tongue and physicochemical analysis exhibits a remarkable prediction model aimed at anticipating carotenoid content.

CONCLUSION

The preliminary results of this investigation indicate that physicochemical and HS-GC-MS analysis, together with multisensory system coupled with chemometric techniques, presented a satisfactory performance regarding olive oil sample discrimination and identification. © 2017 Society of Chemical Industry.

Application of Electronic Nose Systems on Animal-Source Food

Electronic nose, which is designed to perceive artificially the odour-active molecules in a sample headspace, has seen an increased use in the food industry as a rapid and reliable tool for quality assessment, classification, and authentication of several food items. The use of chemometrics and pattern recognition methods, together with gas sensors, emerged to be a very powerful analytical approach. In this chapter, an overview of the recent achievements in the field of electronic nose applications on animal-source food is given. Moreover, the authors deal with the recent research trends to overcome the actual sensor shortcomings, including sensor fusion techniques and their applications to evaluate animal-source foods and novel electronic nose systems.

Electronic Tongue-A Tool for All Tastes?

Electronic tongue systems are traditionally used to analyse: food products, water samples and taste masking technologies for pharmaceuticals. In principle, their applications are almost limitless, as they are able to almost completely reduce the impact of interferents and can be applied to distinguish samples of extreme complexity as for example broths from different stages of fermentation. Nevertheless, their applications outside the three principal sample types are, in comparison, rather scarce. In this review, we would like to take a closer look on what are real capabilities of electronic tongue systems, what can be achieved using mixed sensor arrays and by introduction of biosensors or molecularly imprinted polymers in the matrix. We will discuss future directions both in the sense of applications as well as system development in the ever-growing trend of low cost analysis.

Application of Sensory Evaluation, HS-SPME GC-MS, E-Nose, and E-Tongue for Quality Detection in Citrus Fruits

In this study, electronic tongue (E-tongue), headspace solid-phase microextraction gas chromatography-mass spectrometer (GC-MS), electronic nose (E-nose), and quantitative describe analysis (QDA) were applied to describe the 2 types of citrus fruits (Satsuma mandarins [Citrus unshiu Marc.] and sweet oranges [Citrus sinensis {L.} Osbeck]) and their mixing juices systematically and comprehensively. As some aroma components or some flavor molecules interacted with the whole juice matrix, the changes of most components in the fruit juice were not in proportion to the mixing ratio of the 2 citrus fruits. The potential correlations among the signals of E-tongue and E-nose, volatile components, and sensory attributes were analyzed by using analysis of variance partial least squares regression. The result showed that the variables from the sensor signals (E-tongue system and E-nose system) had significant and positive (or negative) correlations to the most variables of volatile components (GC-MS) and sensory attributes (QDA). The simultaneous utilization of E-tongue and E-nose obtained a perfect classification result with 100% accuracy rate based on linear discriminant analysis and also attained a satisfying prediction with high coefficient association for the sensory attributes (R(2) > 0.994 for training sets and R(2) > 0.983 for testing sets) and for the volatile components (R(2) > 0.992 for training sets and R(2) > 0.990 for testing sets) based on random forest. Being easy-to-use, cost-effective, robust, and capable of providing a fast analysis procedure, E-nose and E-tongue could be used as an alternative detection system to traditional analysis methods, such as GC-MS and sensory evaluation by human panel in the fruit industry.

PRACTICAL APPLICATION

Being easy-to-use, cost-effective, robust, and capable of providing a fast analysis procedure, E-nose and E-tongue could be used as an alternative detection system to traditional analysis methods for characterizing food flavors. Based on those results, one can draw a conclusion that the fusion system composed of E-tongue and E-nose could guarantee a satisfying result in the prediction of sensory attributes and volatile components for fruit quality profile.