Assessment of fruity aroma intensity in olive oils from different Spanish regions using a portable electronic nose

BACKGROUND

The organoleptic profile of an olive oil is a fundamental quality parameter obtained by human sensory panels. In this work, a portable electronic nose was employed to predict the fruity aroma intensity of 199 olive oil samples from different Spanish regions and cultivar varieties ('Picual', 'Arbequina', and 'Cornicabra'), with special emphasis in testing the robustness of the predictions versus cultivar variety variability. The primary data given by the electronic nose were used to obtain two different feature vectors that were employed to fit ridge and lasso regressions models to two datasets: one consisting of all the samples and another just the cv. Picual samples.

RESULTS

The results obtained showed mean average error (MAE) values below 0.88 in all cases, with an MAE of 0.67 for the 'Picual' model. These MAE values and the similarities in the model parameters fitted for the different data folds are in agreement with the results obtained in previous studies.

CONCLUSION

The large number of samples analyzed and the results obtained show the robustness of the approach and the applicability of the methods. Also, the results suggest that better performance can be obtained when specific models are fitted for particular cultivars. Overall, the proposed methods are capable of providing useful information for a fast screening of the fruity aroma intensity of olive oils. © 2023 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Design & development of adulteration detection system by fumigation method & machine learning techniques

A novel method for discovery of adulteration in edible oil is proposed based on concept of refractive index and electronic sensors. The research work focusses on two distinct methodologies like employing datasets and implementing a fumigation technique that integrates real-time hardware for testing Edible oil Impurities. In the first method, the dataset taken into consideration contains spectral data collected using Advanced ATR-MIR Spectroscopy for pure oil and various levels of adulteration with Vegetable oil. Each and every edible oil has a certain value of refractive index. When such oils are contemned in a change adding adulterants, the value of its refractive indices also changes. This value of refractive index serves as a feature for testing the oil and helps us in detecting the adulteration. If Oil is adulterated with vegetable oils, the refractive index will be lower and with animal fats, the refractive index will be higher than that of pure Oil. While in Fumigation Method a hardware module is develop in which adulterated & pure oil samples are heated at 40-50 °C for 4.66 min and the volatiles that are generated by varying gas concentrations are forcefully passed through to the MEMS Gas Sensor-MISC-2714 and Multichannel Gas sensor. The conductance of the sensors changes according to the gases sensed by the sensors contributes to features extraction. The conductance value serves as a feature for the classifier to determine whether the sample is highly, moderately, or lowly contaminated. Thus, in proposed methods we use different algorithms based on machine learning like KNN, Random Forest, CATBOOST and XGBOOST to accurately reveal the adulteration. Amongst all the applied algorithm Random Forest (RF) Classifier & XGBOOST algorithm outperform well and gives 100% accuracy. The proposed work is used for identifying food adulteration in edible food products which helps us to feed Society with high-quality food.

Dynamic changes in the water and volatile compounds of chicken breast during the frying process

The influence of frying times (0, 2, 4, 6, 8, and 10 min) on the continuous changes in the water distribution and the concentrations of key volatile compounds in chicken breast during the frying process were studied. The fried chicken samples could be distinguished by PCA of E-nose and PLS-DA of GC-MS. A total of 40 volatile compounds were identified by GC-MS, and 28 compounds were verified to be the key compounds after further screening by OAVs. The T22 was increased first and then decreased, while the M22 and M23 in fried chicken were considerably decreased and increased with increasing frying time, respectively. The content of the water and the total peak area of LF-NMR in fried chicken samples during the frying process significantly decreased, and the water was transferred from high to low degrees of freedom. In addition, water content, T21, T22, M22 and L* value were positively correlated with most alcohols and aldehydes, and were negatively correlated with pyrazines, while a*, b*, M23 and all amino acids were positively correlated with pyrazines and were negatively correlated with most alcohols and aldehydes. The results may guide the production processes of fried chicken and help produce high-quality chicken products.

Detection of Red Pepper Powder Adulteration with Allura Red and Red Pepper Seeds Using Hyperspectral Imaging

This study used shortwave infrared (SWIR) technology to determine whether red pepper powder was artificially adulterated with Allura Red and red pepper seeds. First, the ratio of red pepper pericarp to seed was adjusted to 100:0 (P100), 75:25 (P75), 50:50 (P50), 25:75 (P25), or 0:100 (P0), and Allura Red was added to the red pepper pericarp/seed mixture at 0.05% (A), 0.1% (B), and 0.15% (C). The results of principal component analysis (PCA) using the L, a, and b values; hue angle; and chroma showed that the pure pericarp powder (P100) was not easily distinguished from some adulterated samples (P50A-C, P75A-C, and P100B,C). Adulterated red pepper powder was detected by applying machine learning techniques, including linear discriminant analysis (LDA), linear support vector machine (LSVM), and k-nearest neighbor (KNN), based on spectra obtained from SWIR (1,000-1,700 nm). Linear discriminant analysis determined adulteration with 100% accuracy when the samples were divided into four categories (acceptable, adulterated by Allura Red, adulterated by seeds, and adulterated by seeds and Allura Red). The application of SWIR technology and machine learning detects adulteration with Allura Red and seeds in red pepper powder.

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.

Volatile-Based Diagnosis for Pathogenic Wood-Rot Fungus Fulvifomes siamensis by Electronic Nose (E-Nose) and Solid-Phase Microextraction/Gas Chromatography/Mass Spectrometry

Wood rot fungus Fulvifomes siamensis infects multiple urban tree species commonly planted in Singapore. A commercial e-nose (Cyranose 320) was used to differentiate some plant and fungi volatiles. The e-nose distinctly clustered the volatiles at 0.25 ppm, and this sensitivity was further increased to 0.05 ppm with the use of nitrogen gas to purge the system and set up the baseline. Nitrogen gas baseline resulted in a higher magnitude of sensor responses and a higher number of responsive sensors. The specificity of the e-nose for F. siamensis was demonstrated by distinctive clustering of its pure culture, fruiting bodies collected from different tree species, and in diseased tissues infected by F. siamensis with a 15-min incubation time. This good specificity was supported by the unique volatile profiles revealed by SPME GC-MS analysis, which also identified the signature volatile for F. siamensis-1,2,4,5-tetrachloro-3,6-dimethoxybenzene. In field conditions, the e-nose successfully identified F. siamensis fruiting bodies on different tree species. The findings of concentration-based clustering and host-tree-specific volatile profiles for fruiting bodies provide further insights into the complexity of volatile-based diagnosis that should be taken into consideration for future studies.

Comparison and discrimination of the terpenoids in 48 species of huajiao according to variety and geographical origin by E-nose coupled with HS-SPME-GC-MS

The unique flavor and aroma characteristics of huajiao were not only influenced by cultivated varieties, maturity, but also geographic origin. This study compared the terpenoids of 48 species of huajiao using headspace solid-phase microextraction-gas chromatography-mass spectrometry (HS-SPME-GC-MS) and electronic nose (E-nose). The E-nose results showed differences in huajiao from different origins and varieties, and from the PCA loading plots it was possible to conclude that some samples contained higher levels of hydrocarbons and alcohols, providing a preliminary discrimination between different species of huajiao. Further, GC-MS results showed that six key biomarkers could be used to distinguish red and green huajiao. Red huajiao in Central China contained more terpenoids than in other regions. Nine key biomarkers could be used to distinguish red huajiao from different regions. Oil huajiao exhibited a more distinct aroma in red huajiao. Green huajiao from Yunnan Province had more terpenoids than that from other provinces. The terpenoids content of Yunnan zhuyeqing was higher than other green huajiao. Heatmap analysis helped to find the most contributors of huajiao, which could be used as key terpenoids to differentiate huajiao of different regions or cultivars. Finally, through the correlation analysis of E-nose and GC-MS, it was found that the E-nose sensors could distinguish different huajiao by specific responses to some terpenoids in the samples.

Comprehensive Flavor Analysis of Volatile Components During the Vase Period of Cut Lily (Lilium spp. 'Manissa') Flowers by HS-SPME/GC-MS Combined With E-Nose Technology

Volatile compounds could affect the flavor and ornamental quality of cut flowers, but the flavor change occurring during the vase period of the cut flower is unclear. To clarify the dynamic changes during the vase period of cut lily (Lilium spp. 'Manissa') flowers, comprehensive flavor profiles were characterized by the electronic nose (E-nose) and headspace solid-phase microextraction gas chromatography-mass spectrometry (HS-SPME/GC-MS). The response value of sensor W2W was significantly higher than other sensors, and its response value reached the highest on day 4. A total of 59 volatiles were detected in cut lilies by HS-SPME/GC-MS, mainly including aldehydes, alcohols, and esters. There were 19 volatiles with odor activity values (OAVs) greater than 1. Floral and fruity aromas were stronger, followed by a pungent scent. Principal component analysis (PCA) and hierarchical cluster analysis (HCA) could effectively discriminate lily samples derived from different vase times on the basis of E-nose and HS-SPME-GC-MS. In summary, our study investigates the flavor change profile and the diversity of volatile compounds during the vase period of cut lilies, and lilies on day 4 after harvest exhibited excellent aroma and flavor taking into consideration of the flavor intensity and diversity. This provided theoretical guidance for the assessment of scent volatiles and flavor quality during the vase period of cut lily flowers and will be helpful for the application of cut lilies during the postharvest process.

Recent Advancement in Postharvest Loss Mitigation and Quality Management of Fruits and Vegetables Using Machine Learning Frameworks

Agriculture is an important component of the concept of sustainable development. Given the projected population growth, sustainable agriculture must accomplish food security while also being economically viable, socially responsible, and having the least possible impact on biodiversity and natural ecosystems. Deep learning has shown to be a sophisticated approach for big data analysis, with several successful cases in image processing, object identification, and other domains. It has lately been applied in food science and engineering. Among the issues and concerns addressed by these systems were food recognition; quality detection of fruits, vegetables, meat, and aquatic items; food supply chain; and food contamination. In precision agriculture, Artificial Intelligence (AI) is a commonly used technology for estimating food quality. It is especially important when evaluating crops at different phases of harvest and postharvest. Crop disease and damage detection is a high-priority activity because some postharvest diseases or damages, such as decay, can destroy crops and produce poisons that are toxic to humans. In this paper, we use Convolutional Neural Networks (CNNs)-based U-Net, DeepLab, and Mask R-CNN models to detect and predict postharvest deterioration zones in stored apple fruits. Our approach is unique in that it segmented and predicted postharvest decay and nondecay zones in fruits separately. This review will focus on postharvest physiology and management of fruits and vegetables, including harvesting, handling, packing, storage, and hygiene, to reduce postharvest loss (PHL) and improve crop quality. It will also cover postharvest handling under extreme weather conditions and potential impacts of climate change on vegetable postharvest and postharvest biotechnology on PHL.

Characterization and Discrimination of Apples by Flash GC E-Nose: Geographical Regions and Botanical Origins Studies in China

Forty-one apple samples from 7 geographical regions and 3 botanical origins in China were investigated. A total of 29 volatile compounds have been identified by flash GC E-nose. They are 17 esters, 5 alcohols, 3 aldehydes, 1 ketone, and 3 others. A principal component analysis was employed to study the relationship between varieties and volatiles. A partial least squares discriminant analysis (PLS-DA), stepwise linear discriminant analysis (SLDA), and decision tree (DT) are used to discriminate apples from 4 geographical regions (34 apple samples) and 3 botanical origins (36 apple samples). The most influential markers identified by PLS-DA are 2-hexadecanone, methyl decanoate, tetradecanal, 1,8-cineole, hexyl 2-butenoate, (Z)-2-octenal, methyl 2-methylbutanoate, ethyl butyrate, dimethyl trisulfide, methyl formate, ethanol, S(-)2-methyl-1-butanol, ethyl acetate, pentyl acetate, butyl butanoate, butyl acetate, and ethyl octanoate. From the present work, SLDA reveals the best discrimination results in geographical regions and botanical origins, which are 88.2% and 88.9%, respectively. Although machine learning DT is attempted to classify apple samples, the results are not satisfactory.

Integration of Innovative Technologies in the Agri-Food Sector: The Fundamentals and Practical Case of DNA-Based Traceability of Olives from Fruit to Oil

Several socio-economic problems have been hidden by the COVID-19 pandemic crisis. Particularly, the agricultural and food industrial sectors have been harshly affected by this devastating disease. Moreover, with the worldwide population increase and the agricultural production technologies being inefficient or obsolete, there is a great need to find new and successful ways to fulfill the increasing food demand. A new era of agriculture and food industry is forthcoming, with revolutionary concepts, processes and technologies, referred to as Agri-food 4.0, which enables the next level of agri-food production and trade. In addition, consumers are becoming more and more aware about the origin, traceability, healthy and high-quality of agri-food products. The integration of new process of production and data management is a mandatory step to meet consumer and market requirements. DNA traceability may provide strong approach to certify and authenticate healthy food products, particularly for olive oil. With this approach, the origin and authenticity of products are confirmed by the means of unique nucleic acid sequences. Selected tools, methods and technologies involved in and contributing to the advance of the agri-food sector are presented and discussed in this paper. Moreover, the application of DNA traceability as an innovative approach to authenticate olive products is reported in this paper as an application and promising case of smart agriculture.

Application of Neuromorphic Olfactory Approach for High-Accuracy Classification of Malts

Current developments in artificial olfactory systems, also known as electronic nose (e-nose) systems, have benefited from advanced machine learning techniques that have significantly improved the conditioning and processing of multivariate feature-rich sensor data. These advancements are complemented by the application of bioinspired algorithms and architectures based on findings from neurophysiological studies focusing on the biological olfactory pathway. The application of spiking neural networks (SNNs), and concepts from neuromorphic engineering in general, are one of the key factors that has led to the design and development of efficient bioinspired e-nose systems. However, only a limited number of studies have focused on deploying these models on a natively event-driven hardware platform that exploits the benefits of neuromorphic implementation, such as ultra-low-power consumption and real-time processing, for simplified integration in a portable e-nose system. In this paper, we extend our previously reported neuromorphic encoding and classification approach to a real-world dataset that consists of sensor responses from a commercial e-nose system when exposed to eight different types of malts. We show that the proposed SNN-based classifier was able to deliver 97% accurate classification results at a maximum latency of 0.4 ms per inference with a power consumption of less than 1 mW when deployed on neuromorphic hardware. One of the key advantages of the proposed neuromorphic architecture is that the entire functionality, including pre-processing, event encoding, and classification, can be mapped on the neuromorphic system-on-a-chip (NSoC) to develop power-efficient and highly-accurate real-time e-nose systems.

Volatile-Olfactory Profiles of cv. Arbequina Olive Oils Extracted without/with Olive Leaves Addition and Their Discrimination Using an Electronic Nose

Oils from cv. Arbequina were industrially extracted together with olive leaves of cv. Arbequina or Santulhana (1%, w/w), and their olfactory and volatile profiles were compared to those extracted without leaves addition (control). The leaves incorporation resulted in green fruity oils with fresh herbs and cabbage olfactory notes, while control oils showed a ripe fruity sensation with banana, apple, and dry hay grass notes. In all oils, total volatile contents varied from 57.5 to 65.5 mg/kg (internal standard equivalents), being aldehydes followed by esters, hydrocarbons, and alcohols the most abundant classes. No differences in the number of volatiles were observed. The incorporation of cv. Arbequina or Santulhana leaves significantly reduced the total content of alcohols and esters (minus 37–56% and 10–13%, respectively). Contrary, cv. Arbequina leaves did not influence the total content of aldehydes or hydrocarbons, while cv. Santulhana leaves promoted a significant increase (plus 49 and 10%, respectively). Thus, a leaf-cultivar dependency was observed, tentatively attributed to enzymatic differences related to the lipoxygenase pathway. Olfactory or volatile profiles allowed the successful unsupervised differentiation of the three types of studied cv. Arbequina oils. Finally, a lab-made electronic nose was applied to allow the nondestructive discrimination of cv. Arbequina oils extracted with or without the incorporation of olive leaves (100% and 99 ± 5% of correct classifications for leave-one-out and repeated K-fold cross-validation variants), being a practical tool for ensuring the label correctness if future commercialization is envisaged. Moreover, this finding also strengthened that olive oils extracted with or without olive leaves incorporation possessed quite different olfactory patterns, which also depended on the cultivar of the olive leaves.

Prediction of Fruity Aroma Intensity and Defect Presence in Virgin Olive Oil Using an Electronic Nose

The organoleptic profile of a Virgin Olive Oil is a key quality parameter that is currently obtained by human sensory panels. The development of an instrumental technique capable of providing information about this profile quickly and online is of great interest. This work employed a general purpose e-nose, in lab conditions, to predict the level of fruity aroma and the presence of defects in Virgin Olive Oils. The raw data provided by the e-nose were used to extract a set of features that fed a regressor to predict the level of fruity aroma and a classifier to detect the presence of defects. The results obtained were a mean validation error of 0.5 units for the prediction of fruity aroma using lasso regression; and 88% accuracy for the defect detection using logistic regression. Finally, the identification of two out of ten specific sensors of the e-nose that can provide successful results paves the way to the design of low-cost specific electronic noses for this application.

Detection of lung cancer with electronic nose using a novel ensemble learning framework

Breath analysis based on electronic nose (e-nose) is a promising new technology for the detection of lung cancer that is non-invasive, simple to operate and cost-effective. Lung cancer screening by e-nose relies on predictive models established using machine learning methods. However, using only a single machine learning method to detect lung cancer has some disadvantages, including low detection accuracy and high false negative rate. To address these problems, groups of individual learning models with excellent performance were selected from classic models, including Support Vector Machine, Decision Tree, Random Forest, Logistic Regression and K-nearest neighbor regression, to build an ensemble learning framework (PCA-SVE). The output result of the PCA-SVE framework was obtained by voting. To test this approach, we analyzed 214 breath samples measured by e-nose with 11 gas sensors of four types using the proposed PCA-SVE framework. Experimental results indicated that the accuracy, sensitivity, and specificity of the proposed framework were 95.75%, 94.78%, and 96.96%, respectively. This framework overcomes the disadvantages of a single model, thereby providing an improved, practical alternative for exhaled breath analysis by e-nose.

Comparison of flavour fingerprint, electronic nose and multivariate analysis for discrimination of extra virgin olive oils

Flavour is a special way to discriminate extra virgin olive oils (EVOOs) from other aroma plant oils. In this study, different ratios (5, 10, 15, 20, 30, 50, 70 and 100%) of peanut oil (PO), corn oil (CO) and sunflower seed oil (SO) were discriminated from raw EVOO using flavour fingerprint, electronic nose and multivariate analysis. Fifteen different samples of EVOO were selected to establish the flavour fingerprint based on eight common peaks in solid-phase microextraction-gas chromatography-mass spectrometry corresponding to 4-methyl-2-pentanol, (E)-2-hexenal, 1-tridecene, hexyl acetate, (Z)-3-hexenyl acetate, (E)-2-heptenal, nonanal and α-farnesene. Partial least square discrimination analysis (PLS-DA) was used to differentiate EVOOs and mixed oils containing more than 20% of PO, CO and SO. Furthermore, better discrimination efficiency was observed in PLS-DA than PCA (70% of CO and SO), which was equivalent to the correlation coefficient method of the fingerprint (20% of PO, CO and SO). The electronic nose was able to differentiate oil samples from samples containing 5% mixture. The discrimination method was selected based on the actual requirements of quality control.

Odor Discrimination by Similarity Measures of Abstract Odor Factor Maps from Electronic Noses

The aim of this study is to improve the discrimination performance of electronic noses by introducing a new method for measuring the similarity of the signals obtained from the electronic nose. We constructed abstract odor factor maps (AOFMs) as the characteristic maps of odor samples by decomposition of three-way signal data array of an electronic nose. A similarity measure for two-way data was introduced to evaluate the similarities and differences of AOFMs from different samples. The method was assessed by three types of pipe and powder tobacco samples. Comparisons were made with other techniques based on PCA, SIMCA, PARAFAC and PARAFAC2. The results showed that our method had significant advantages in discriminating odor samples with similar flavors or with high VOCs release.