Electronic Nose Research Articles

Early Identification of Rotten Potatoes Using an Electronic Nose Based on Feature Discretization and Ensemble Convolutional Neural Network

Early Identification of Rotten Potatoes Using an Electronic Nose Based on Feature Discretization and Ensemble Convolutional Neural Network

Evaluating the Non-Invasive Measurement of Apple Aroma Using Electronic Nose Device through Comparison with Direct Mass Spectrometry, Sugar Content, and Ripeness Measurements

Evaluating the Non-Invasive Measurement of Apple Aroma Using Electronic Nose Device through Comparison with Direct Mass Spectrometry, Sugar Content, and Ripeness Measurements

Diagnostic performance of volatile organic compounds analysis and electronic noses for detecting colorectal cancer: a systematic review and meta-analysis

IntroductionThe detection of Volatile Organic Compounds (VOCs) could provide a potential diagnostic modality for the early detection and surveillance of colorectal cancers. However, the overall diagnostic accuracy of the proposed tests remains uncertain.ObjectiveThis systematic review is to ascertain the diagnostic accuracy of using VOC analysis techniques and electronic noses (e-noses) as noninvasive diagnostic methods for colorectal cancer within the realm of clinical practice.MethodsA systematic search was undertaken on PubMed, EMBASE, Web of Science, and the Cochrane Library to scrutinize pertinent studies published from their inception to September 1, 2023. Only studies conducted on human subjects were included. Meta-analysis was performed using a bivariate model to obtain summary estimates of sensitivity, specificity, and positive and negative likelihood ratios. The Quality Assessment of Diagnostic Accuracy Studies 2 tool was deployed for quality assessment. The protocol for this systematic review was registered in PROSPERO, and PRISMA guidelines were used for the identification, screening, eligibility, and selection process.ResultsThis review encompassed 32 studies, 22 studies for VOC analysis and 9 studies for e-nose, one for both, with a total of 4688 subjects in the analysis. The pooled sensitivity and specificity of VOC analysis for CRC detection were 0.88 (95% CI, 0.83-0.92) and 0.85 (95% CI, 0.78-0.90), respectively. In the case of e-nose, the pooled sensitivity was 0.87 (95% CI, 0.83-0.90), and the pooled specificity was 0.78 (95% CI, 0.62-0.88). The area under the receiver operating characteristic analysis (ROC) curve for VOC analysis and e-noses were 0.93 (95% CI, 0.90-0.95) and 0.90 (95% CI, 0.87-0.92), respectively.ConclusionThe outcomes of this review substantiate the commendable accuracy of VOC analysis and e-nose technology in detecting CRC. VOC analysis has a higher specificity than e-nose for the diagnosis of CRC and a sensitivity comparable to that of e-nose. However, numerous limitations, including a modest sample size, absence of standardized collection methods, lack of external validation, and a notable risk of bias, were identified. Consequently, there exists an imperative need for expansive, multi-center clinical studies to elucidate the applicability and reproducibility of VOC analysis or e-nose in the noninvasive diagnosis of colorectal cancer.Systematic review registrationhttps://www.crd.york.ac.uk/prospero/#recordDetails, identifier CRD42023398465.

Development of a comprehensive classification model for determining the storage day of frigate tuna (Auxis thazard) for freshness evaluation using a portable electronic nose

SummaryEnsuring the freshness of fish is essential to guaranteeing safer products for consumers. A classification model was developed using the PEN3 electronic nose to predict fish freshness with its storage day. Frigate tuna (Auxis thazard) was used for odour sampling along with the total volatile base nitrogen (TVB‐N), at 4 °C for 14 days every other day. Random forest and support vector machine (SVM) were performed to develop freshness classification models based on PEN3 data and 100% and 99.8% accuracies were obtained, respectively, in distinguishing the eight storage day classes. The PEN3 sensors including W2S, W1S, W1W, W3S, and W6S were identified as key sensors for fish freshness. TVB‐N analysis advances the freshness prediction of e‐nose and three freshness levels were identified as ‘Fresh’, applicable from the 0th to the 6th day; ‘Moderately fresh’, lasting from the 7th to the 9th day; and ‘Unsuitable for consumption’, applicable from the 10th day onwards.

Insights into the Volatile Flavor Profiles of Two Types of Beef Tallow via Electronic Nose and Gas Chromatography–Ion Mobility Spectrometry Analysis

In the current study, an electronic nose (E-nose) and gas chromatography–ion mobility spectrometry (GC-IMS) were employed to investigate the volatile flavor compounds (VFCs) of intense flavor beef tallow (L) and ordinary beef tallow (P). The study results indicate that an E-nose combined with an LDA and GC-IMS combined with an OPLS-DA can effectively distinguish between the two types of beef tallow. Compared with ordinary beef tallow, the E-nose sensors of intense flavor beef tallow have stronger response signals to sulfides, terpenes, and nitrogen oxides. A total of 22 compounds contribute to making the flavor of intense flavor beef tallow more typical and richer; in contrast, ethyl acetate was the main aroma-active compound found in the ordinary beef tallow. Sulfur-containing compounds and terpenoids might be the key substances that cause sensory flavor differences between the two types of beef tallow. In conclusion, the results of this study clarify the characteristics and differences of the two types of beef tallow and provide an enhanced understanding of the differences in the flavors of the two types of beef tallow.

Comparative metabolomics study on the quality of Antarctic krill (Euphausia superba) stored at different temperatures

SummaryIn this study, the effect of short‐term storage at different temperatures (0, 4 and −8 °C) on the quality of Antarctic krill was investigated using the main quality indicators as a reference, combined with electronic nose and untargeted metabolomics. Antarctic krill stored at lower temperatures (−8 °C) were of better quality and had a flavour similar to that of the original Antarctic krill. Metabolomics analyses showed that differential metabolites (DMS) were more abundant in Antarctic krill at higher temperatures (4 °C), with sixty‐five metabolites having reduced expression and forty‐five metabolites having increased expression; Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses showed that amino acid metabolism and nucleotide metabolism pathways were the Five DMS, including α‐ketoglutarate, glutamate, succinate, sucrose and glutarate, can be used as potential biomarkers to monitor quality changes during short‐term storage of Antarctic krill. In addition, the association between quality indicators and differential metabolites remains to be explored.

Cross-site validation of lung cancer diagnosis by electronic nose with deep learning: a multicenter prospective study

BackgroundAlthough electronic nose (eNose) has been intensively investigated for diagnosing lung cancer, cross-site validation remains a major obstacle to be overcome and no studies have yet been performed.MethodsPatients with lung cancer, as well as healthy control and diseased control groups, were prospectively recruited from two referral centers between 2019 and 2022. Deep learning models for detecting lung cancer with eNose breathprint were developed using training cohort from one site and then tested on cohort from the other site. Semi-Supervised Domain-Generalized (Semi-DG) Augmentation (SDA) and Noise-Shift Augmentation (NSA) methods with or without fine-tuning was applied to improve performance.ResultsIn this study, 231 participants were enrolled, comprising a training/validation cohort of 168 individuals (90 with lung cancer, 16 healthy controls, and 62 diseased controls) and a test cohort of 63 individuals (28 with lung cancer, 10 healthy controls, and 25 diseased controls). The model has satisfactory results in the validation cohort from the same hospital while directly applying the trained model to the test cohort yielded suboptimal results (AUC, 0.61, 95% CI: 0.47─0.76). The performance improved after applying data augmentation methods in the training cohort (SDA, AUC: 0.89 [0.81─0.97]; NSA, AUC:0.90 [0.89─1.00]). Additionally, after applying fine-tuning methods, the performance further improved (SDA plus fine-tuning, AUC:0.95 [0.89─1.00]; NSA plus fine-tuning, AUC:0.95 [0.90─1.00]).ConclusionOur study revealed that deep learning models developed for eNose breathprint can achieve cross-site validation with data augmentation and fine-tuning. Accordingly, eNose breathprints emerge as a convenient, non-invasive, and potentially generalizable solution for lung cancer detection.Clinical trial registrationThis study is not a clinical trial and was therefore not registered.

Determining the potato samples processed manner with an electronic nose system supported by a machine-learning approach

Through several studies, electronic nose (E-nose) devices have been demonstrated to serve as useful measurement equipment for the fast and reliable analysis of complex odour profiles in a wide range of fields, including the area of ensuring food safety. In the same perspective, i.e. checking food safety comes this work, where potatoes are assessed using an E-nose principally made of five metal oxide gas sensors supported with a machine learning algorithm, said evaluation is based on their origin fields: naturally treated, treated with chemical NPK fertilizers, or treated with chicken manure. The technique of support vector machines has been exploited for the data obtained from the multi-sensor system in order to distinguish the potato types mentioned by following two methods: a direct method where all the data have been exploited with a rate of success of 91.7%, and a composed method where the classification was first between naturally treated samples and those treated differently with a success rate of 96.7%, then a classification between those treated differently had a 92.5% success rate. A microbiological analysis was also carried out and its results were compared with those obtained by the E-nose. As per the two methods’ results, the distinction of the potato types by the nature of the cultivated fields is possible with the recording of the multisensory system superiority due to response time, low cost, simplicity, and portability.

Effect of jujube powder addition on the aroma profile of quinoa snacks (QS)

AbstractQuinoa is a full‐nutrition food; however, its poor flavor and small size make it not the best food option for direct consumption. In this study, a quinoa snack (QS, a cake) was developed, and the aroma profile of the products was improved by adding jujube fruit powder (made from dried jujube fruits, from 5% to 30%). Gas chromatography mass spectrum (GC–MS) combined with electronic nose (e‐nose) was applied for characterizing the aroma profiles of QS samples. Results showed a total of 26 aroma compounds were identified in QS samples by GC–MS, and 3‐methylbutanol (from 1525 μg/kg in QS‐30 to 3487 μg/kg in QS‐0), ethanol (from 1126 μg/kg in QS‐0 to 3581 μg/kg in QS‐30), hexanal (from 125.6 μg/kg in QS‐30 to 984.1 μg/kg in QS‐0), and acetaldehyde (from 531.9 μg/kg in QS‐30 to 191.1 μg/kg in QS‐0) were common. The e‐nose response of W1S (sensitive to methane, from 17.50 of QS‐0 to 93.85 of QS‐30) and W1W (sensitive to sulfur‐organic compounds of e‐nose, from 15.57 of QS‐0 to 39.50 of QS‐30) were significantly higher, and significant differences were presented among QS samples. In conclusion, the aroma profile of the QS sample was significantly (p < .05) enhanced by the addition of jujube powder, and QS‐30 with the highest jujube content (30%) presented the strongest aroma profile. Moreover, QS samples with different additions of jujube powders could be well distinguished by principal component analysis (PCA), and the combination of e‐nose and GC–MS was effective in the volatile profile analysis of QS samples.

Influence of germination and roasting on the characteristic volatile organic compounds of quinoa using sensory evaluation, E-nose, HS-GC-IMS, and HS-SPME-GC-MS

This study aimed to investigate the effects of germination and roasting on the flavor of quinoa. Firstly, the aroma of quinoa and germinated quinoa roasted under different conditions was analyzed using sensory evaluation and electronic nose (E-nose). Results showed that the best favorable aroma of quinoa and germinated quinoa was obtained when roasted at 160 °C for 15 min. Then, a total of 34 and 80 volatile organic compounds (VOCs) of quinoa and germinated quinoa roasted at 160 °C for 15 min were determined using headspace-gas chromatography-ion mobility spectrometry (HS-GC-IMS) and headspace solid-phase microextraction gas chromatography–mass spectrometry (HS-SPME-GC–MS), respectively. Germination and roasting effectively reduced the contents of VOCs that produced undesirable flavor. Moreover, germination improved the floral aromas, while roasting mainly produced caramel, cocoa, and roasted nut aromas of quinoa. This study indicated that germination and roasting treatments might serve as promising processing methods to improve the flavor of quinoa.

Effect of Lactobacillus plantarum and flavourzyme on protein degradation and flavor development in grass carp during fermentation

This study examined the effect of Flavourzyme and Lactobacillus plantarum (L. plantarum) on protein degradation and flavor development during grass carp fermentation. The control groups comprised natural fermentation and fermentation with L. plantarum. Compared with the two control samples, those exposed to combined Flavourzyme and L. plantarum fermentation exhibited lower moisture content and enhanced protein hydrolysis, which accelerated the production of water-soluble taste substances (trichloroacetic acid-soluble peptides and free amino acids). The electronic tongue and electronic nose results indicated that the grass carp subjected to combined fermentation way displayed a more intense umami taste and aroma. Moreover, the sensory evaluation results confirmed that the combined fermentation method significantly improved the taste and odor attributes of fermented grass carp. In conclusion, combined fermentation with Flavourzyme and L. plantarum may effectively reduce fermentation time and enhance the flavor of fermented grass carp products.

Preparation, taste characterization, and evaluation of oyster composite products with increased umami and salty

Excessive consumption of sodium chloride is known to contribute to a range of health issues. Umami components, when combined with salt, can effectively lower sodium consumption due to their synergistic flavor enhancement. In this research, through sensory evaluation, electronic tongue, and electronic nose, we have determined the optimal formulation of oyster extracts for a Composite Umami-Enhancing Seasoning (CUES). The ideal CUES formulation comprises 50% monosodium glutamate (MSG), 16% salt, 6% sugar, 5% maltodextrin, 10 % of oyster powder (OY-W), 10% plant hydrolyzed protein, and 3% I+G. The OY-W fraction contains a low-threshold umami peptide that enhances the overall taste profile. Sensory evaluation indicates that the CUES formulation diminishes perceived sourness, sweetness, and bitterness, while simultaneously elevating the umami and saltiness compared to OY-W alone. Among the CUES formulations with an equivalent sodium chloride content, M-PO achieves the highest umami value. CUES were distinguished by Principal Component Analysis (PCA) analysis from the electronic nose, and odor profiles of M-PO and a commercially available clam-based umami enhancer (BWG) were similar. The W5S component was identified as the most significant contributor. The physical properties of the CUES formulations were systematically evaluated, taking into account factors such as water loss, moisture retention, hygroscopicity, bulk density, solubility, and flowability. The utilization of maltodextrin has led to a significant enhancement in water loss and moisture retention. This study paves the way for the development of low-sodium seasoning alternatives that can satisfy consumer taste preferences without compromising health and safety.

Electronic nose for odor monitoring at a landfill fenceline: training and validation of a model for real-time odor concentration measurement

In recent years, electronic noses, or more generally Instrumental Odor Monitoring Systems (IOMS), have aroused increasing interest in the field of environmental monitoring.One of the most interesting applications of these instruments is the real-time estimation of the odor concentration at plant fencelines to continuously monitor odor emissions and identify anomalous conditions. In this type of application, it is possible to setting a “warning” threshold, enabling the continuous check of proper functioning of the plant and sudden intervention in case of malfunctions, preventing, at the same time, the risk of odor events at the receptors. For this purpose, it is necessary to provide a continuous, fast and reliable measurement of the odor concentration, which is nowadays one of the main challenges of this technology.In this context, this work proposes the development of a quantification model for quantifying odors detected at the fenceline of a landfill characterized by very different odor fingerprints. A double-step quantification model, firstly identifying the different odor classes to which the ambient air monitored at the fenceline by the IOMS belong to, and then developing different specific PLS regression models for each of the odor classes identified, was developed. The results of the proposed quantification model were compared to the ones obtained developing a “global” quantification model, which implements the regression on the globality of the training set, without differentiating between the odor classes. Then, they were further evaluated by comparison with the odor events detected at the sensitive receptor by another electronic nose. Moreover, the combined evaluation of the odor events at the plant fenceline and the receptor, respectively, together with the meteorological data highlighted the need of identifying variable warning thresholds for the odor concentrations at the fenceline according to effectively account for meteorological conditions and produce an output that is more correlated with the probability that an odor is perceived outside of the plant.

Combining lipase enzymatic techniques and antioxidants on the flavor of structured lipids (SLs) prepared from goat butter and coconut oil

Enzymatic transesterification can improve the quality of goat butter, however, the high temperature may lead to oil oxidation and produce a bad taste. In this study, goat butter (GB) and coconut oil (CO) were combined to synthesize structured lipids (SLs) by enzymatic transesterification, and antioxidants were added to inhibit oxidation to improve the oils’ flavor. The Lipozyme TLIM and tert-butylhydroquinone (TBHQ) were screened for SLs synthesis. The contents of SLs were 56.24% under the optimal conditions of 8 h reaction time, 5°C reaction temperature, 8% enzyme dosage, and 3:1 (w/w) substrate ratio, and the addition of antioxidants had no significant effect on the contents of SLs. It was demonstrated that short-chain fatty acids in the SLs were significantly reduced by 59.2%, and the medium-chain fatty acids were increased by 54.9% compared to GB. One hundred volatile compounds were identified in the lipid samples and classified as (1) long-chain alkane aromatic components and aromatic components, which remarkably decreased by 58.9%, and (2) alcohols, aldehydes, and ketones, which increased by 12.9%, through using solid-phase microextraction coupled with gas chromatography-mass spectrometry (SPME-GC-MS) and electronic nose. The relative aroma activity value (ROAV) of 9 key volatile aroma components was higher than 1 in the SLs, which greatly contributed to the reduction of goaty flavor and increasing cream flavor. The results suggested that the goaty flavor of GB could be significantly reduced by decreasing the short-chain fatty acids contents in SLs through enzymatic transesterification with CO, while the addition of antioxidants efficiently inhibited excessive lipids oxidation and increased the content of long-chain aldehydes, ketones, and lactones, thus enhancing the cream flavor, which had great potential to be utilized as natural food flavor additives.

Characterization and discrimination of the taste and aroma of Tibetan Qingke baijiu using electronic tongue, electronic nose and gas chromatography–mass spectrometry

Qingke baijiu (QKBJ) serves as a distinctive representation of Tibet in China. Nevertheless, the characteristics and regional disparities of QKBJ from various Tibetan locales have yet to be comprehensively explored. This study, through the use of cutting-edge technologies including electronic nose (E-nose), electronic tongue (E-tongue), and gas chromatography–mass spectrometry (GC–MS), had identified that eight distinct varieties of QKBJ predominantly exhibit sweetness, sourness, and umami in terms of taste. Furthermore, E-nose showed that QKBJ samples contain elevated levels of nitrogen oxides, methane, sulfur compounds, alcohols, aldehydes, ketones and aromatics. Concurrently, the content proportions of esters, alcohols, acids, aldehydes, and ketones varied among QKBJ samples, leading to distinct aromas such as baked and vegetal notes. The comprehensive results consistently highlighted the significant differentiation of Sannan samples from the others in terms of taste and aroma. In conclusion, this research could provide a data support for excavating and improving flavor quality of QKBJ.

A feature extractor for temporal data of electronic nose based on parallel long short-term memory network in flavor discrimination of Chinese vinegars

Volatile flavor is a key indicator of food quality which can directly affect consumer preference and purchase intention. Electronic nose is considered as a promising intelligent sensory analysis tool for food flavor assessment, however, extracting effective features from the gas sensor array is still a major challenge, which largely determines the performance of subsequent classifiers. Here, a parallel long short-term memory (LSTM) network is proposed as a feature extractor for automatically extracting features from the whole time series of sensor responses in flavor discrimination of five Chinese vinegars. The network was trained by the temporal data from the sensor array and yielded different feature patterns corresponding to different vinegars, which were then fed to other conventional classifiers for pattern recognition. We also evaluated the influence of the extracted feature dimension that is related to the dimension of the hidden state of the LSTM layer on the classification performance. The results indicate that a larger dimension of extracted feature is unnecessary for promoting classification accuracy, instead, the optimum dimension 4 of the hidden state gives the highest accuracy of 95.8% in this application under the softmax evaluator. Moreover, much higher accuracies were obtained when combined with other sophisticated classifiers such as support vector machine. The results demonstrate that the proposed network is competent to extract features directly and automatically from the temporal data of the electronic nose.

Autonomous Artificial Olfactory Sensor Systems with Homeostasis Recovery via a Seamless Neuromorphic Architecture.

Neuromorphic olfactory systems have been actively studied in recent years owing to their considerable potential in electronic noses, robotics, and neuromorphic data processing systems. However, conventional gas sensors typically have the ability to detect hazardous gas levels but lack synaptic functions such as memory and recognition of gas accumulation, which are essential for realizing human-like neuromorphic sensory system. In this study, we propose a seamless architecture for a neuromorphic olfactory system capable of detecting and memorizing the present level and accumulation status of nitrogen dioxide (NO2) during continuous gas exposure, regulating a self-alarm implementation triggered after 147 and 85 s at a continuous gas exposure of 20 and 40ppm, respectively. Thin-film-transistor type gas sensors utilizing carbon nanotube semiconductors detect NO2 gas molecules through carrier trapping and exhibit long-term retention properties, which are compatible with neuromorphic excitatory applications. Additionally, the neuromorphic inhibitory performance was also characterized via gas desorption with programmable ultraviolet light exposure, demonstrating homeostasis recovery. These results provide a promising strategy for developing a facile artificial olfactory system that demonstrates complicated biological synaptic functions with a seamless and simplified system architecture. This article is protected by copyright. All rights reserved.

InGaN/GaN multi-quantum well nanowires: Enhanced trace-level NO2 detection for environmental and breath analysis

The World Health Organization highlights nitrogen dioxide (NO2) as a key atmospheric pollutant impacting air quality and human health. To date, several sensors have been proposed for NO2 detection and disease monitoring, but their effectiveness is limited because of low sensitivity and high operational temperatures. Herein, we propose a selective and sensitive NO2 sensor based on indium gallium nitride/gallium nitride multiple quantum wells (InGaN/GaN-MQWs). We explored different InGaN/GaN-MQWs configurations (InGaN/GaN-MQW1, InGaN/GaN-MQW2, InGaN/GaN-MQW3), developed through metal–organic chemical vapor deposition (MOCVD), to analyze their impact on gas sensing performance. Our findings reveal that the InGaN/GaN-MQW2 sensor at 150 °C exhibits a response 4.0, 3.1, and 1.65 times greater than GaN-NWs, InGaN/GaN-MQW1, and InGaN/GaN-MQW3 sensors, respectively. The limit of detection (LOD) for the InGaN/GaN-MQW2 sensor is 3 parts per billion (ppb), significantly lower than the NO2 threshold value of 53 ppb. Under ultraviolet (UV) light, the response of InGaN/GaN-MQW2 is 5.51-fold, 4.18-fold, and 1.82-fold higher than that of the GaN-NWs, InGaN/GaN-MQW1, and InGaN/GaN-MQW2 sensors, respectively. Importantly, our hybrid nanocomposite-based electronic nose (e-nose) sensor arrays could distinguish between healthy and simulated unhealthy breaths with high accuracy, promising a new era of efficient, non-invasive disease detection through breath analysis.

An Adaptive Deep Learning Method Combined With an Electronic Nose System for Quality Identification of Soybeans Storage Period

An Adaptive Deep Learning Method Combined With an Electronic Nose System for Quality Identification of Soybeans Storage Period

An Embedded Machine Learning-Based Spoiled Leftover Food Detection Device for Multiclass Classification

Food waste’s negative environmental repercussions are causing it to become a global concern. Several studies have examined thefactors influencing food waste behaviour and management. This work was motivated by the lack of previous research on machinelearning and electronic noses to detect contamination from leftover cooked food. This work proposes using machine learning algorithms and electronic nose technology to recognise and forecast the contamination in leftover cooked food. After five days of storage, the freshness of cooked leftovers was evaluated using an electronic nose combined with machine learning algorithms. Most food samples used in this work were from Malaysian’s leftover lunch and dinner dishes. Four (4) gas sensors—MQ-2, MQ-136, MQ-137, and MQ-138—are used in developing the electronic nose to identify the presence of gas in the food sample. The data from the gas sensors was analysed using machine learning methods, namely Random Forest, k-nearest Neighbors, Support Vector Machine, and Linear Discriminant Analysis. Based on the results, a multi-classification technique yielded a greater accuracy rate in classifying and identifying the level of contamination in the cooked food leftovers, with average accuracy ranging from 90 percent to 100 percent. In conclusion, the work demonstrates a novel method for using machine learning algorithms to classify, identify, and predict the contamination level of leftover cooked food, contributing to reducing food waste generated primarily by Malaysians.