VOC-based detection of prostate cancer using an electronic nose and ion mobility spectrometry: A novel urine-based approach.

BACKGROUND: Many diseases leave behind specific metabolites which can be detected from breath and urine as volatile organic compounds (VOC). Our group previously described VOC-based methods for the detection of bladder cancer and urinary tract infections. This study investigated whether prostate cancer can be diagnosed from VOCs in urine headspace. METHODS: For this pilot study, mid-stream urine samples were collected from 56 patients with histologically confirmed prostate cancer. A control group was formed with 53 healthy male volunteers matched for age who had recently undergone a negative screening by prostate-specific antigen (PSA) and digital rectal exam. Headspace measurements were performed with the electronic nose Cyranose 320TM. Statistical comparison was performed using principal component analysis, calculating Mahalanobis distance, and linear discriminant analysis. Further measurements were carried out with ion mobility spectrometry (IMS) to compare detection accuracy and to identify potential individual analytes. Bonferroni correction was applied for multiple testing. RESULTS: The electronic nose yielded a sensitivity of 77% and specificity of 62%. Mahalanobis distance was 0.964, which is indicative of limited group separation. IMS identified a total of 38 individual analytical peaks, two of which showed significant differences between groups (p < 0.05). To discriminate between tumor and controls, a decision tree with nine steps was generated. This model led to a sensitivity of 98% and specificity of 100%. CONCLUSIONS: VOC-based detection of prostate cancer seems feasible in principle. While the first results with an electronic nose show some limitations, the approach can compete with other urine-based marker systems. However, it seems less reliable than PSA testing. IMS is more accurate than the electronic nose with promising sensitivity and specificity, which warrants further research. The individual relevant metabolites identified by IMS should further be characterized using gas chromatography/mass spectrometry to facilitate potential targeted rapid testing.

Advancing accuracy in breath testing for lung cancer: strategies for improving diagnostic precision in imbalanced data.

BACKGROUND: Breath testing using an electronic nose has been recognized as a promising new technique for the early detection of lung cancer. Imbalanced data are commonly observed in electronic nose studies, but methods to address them are rarely reported. OBJECTIVE: The objectives of this study were to assess the accuracy of electronic nose screening for lung cancer with imbalanced learning and to select the best mechanical learning algorithm. METHODS: We conducted a case‒control study that included patients with lung cancer and healthy controls and analyzed metabolites in exhaled breath using a carbon nanotube sensor array. The study used five machine learning algorithms to build predictive models and a synthetic minority oversampling technique to address imbalanced data. The diagnostic accuracy of lung cancer was assessed using pathology reports as the gold standard. RESULTS: We enrolled 190 subjects between 2020 and 2023. A total of 155 subjects were used in the final analysis, which included 111 lung cancer patients and 44 healthy controls. We randomly divided samples into one training set, one internal validation set, and one external validation set. In the external validation set, the summary sensitivity was 0.88 (95% CI 0.84-0.91), the summary specificity was 1.00 (95% CI 0.85-1.00), the AUC was 0.96 (95% CI 0.94-0.98), the pAUC was 0.92 (95% CI 0.89-0.96), and the DOR was 207.62 (95% CI 24.62-924.64). CONCLUSION: Electronic nose screening for lung cancer is highly accurate. The support vector machine algorithm is more suitable for analyzing chemical sensor data from electronic noses.

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

BACKGROUND: Although 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. METHODS: Patients 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. RESULTS: In 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]). CONCLUSION: Our 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 REGISTRATION: This study is not a clinical trial and was therefore not registered.

An electronic nose can identify humans by the smell of their ear.

Terrestrial mammals identify conspecifics by body odor. Dogs can also identify humans by body odor, and in some instances, humans can identify other humans by body odor as well. Despite the potential for a powerful biometric tool, smell has not been systematically used for this purpose. A question arising in the application of smell to biometrics is which bodily odor source should we measure. Breath is an obvious candidate, but the associated humidity can challenge many sensing devices. The armpit is also a candidate source, but it is often doused in cosmetics. Here, we test the hypothesis that the ear may provide an effective source for odor-based biometrics. The inside of the ear has relatively constant humidity, cosmetics are not typically applied inside the ear, and critically, ears contain cerumen, a potent source of volatiles. We used an electronic nose to identify 12 individuals within and across days, using samples from the armpit, lower back, and ear. In an identification setting where chance was 8.33% (1 of 12), we found that we could identify a person by the smell of their ear within a day at up to ~87% accuracy (~10 of 12, binomial P < 10-5), and across days at up to ~22% accuracy (~3 of 12, binomial P < 0.012). We conclude that humans can indeed be identified from the smell of their ear, but the results did not imply a consistent advantage over other bodily odor sources.

Discrimination between raw and ginger juice processed Fructus Gardeniae based on UHPLC-Q-TOF-MS and Heracles NEO ultra-fast gas phase electronic nose.

INTRODUCTION: Fructus Gardeniae (ZZ), a traditional Chinese herb, has been used in treating patients with jaundice, inflammation, etc. When mixed with ginger juice and stir-baked, ginger juice-processed Fructus Gardeniae (JZZ) is produced, and the chemical compositions in ZZ would be changed by adding the ginger juice. OBJECTIVE: To illuminate the differential components between ZZ and JZZ. METHODS: HPLC, UHPLC-Q-TOF-MS, and Heracles NEO ultra-fast gas phase electronic nose were applied to identify the differential components between ZZ and JZZ. RESULTS: HPLC fingerprints of ZZ and JZZ were established, and 24 common peaks were found. The content determination results showed that the contents of shanzhiside, geniposidic acid, genipin-1-ß-D-gentiobioside and geniposide increased, while the contents of crocin I and crocin II decreased in JZZ. By UHPLC-Q-TOF-MS, twenty-six possible common components were inferred, among which 11 components were different. In further investigation, eight components were identified as the possible distinctive non-volatile compounds between ZZ and JZZ. By Heracles NEO ultra-fast gas phase electronic nose, four substances were inferred as the possible distinctive volatile compounds in JZZ. CONCLUSION: Shanzhiside, caffeic acid, genipin-1-ß-D-gentiobioside, geniposide, rutin, crocin I, crocin II, and 4-Sinapoyl-5-caffeoylquinic acid were identified as the possible differential non-volatile components between ZZ and JZZ. Aniline, 3-methyl-3-sulfanylbutanol-1-ol, E-3-octen-2-one, and decyl propaonate were inferred as the possible distinctive volatile compounds in JZZ. This experiment explored a simple approach with objective and stable results, which would provide new ideas for studying decoction pieces with similar morphological appearance, especially those with different odors.

Electronic Nose Drift Suppression Based on Smooth Conditional Domain Adversarial Networks.

Anti-drift is a new and serious challenge in the field related to gas sensors. Gas sensor drift causes the probability distribution of the measured data to be inconsistent with the probability distribution of the calibrated data, which leads to the failure of the original classification algorithm. In order to make the probability distributions of the drifted data and the regular data consistent, we introduce the Conditional Adversarial Domain Adaptation Network (CDAN)+ Sharpness Aware Minimization (SAM) optimizer-a state-of-the-art deep transfer learning method.The core approach involves the construction of feature extractors and domain discriminators designed to extract shared features from both drift and clean data. These extracted features are subsequently input into a classifier, thereby amplifying the overall model's generalization capabilities. The method boasts three key advantages: (1) Implementation of semi-supervised learning, thereby negating the necessity for labels on drift data. (2) Unlike conventional deep transfer learning methods such as the Domain-adversarial Neural Network (DANN) and Wasserstein Domain-adversarial Neural Network (WDANN), it accommodates inter-class correlations. (3) It exhibits enhanced ease of training and convergence compared to traditional deep transfer learning networks. Through rigorous experimentation on two publicly available datasets, we substantiate the efficiency and effectiveness of our proposed anti-drift methodology when juxtaposed with state-of-the-art techniques.

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

The early identification of rotten potatoes is one of the most important challenges in a storage facility because of the inconspicuous symptoms of rot, the high density of storage, and environmental factors (such as temperature, humidity, and ambient gases). An electronic nose system based on an ensemble convolutional neural network (ECNN, a powerful feature extraction method) was developed to detect potatoes with different degrees of rot. Three types of potatoes were detected: normal samples, slightly rotten samples, and totally rotten samples. A feature discretization method was proposed to optimize the impact of ambient gases on electronic nose signals by eliminating redundant information from the features. The ECNN based on original features presented good results for the prediction of rotten potatoes in both laboratory and storage environments, and the accuracy of the prediction results was 94.70% and 90.76%, respectively. Moreover, the application of the feature discretization method significantly improved the prediction results, and the accuracy of prediction results improved by 1.59% and 3.73%, respectively. Above all, the electronic nose system performed well in the identification of three types of potatoes by using the ECNN, and the proposed feature discretization method was helpful in reducing the interference of ambient gases.

E-Nose: Time-Frequency Attention Convolutional Neural Network for Gas Classification and Concentration Prediction.

In the electronic nose (E-nose) systems, gas type recognition and accurate concentration prediction are some of the most challenging issues. This study introduced an innovative pattern recognition method of time-frequency attention convolutional neural network (TFA-CNN). A time-frequency attention block was designed in the network, aiming to excavate and effectively integrate the temporal and frequency domain information in the E-nose signals to enhance the performance of gas classification and concentration prediction tasks. Additionally, a novel data augmentation strategy was developed, manipulating the feature channels and time dimensions to reduce the interference of sensor drift and redundant information, thereby enhancing the model's robustness and adaptability. Utilizing two types of metal-oxide-semiconductor gas sensors, this research conducted qualitative and quantitative analysis on five target gases. The evaluation results showed that the classification accuracy could reach 100%, and the coefficient of the determination (R2) score of the regression task was up to 0.99. The Pearson correlation coefficient (r) was 0.99, and the mean absolute error (MAE) was 1.54 ppm. The experimental test results were almost consistent with the system predictions, and the MAE was 1.39 ppm. This study provides a method of network learning that combines time-frequency domain information, exhibiting high performance in gas classification and concentration prediction within the E-nose system.

Optimization of Temperature Modulation for Gas Classification Based on Bayesian Optimization.

This study proposes an optimization method for temperature modulation in chemiresistor-type gas sensors based on Bayesian optimization (BO), and its applicability was investigated. As voltage for a sensor heater, our previously proposed waveform was employed, and the parameters determining the voltage range were optimized. Employing the Bouldin-Davies index (DBI) as an objective function (OBJ), BO was utilized to minimize the DBI calculated from a feature matrix built from the collected data followed by pre-processing. The sensor responses were measured using five test gases with five concentrations, amounting to 2500 data points per parameter set. After seven trials with four initial parameter sets (ten parameter sets were tested in total), the DBI was successfully reduced from 2.1 to 1.5. The classification accuracy for the test gases based on the support vector machine tends to increase with decreasing the DBI, indicating that the DBI acts as a good OBJ. Additionally, the accuracy itself increased from 85.4% to 93.2% through optimization. The deviation from the tendency that the accuracy increases with decreasing the DBI for some parameter sets was also discussed. Consequently, it was demonstrated that the proposed optimization method based on BO is promising for temperature modulation.

Application of MOX Sensors to Determine the Emission of Volatile Compounds in Corn Groats as a Function of Vertical Pressure in the Silo and Moisture Content of the Bed.

This study was focused on the analysis of the emission of volatile compounds as an indicator of changes in the quality degradation of corn groats with 14% and 17% moisture content (wet basis) using an electronic nose (Agrinose) at changing vertical pressure values. The corn groats were used in this study in an unconsolidated state of 0 kPa (the upper free layer of bulk material in the silo) and under a consolidation pressure of 40 kPa (approximately 3 m from the upper layer towards the bottom of the silo) and 80 kPa (approximately 6 m from the upper layer towards the bottom of the silo). The consolidation pressures corresponded to the vertical pressures acting on the layers of the bulk material bed in medium-slender and low silos. Chromatographic determinations of volatile organic compounds were performed as reference tests. The investigations confirmed the correlation of the electronic nose response with the quality degradation of the groats as a function of storage time. An important conclusion supported by the research results is that, based on the determined levels of intensity of volatile compound emission, the electronic nose is able to distinguish the individual layers of the bulk material bed undergoing different degrees of quality degradation.

Structure Optimization and Data Processing Method of Electronic Nose Bionic Chamber for Detecting Ammonia Emissions from Livestock Excrement Fermentation.

In areas where livestock are bred, there is a demand for accurate, real-time, and stable monitoring of ammonia concentration in the breeding environment. However, existing electronic nose systems have slow response times and limited detection accuracy. In this study, we introduce a novel solution: the bionic chamber construction of the electronic nose is optimized, and the sensor response data in the chamber are analyzed using an intelligent algorithm. We analyze the structure of the biomimetic chamber and the surface airflow of the sensor array to determine the sensing units of the system. The system employs an electronic nose to detect ammonia and ethanol gases in a circulating airflow within a closed box. The captured signals are processed, followed by the application of classification and regression models for data prediction. Our results suggest that the system, leveraging the biomimetic chamber, offers rapid gas detection response times. A high classification prediction accuracy, with a determination coefficient R2 value of 0.99 for single-output regression and over 0.98 for multi-output regression predictions, is achieved by incorporating a backpropagation (BP) neural network algorithm. These outcomes demonstrate the effectiveness of the electronic nose, based on an optimized bionic chamber combined with a BP neural network algorithm, in accurately detecting ammonia emitted during livestock excreta fermentation, satisfying the ammonia detection requirements of breeding farms.

New Insights into the Comprehensive System of Thermodynamic Sensors and Electronic Nose and Its Practical Applications in Dough Fermentation Monitoring.

This study focuses on an applicability of the device designed for monitoring dough fermentation. The device combines a complex system of thermodynamic sensors (TDSs) with an electronic nose (E-nose). The device's behavior was tested in experiments with dough samples. The configuration of the sensors in the thermodynamic system was explored and their response to various positions of the heat source was investigated. When the distance of the heat source and its intensity from two thermodynamic sensors changes, the output signal of the thermodynamic system changes as well. Thus, as the distance of the heat source decreases or the intensity increases, there is a higher change in the output signal of the system. The linear trend of this change reaches an R2 value of 0.936. Characteristics of the doughs prepared from traditional and non-traditional flours were successfully detected using the electronic nose. To validate findings, the results of the measurements were compared with signals from the rheofermentometer Rheo F4, and the correlation between the output signals was closely monitored. The data after statistical evaluation show that the measurements using thermodynamic sensors and electronic nose directly correlate the most with the measured values of the fermenting dough volume. Pearson's correlation coefficient for TDSs and rheofermentometer reaches up to 0.932. The E-nose signals also correlate well with dough volume development, up to 0.973. The data and their analysis provided by this study declare that the used system configuration and methods are fully usable for this type of food analysis and also could be usable in other types of food based on the controlled fermentation. The system configuration, based on the result, will be also used in future studies.

A Study on E-Nose System in Terms of the Learning Efficiency and Accuracy of Boosting Approaches.

With the development of the field of e-nose research, the potential for application is increasing in various fields, such as leak measurement, environmental monitoring, and virtual reality. In this study, we characterize electronic nose data as structured data and investigate and analyze the learning efficiency and accuracy of deep learning models that use unstructured data. For this purpose, we use the MOX sensor dataset collected in a wind tunnel, which is one of the most popular public datasets in electronic nose research. Additionally, a gas detection platform was constructed using commercial sensors and embedded boards, and experimental data were collected in a hood environment such as used in chemical experiments. We investigated the accuracy and learning efficiency of deep learning models such as deep learning networks, convolutional neural networks, and long short-term memory, as well as boosting models, which are robust models on structured data, using both public and specially collected datasets. The results showed that the boosting models had a faster and more robust performance than deep learning series models.

Noninvasive Diabetes Detection through Human Breath Using TinyML-Powered E-Nose.

Volatile organic compounds (VOCs) in exhaled human breath serve as pivotal biomarkers for disease identification and medical diagnostics. In the context of diabetes mellitus, the noninvasive detection of acetone, a primary biomarker using electronic noses (e-noses), has gained significant attention. However, employing e-noses requires pre-trained algorithms for precise diabetes detection, often requiring a computer with a programming environment to classify newly acquired data. This study focuses on the development of an embedded system integrating Tiny Machine Learning (TinyML) and an e-nose equipped with Metal Oxide Semiconductor (MOS) sensors for real-time diabetes detection. The study encompassed 44 individuals, comprising 22 healthy individuals and 22 diagnosed with various types of diabetes mellitus. Test results highlight the XGBoost Machine Learning algorithm's achievement of 95% detection accuracy. Additionally, the integration of deep learning algorithms, particularly deep neural networks (DNNs) and one-dimensional convolutional neural network (1D-CNN), yielded a detection efficacy of 94.44%. These outcomes underscore the potency of combining e-noses with TinyML in embedded systems, offering a noninvasive approach for diabetes mellitus detection.

The Potential of Fecal Volatile Organic Compound Analysis for the Early Diagnosis of Late-Onset Sepsis in Preterm Infants: A Narrative Review.

Early diagnosis and treatment of late-onset sepsis (LOS) is crucial for survival, but challenging. Intestinal microbiota and metabolome alterations precede the clinical onset of LOS, and the preterm gut is considered an important source of bacterial pathogens. Fecal volatile organic compounds (VOCs), formed by physiologic and pathophysiologic metabolic processes in the preterm gut, reflect a complex interplay between the human host, the environment, and microbiota. Disease-associated fecal VOCs can be detected with an array of devices with various potential for the development of a point-of-care test (POCT) for preclinical LOS detection. While characteristic VOCs for common LOS pathogens have been described, their VOC profiles often overlap with other pathogens due to similarities in metabolic pathways, hampering the construction of species-specific profiles. Clinical studies have, however, successfully discriminated LOS patients from healthy individuals using fecal VOC analysis with the highest predictive value for Gram-negative pathogens. This review discusses the current advancements in the development of a non-invasive fecal VOC-based POCT for early diagnosis of LOS, which may potentially provide opportunities for early intervention and targeted treatment and could improve clinical neonatal outcomes. Identification of confounding variables impacting VOC synthesis, selection of an optimal detection device, and development of standardized sampling protocols will allow for the development of a novel POCT in the near future.

Sub-PPB Detection with Gas-Phase Multiphoton Electron Extraction Spectroscopy under Ambient Conditions.

Multiphoton electron extraction spectroscopy (MEES) is an advanced analytical technique that has demonstrated exceptional sensitivity and specificity for detecting molecular traces on solid and liquid surfaces. Building upon the solid-state MEES foundations, this study introduces the first application of MEES in the gas phase (gas-phase MEES), specifically designed for quantitative detection of gas traces at sub-part per billion (sub-PPB) concentrations under ambient atmospheric conditions. Our experimental setup utilizes resonant multiphoton ionization processes using ns laser pulses under a high electrical field. The generated photoelectron charges are recorded as a function of the laser's wavelength. This research showcases the high sensitivity of gas-phase MEES, achieving high spectral resolution with resonant peak widths less than 0.02 nm FWHM. We present results from quantitative analysis of benzene and aniline, two industrially and environmentally significant compounds, demonstrating linear responses in the sub-PPM and sub-PPB ranges. The enhanced sensitivity and resolution of gas-phase MEES offer a powerful approach to trace gas analysis, with potential applications in environmental monitoring, industrial safety, security screening, and medical diagnostics. This study confirms the advantages of gas-phase MEES over many traditional optical spectroscopic methods and demonstrates its potential in direct gas-trace sensing in ambient atmosphere.

Classification in Early Fire Detection Using Multi-Sensor Nodes-A Transfer Learning Approach.

Effective early fire detection is crucial for preventing damage to people and buildings, especially in fire-prone historic structures. However, due to the infrequent occurrence of fire events throughout a building's lifespan, real-world data for training models are often sparse. In this study, we applied feature representation transfer and instance transfer in the context of early fire detection using multi-sensor nodes. The goal was to investigate whether training data from a small-scale setup (source domain) can be used to identify various incipient fire scenarios in their early stages within a full-scale test room (target domain). In a first step, we employed Linear Discriminant Analysis (LDA) to create a new feature space solely based on the source domain data and predicted four different fire types (smoldering wood, smoldering cotton, smoldering cable and candle fire) in the target domain with a classification rate up to 69% and a Cohen's Kappa of 0.58. Notably, lower classification performance was observed for sensor node positions close to the wall in the full-scale test room. In a second experiment, we applied the TrAdaBoost algorithm as a common instance transfer technique to adapt the model to the target domain, assuming that sparse information from the target domain is available. Boosting the data from 1% to 30% was utilized for individual sensor node positions in the target domain to adapt the model to the target domain. We found that additional boosting improved the classification performance (average classification rate of 73% and an average Cohen's Kappa of 0.63). However, it was noted that excessively boosting the data could lead to overfitting to a specific sensor node position in the target domain, resulting in a reduction in the overall classification performance.

Characterization of Flavor Profile of Sauced Pork from Different Regions of China Based on E-Nose, E-Tongue and Gas Chromatography-Ion Mobility Spectroscopy.

This study aimed to investigate the volatile flavor compounds and tastes of six kinds of sauced pork from the southwest and eastern coastal areas of China using gas chromatography-ion mobility spectroscopy (GC-IMS) combined with an electronic nose (E-nose) and electronic tongue (E-tongue). The results showed that the combined use of the E-nose and E-tongue could effectively identify different kinds of sauced pork. A total of 52 volatile flavor compounds were identified, with aldehydes being the main flavor compounds in sauced pork. The relative odor activity value (ROAV) showed that seven key volatile compounds, including 2-methylbutanal, 2-ethyl-3, 5-dimethylpyrazine, 3-octanone, ethyl 3-methylbutanoate, dimethyl disulfide, 2,3-butanedione, and heptane, contributed the most to the flavor of sauced pork (ROAV ≥1). Multivariate data analysis showed that 13 volatile compounds with the variable importance in projection (VIP) values > 1 could be used as flavor markers to distinguish six kinds of sauced pork. Pearson correlation analysis revealed a significant link between the E-nose sensor and alcohols, aldehydes, terpenes, esters, and hetero-cycle compounds. The results of the current study provide insights into the volatile flavor compounds and tastes of sauced pork. Additionally, intelligent sensory technologies can be a promising tool for discriminating different types of sauced pork.

Characterization of Key Odor-Active Compounds in Draft Beers for the Chinese Market Using Molecular Sensory Science Approaches.

Beer is a popular alcoholic beverage worldwide. However, limited research has been conducted on identifying key odor-active components in lager-type draft beers for the Chinese market. Therefore, this study aims to elucidate the odor characteristics of the four most popular draft beer brands through a sensory evaluation and an electronic nose. Subsequently, the four draft beers were analyzed through solid-phase microextraction and liquid-liquid extraction using a two-dimensional comprehensive gas chromatography-olfactometry-mass spectrometry analysis (GC×GC-O-MS). Fifty-five volatile odor compounds were detected through GC×GC-O-MS. Through an Aroma Extract Dilution Analysis, 22 key odor-active compounds with flavor dilution factors ≥ 16 were identified, with 11 compounds having odor activity values > one. An electronic nose analysis revealed significant disparities in the odor characteristics of the four samples, enabling their distinct identification. These findings help us to better understand the flavor characteristics of draft beer and the stylistic differences between different brands of products and provide a theoretical basis for objectively evaluating the quality differences between different brands of draft beer.

Prediction of total volatile basic nitrogen (TVB-N) in fish meal using a metal-oxide semiconductor electronic nose based on the VMD-SSA-LSTM algorithm.

BACKGROUND: The total volatile basic nitrogen (TVB-N) is the main indicator for evaluating the freshness of fish meal, and accurate detection and monitoring of TVB-N is of great significance for the health of animals and humans. Here, to realize fast and accurate identification of TVB-N, in this article, a self-developed electronic nose (e-nose) was used, and the mapping relationship between the gas sensor response characteristic information and TVB-N value was established to complete the freshness detection. RESULTS: The TVB-N variation curve was decomposed into seven subsequences with different frequency scales by means of variational mode decomposition (VMD). Each subsequence was modelled using different long short-term memory (LSTM) models, and finally, the final TVB-N prediction result was obtained by adding the prediction results based on different frequency components. To improve the performance of the LSTM, the sparrow search algorithm (SSA) was used to optimize the number of hidden units, learning rate and regularization coefficient of LSTM. The prediction results indicated that the high accuracy was obtained by the VMD-LSTM model optimized by SSA in predicting TVB-N. The coefficient of determination (R2), the root-mean-squared error (RMSE) and relative standard deviation (RSD) between the predicted value and the actual value of TVBN were 0.91, 0.115 and 6.39%, respectively. CONCLUSIONS: This method improves the performance of e-nose in detecting the freshness of fish meal and provides a reference for the quality detection of e-nose in other materials. © 2024 Society of Chemical Industry.