Search Results (360)

Accurate classification of volatile organic compounds (VOCs) is important for environmental monitoring and industrial safety via electronic nose (E-nose) systems. However, extracting discriminative features from dynamic one-dimensional sensor responses remains challenging, especially when the recognition model is expected to maintain low computational complexity. This study introduces MSD-GasNet, a lightweight multi-scale depthwise convolutional network combined with Gramian Angular Summation Field (GASF) encoding, for VOC classification using E-nose response signals. The gas-sensing response curves are first transformed into two-dimensional GASF images to preserve temporal correlation information and provide structured inputs for convolutional feature learning. MSD-GasNet further adopts parallel 3 × 3 and 5 × 5 depthwise convolutional branches with feature fusion to capture local response details and broader morphology-related patterns while reducing parameter redundancy. Evaluated on Dataset 1, which contains five representative VOC categories including 1-butanol, acetone, benzaldehyde, butyl acetate, and dimethylbenzene, MSD-GasNet achieves an accuracy of 96.80 ± 0.78%, with 796.6 K parameters and 2.54 ms inference time per sample. Compared with traditional machine learning classifiers, conventional CNN baselines, recent lightweight networks, and a single-scale ablation model, MSD-GasNet shows better classification performance under the current five-class setting. An additional independent validation on Dataset 2 achieves an accuracy of 95.12 ± 1.11% under a chronological train/test split, further supporting the generalization potential of the proposed method. This work provides a GASF-based lightweight multi-scale framework with potential for efficient VOC recognition in portable or resource-limited E-nose applications. Full article

Soil pesticide-residue screening is important for ecological protection, food safety, and public health. However, conventional chromatographic and spectroscopic methods often require complex sample pretreatment, expensive instruments, trained operators, and long analysis times, which limits their use for rapid and large-scale screening. In this study, an electronic-nose system was developed for volatile-fingerprint classification of pesticide-treated loess soil. Six commercial pesticide formulations from three chemical categories were evaluated: deltamethrin and cyfluthrin as pyrethroids, glyphosate and chlorpyrifos as organophosphorus pesticides, and zineb and mancozeb as organosulfur pesticides. These compounds were selected to represent commonly used pesticides with different chemical structures and volatile profiles. A mirror-symmetric gas-sensing chamber was designed for a 26-sensor metal oxide semiconductor (MOS) array to improve gas-flow uniformity and response repeatability. A total of 960 pesticide-treated electronic-nose response curves were collected from four soil depths. Eight feature extraction methods and four classifiers were compared. The Synthetic Minority Over-sampling Technique (SMOTE) and Geometric SMOTE (G-SMOTE) were then evaluated using training-fold-only oversampling to reduce data-leakage risk in imbalanced classification. The results showed that k-nearest neighbors (KNN) combined with direct or transform-based features provided strong classification performance under controlled laboratory conditions. For minority-class recognition, SMOTE showed more consistent improvement than G-SMOTE in the tested pesticide–depth–feature combinations, although the effect depended on feature representation and pesticide class. These findings indicate that the proposed chamber/sensor-array/SMOTE framework is feasible for rapid volatile-fingerprint classification of pesticide-treated soil, but larger independent field datasets and quantitative chemical validation are still required before general deployment. Full article

Meat flavor significantly influences consumer preference and market value, particularly for indigenous pig breeds renowned for distinctive sensory characteristics. While traditional research has focused on genetic factors and feeding regimens, emerging evidence suggests that gut microbiota plays a crucial role in meat quality attributes. However, the specific contribution of bacterial–fungal co-occurrence to meat flavor formation remains largely unexplored. This study aimed to characterize the associations between intestinal bacterial–fungal co-occurrence networks and the muscle flavor-related metabolite profiles of CX pigs, using an integrated multi-omics approach. Twenty male pigs (10 CX and 10 LAN, 12 months old) were subjected to comprehensive analyses, including meat quality evaluation, electronic nose analysis, 16S and 18S rRNA sequencing, and untargeted metabolomics. CX pigs exhibited significantly superior meat quality characteristics, including higher moisture content (p < 0.001), fat content (p = 0.008), and meat color scores (p < 0.001). Electronic nose analysis revealed significantly higher response values across all ten aroma sensors in CX pigs (p < 0.001), with the most pronounced differences observed in sensors detecting sulfur compounds and organic compounds. Untargeted metabolomics identified 40 differential metabolites, with 27 up-regulated in CX pigs, including key flavor compounds such as glycocholic acid, isorhamnetin, and pantothenic acid. Microbiome analysis demonstrated significantly higher bacterial alpha diversity in CX pigs (p < 0.05), with enrichment of beneficial bacteria, including Rikenellaceae_RC9_gut_group, Prevotellaceae_UCG_003, and Phascolarctobacterium, while fungal communities showed enrichment of Candida_Lodderomyces_clade. Correlation network analysis revealed that Rikenellaceae_RC9_gut_group demonstrated strong positive correlations with flavor compounds (r = 0.575 for isorhamnetin, r = 0.535 for pantothenic acid, p < 0.001) and all electronic nose responses (r = 0.434–0.691, p < 0.001). Bacterial–fungal co-occurrence networks showed synergistic relationships, with Rikenellaceae_RC9_gut_group positively correlated with Candida_Lodderomyces_clade (r = 0.711, p < 0.001) while exhibiting antagonistic relationships with Piromyces (r = −0.714, p < 0.001). These findings offer novel insights for developing microbiome-targeted strategies to enhance meat quality in pig production systems. Full article

The dried rhizome of Atractylodes lancea (RAL) is a widely used traditional Chinese medicine (TCM). Its quality evaluation and origin authentication have long relied on time-consuming chromatographic methods, which are poorly suited for rapid, on-site decisions in commercial supply chains, and existing studies generally focus on isolated morphological indicators without systematic digital characterization and practical on-site grading tools. Guided by the traditional empirical knowledge of “Bianzhuang Lunzhi”, which holds that external morphological traits can reflect the internal quality of TCM, this study presents the first systematic multi-dimensional digital characterization of RAL morphological traits using an integrated multi-sensor approach and quantitatively explores the underlying correlations between digital traits and key bioactive constituent contents. Nighty samples from three major producing regions were analyzed. Significant correlations were observed between odor indices, color parameters, density, oil cavity area ratio and bioactive component contents in the authentic Maoshan-sourced RAL (p < 0.01 or p < 0.05). Such associations were absent in the emerging regions (Dabie and Qin−Ba Mountains). A three-grade quality classification system based on density thresholds (Grade A: ≥0.73 g/cm³; B: 0.58–0.73 g/cm³; C: <0.58 g/cm³) was established specifically for Maoshan RAL. Additionally, an electronic nose-based classification model was constructed for geographical origin discrimination, which delivered reliable and robust classification performance in external validation with independent blind test samples. This work provides practical, low-cost tools for rapid quality grading and origin identification of RAL. The proposed trait-driven analytical strategy offers a generalizable framework for the quality control of other complex herbal medicines. Full article

Ensuring adequate indoor air quality (IAQ) in industrial environments is essential for protecting worker health, particularly in facilities characterized by chemical emissions and complex layouts, such as automotive painting lines. This study presents the implementation and field evaluation of a low-cost multisensory electronic system prototype designed for continuous, long-term monitoring of six key environmental parameters: temperature, relative humidity, atmospheric pressure, carbon dioxide equivalent (CO₂ eq), total volatile organic compounds (VOC), and an overall Indoor Air Quality (IAQ) index. The system consists of autonomous sensing stations with integrated multi-parameter MEMS sensors and a centralized data aggregation hub. The system was engineered to ensure metrological stability across power cycles, adaptive energy management, and robust long-range wireless communication, thereby addressing common limitations of conventional industrial monitoring solutions. The prototype was deployed in an operational automotive manufacturing plant, where seven sensing stations were installed along the painting line for a two-week continuous monitoring campaign, identifying process-dependent peaks in CO₂ and VOC concentrations and corresponding reductions in IAQ values. The system was able to identify CO₂ peaks as high as 2997.7 ppm (Sensor 3) in localized industrial zones, significantly exceeding standard indoor thresholds. At the same time the system demonstrated the ability to detect VOC fluctuations with a resolution capable of capturing peaks up to 144.1 ppb (Sensor 3) during high-activity shifts. All sensors provided continuous and reliable data over an extended monitoring period. The measured trends and value ranges were consistent with expected industrial conditions, indicating satisfactory system performance under real operating conditions. Overall, the results demonstrate that the developed multisensory prototype is a promising, portable, and economically sustainable solution for distributed continuous IAQ assessment in complex industrial environments, with strong potential for scalable large-scale implementation in occupational health protection and environmental sustainability frameworks. Full article

Conventional chemical analysis relies on costly laboratory instrumentation, while current e-nose systems are expensive for widespread deployment. New opportunities for low-cost, accessible e-nose applications are emerging for diverse fields due to the rapid evolution of inexpensive sensor technologies. We developed a framework that enables rapid integration of newly available low-cost gas sensors into functional e-nose systems, continuously evaluating them as they become commercially available. By characterizing their performance in multi-sensor arrays that mimic biological olfaction, the framework demonstrates effective odor discrimination in a low-cost e-nose system through coordinated behavior of a heterogeneous sensor array. Our testing approach includes sensor sensitivity, selectivity, and stability, which are to be combined with appropriate pattern recognition and AI algorithms in the future for effective chemical discrimination. This work provides a pathway for continuously updating e-nose technology with the latest available sensors in a cost-effective manner, thereby making advanced chemical sensing accessible for resource-limited settings and enabling large-scale deployment in real-world applications with future potential applications such as food quality monitoring, environmental sensing, smart agriculture, etc. Full article

Honeybee brood is a nutrient-rich food source containing natural umami-active compounds, such as glutamic acid, aspartic acid, and 5′-nucleotides, which are responsible for its characteristic umami taste. This study aimed to optimize drying conditions to enhance the umami composition and sensory properties of honeybee brood umami powder (HBb-UP). A factorial design was employed to evaluate the effects of drying temperature and time on umami-related amino acids, 5′-nucleotides, and equivalent umami concentration (EUC). Drying temperature and time significantly influenced the formation of umami compounds, with the optimized drying condition (65 °C for 3 h) promoting higher umami composition and improved sensory attributes of HBb-UP. Volatile flavor analysis using GC–MS and an electronic nose revealed a diverse range of aroma compounds contributing to the overall flavor profile. Descriptive sensory evaluation and electronic tongue analysis indicated that umami and saltiness were the dominant taste attributes, accompanied by mild seasoning and fishy notes associated with interactions between amino acids and nucleotides. Principal component analysis demonstrated positive correlations among umami-related amino acids, nucleotides, EUC, and sensory attributes, confirming their combined contribution to taste perception. These findings highlight the potential of optimized HBb-UP as a natural flavor enhancer and functional ingredient for use in sustainable food systems. Full article

Efficient monitoring of pork freshness is essential to minimize spoilage-related losses in the meat industry. To address the limitations of existing detection technologies, namely high cost, poor timeliness and high environmental sensitivity, this study developed a novel electronic nose system integrating a hybrid sensor array with dynamic gas path control. By combining metal oxide semiconductor (MOS) and electrochemical sensors (e.g., MQ137, MQ136), the system exhibits high sensitivity to the key volatile organic compounds (VOCs) released during pork spoilage, achieving a detection accuracy of over 90% in identifying spoilage stages. Combined with a dual-mode gas circuit design (solenoid valve switching time: 0.85 s), the reliability of the system was further demonstrated. This technology offers an economical and efficient real-time monitoring solution for slaughterhouses and cold chain logistics, providing a new low-cost scientific approach for pork freshness assessment. Full article

Metal oxide semiconductor (MOS) gas sensors are an important part of electronic nose technology because they are sensitive, cheap, and work well with microfabrication for system integration. But sensor drift makes them less useful for long-term, continuous gas monitoring. Changes in how sensors respond over time make pattern recognition models that were trained at first less accurate. This review looks at new ways to deal with sensor drift, with a focus on transfer learning and deep learning methods that have been developing continuously in the last five years. It emphasizes the shift from conventional recalibration and component correction to sophisticated methodologies, including deep domain adaptation, contrastive representation learning, and attention-based models. The review does not just list these methods; it also analyzes their pros and downsides, especially in situations where there is not much labeled data, drift is hard to anticipate, or the computational resources are limited, which is often the case with edge sensors. Full article

Real-time online monitoring of key parameters such as the ammonium nitrogen (NH₄⁺) concentration during biological fermentation is important for the optimization of a biological fermentation process. Traditional offline detection technologies like spectrophotometry need contact sampling, with drawbacks of monitoring lag, risk of contamination, etc. In this work, taking the gentamicin fermentation process as an example, we developed an intelligent electronic nose non-contact monitoring system on the basis of fermentation off-gas signals. We captured the typical signals of off-gas and established a quantitative relationship between the signals and the NH₄⁺ concentration in fermentation broth; the system then realized non-contact real-time monitoring. The whole system consists of a gas-switching module, a sensor array module, a signal-processing module, and an intelligent prediction module. The system adopts a five-phase gas switching strategy to suppress sensor drift in metal–oxide–semiconductor (MOS) sensors and a light neural network for prediction, which improve both prediction speed and accuracy. Experiments were conducted using a 5 L fermenter, and the prediction result was consistent with the offline measured value (coefficient of determination, R² = 0.9871, root mean square error, RMSE = 0.0317 g/L). This technique provides a new method for the non-contact measurement of key fermentation parameters, and it can be expanded to other fermentations. Full article

Precision in estimating the ripeness of fruits is critical in quality control and minimizing losses in supply chains of agricultural produce following harvesting. Conventional ripeness assessment techniques tend to be destructive, time-consuming and unsuited to monitoring in real-time. In order to avoid these drawbacks, this research suggests a cloud-integrated smart electronic nose (E-nose) system to predict fruit ripeness in a non-destructive and real-time manner. The system uses a low-priced, non-selective gas sensor array with an ESP8266-based Internet of Things (IoT) board to record volatile organic compound (VOC) signatures released at various maturation phases of fruits. The obtained sensor data will be sent to a cloud server to be preprocessed centrally and classified using machine learning, thus reducing the computational needs at the edge. There is a collection of 953 samples of the unripe, ripe, and rotten stages of banana under controlled conditions. Several supervised machine learning algorithms are tested, and methods of ensemble boosting proved to be more effective. The Light Gradient Boosting Machine (LightGBM) is the most accurate in terms of classification of 96.50% and weighted F1-score of 96.49%. The confusion matrix analysis shows that the majority of misclassifications are observed among the neighboring stages of ripeness, indicating the gradual biochemical changes. The system is practically applicable as visualization of the predicted ripeness levels occurs in real time via a mobile application. The suggested model provides a scalable, low-cost, and smart solution to precision agriculture, which can allow efficient, automated, and non-destructive measurement of fruit quality. Full article

Characteristic gas-based detection technology can facilitate the warning of lithium-ion battery thermal runaway with a high accuracy at an early stage. Microelectromechanical system (MEMS) metal–oxide–semiconductor (MOS) gas sensors have advantages of a low cost, a high accuracy, and low power consumption; therefore, they are ideal candidates for the lithium-ion battery thermal-runaway warning. MEMS MOS gas sensors are composed of a micro-hotplate and gas-sensitive materials. The micro-hotplate component strongly influences the device’s mechanical and thermal properties. Initially, we used COMSOL to optimize the micro-hotplate component. Then, we fabricated the device based on the optimal micro-hotplate. Next, gas-sensitive materials made of ZnO and ZnO-Au were deposited on the micro-hotplate by radio-frequency magnetic sputtering. The self-made and commercial MEMS MOS sensors were integrated to form an electronic nose. The as-made electronic nose can classify hydrogen, ethylene, acetylene, methane, carbon monoxide, and ethanol with a maximum accuracy of 99.4% using gas response data acquired over only 20 s. The reported work can provide a solution for an early and accurate lithium-ion battery thermal runaway warning. Full article

A portable electronic nose based on modern digital metal oxide (MOX) gas sensors and programmable temperature modulation was developed and validated. The system integrates four modern commercially available MOX sensors capable of generating temperature-dependent odor fingerprints and multidimensional sensor responses compared with conventional fixed-temperature operation. The performance of the device was assessed in terms of sensor stability, repeatability, and pattern-recognition capability under long-term operation. As a proof of concept, the electronic nose was applied to the discrimination of Extra Virgin Olive Oil and pomace oil. Repeatability analysis using the Root Mean Squared Error (RMSE) demonstrated stable responses across one month of measurements. Temperature-modulated signals were processed using Principal Component Analysis (PCA) and classified with k-Nearest Neighbors (KNNs) and Multilayer Perceptrons (MLPs), achieving 100% accuracy after selecting the most repeatable sensor. These results highlight the robustness and analytical potential of temperature-modulated digital MOX sensors and demonstrate the feasibility of a compact and highly reproducible electronic-nose platform suitable for complex odor-analysis tasks in real-world applications. Full article

Prostate cancer (PCa) is one of the leading causes of cancer-related morbidity and mortality in men worldwide, and early detection remains crucial for ensuring effective treatment and improving patient outcomes. In this context, the development of non-invasive, accurate, and cost-effective screening strategies is of paramount importance. One particularly promising and innovative approach is the analysis of volatile organic compounds (VOCs), a field known as volatolomics. VOCs, which are metabolic by products released by the body, reflect underlying biochemical processes and offer a valuable, non-invasive source of diagnostic information. Recent advances have highlighted the potential of VOC profiling in PCa detection. A variety of biological systems have demonstrated remarkable sensitivity and specificity in recognizing disease-associated VOC signatures. Notably, trained dogs, selected invertebrates, and artificial sensing platforms have all shown the ability to identify PCa-related olfactory patterns. Among technological approaches, electronic noses (eNoses), which combine chemical sensor arrays with pattern recognition algorithms such as neural networks, represent a rapidly evolving diagnostic tool. Together, these biologically inspired and technology-driven strategies are reshaping the landscape of cancer diagnostics. They offer a compelling foundation for the development of rapid, non-invasive, and clinically translatable methods for PCa detection. This narrative review summarizes recent advances in using VOCs for PCa diagnosis and evaluates the reproducibility and clinical robustness of these approaches, focusing on challenges such as standardizing sampling, storage, and analysis, small cohort sizes, and the need for external validation and regulatory integration. Full article

Tea quality evaluation is increasingly moving from subjective sensory assessment and destructive laboratory analysis toward rapid, non-destructive, and data-driven approaches. This review summarizes recent advances in multimodal sensing integrated with deep learning for tea quality evaluation, with emphasis on sensor complementarity, data-fusion strategies, representative applications, and deployment-related limitations. Major sensing modalities, including machine vision, near- and mid-infrared spectroscopy, Raman and fluorescence spectroscopy, hyperspectral imaging, and electronic nose/electronic tongue systems, are discussed in relation to their ability to characterize appearance, chemical composition, aroma, flavor, processing status, and safety-related attributes. Applications are examined for quality grading, chemical composition prediction, aroma and flavor characterization, fermentation monitoring, and safety-related extensions across representative tea products, including green tea, black tea, dark tea, matcha, and jasmine tea. Overall, multimodal approaches can outperform single-sensor systems only when the selected modalities provide complementary, rather than redundant, information layers. However, practical translation remains constrained by small and weakly standardized datasets, insufficient external validation, sensor instability, limited model transferability, high computational cost, and insufficient interpretability. Future research should prioritize standardized datasets, leakage-free validation protocols, interpretable multimodal modeling, truly independent external validation, interoperable multi-sensor platforms, and lightweight deployable models. Full article