Search

The gradual and unpredictable variation in chemo-sensory signal responses when exposed to the same analyte under identical conditions, commonly referred to as sensor drift, has long been recognized as one of the most serious challenges faced by chemical sensors. The traditional drift compensation method is both labor-intensive and expensive, as it requires frequent collection and labeling of gas samples for recalibration. Introducing a small number of meaningful drift calibration samples can be an attractive strategy to reduce the computational load and improve the performance of the updated classifier. However, under the influence of drift, new challenges arise due to the difference in the distribution of source and target domain data. This paper proposes a novel algorithm framework called semi-supervised contrastive learning drift compensation (SSCLDC). The framework automatically extracts high-level abstract features based on a multilayer perceptron to better represent the structure of the source data. In addition, to address the issue of data distribution differences caused by drift between the source and target domains. We add a small number of reference sample pairs into the training for semi-supervised learning. Combining a contrastive loss function that can represent the matching degree of paired samples effectively overcomes the problem of sensor drift. The Kennard-Stone sequential algorithm is used to select the representative reference sample from the set of candidate reference samples. Experiments conducted on a widely used long-term chemical gas sensor drift dataset demonstrate that the proposed method outperforms several classic drift compensation techniques, highlighting its effectiveness and practical applicability. [ABSTRACT FROM AUTHOR]

There has been a recent increase in the frequency of mass disaster events. Following these events, the rapid location of victims is paramount. Currently, the most reliable search method is scent detection dogs, which use their sense of smell to locate victims accurately and efficiently. Despite their efficacy, they have limited working times, can give false positive responses, and involve high costs. Therefore, alternative methods for detecting volatile compounds are needed, such as using electronic noses (e-noses). An e-nose named the 'NOS.E' was developed and has been used successfully to detect VOCs released from human remains in an open-air environment. However, the system's full capabilities are currently unknown, and therefore, this work aimed to evaluate the NOS.E to determine the efficacy of detection and expected sensor response. This was achieved using analytical standards representative of known human ante-mortem and decomposition VOCs. Standards were air diluted in Tedlar gas sampling bags and sampled using the NOS.E. This study concluded that the e-nose could detect and differentiate a range of VOCs prevalent in ante-mortem and decomposition VOC profiles, with an average LOD of 7.9 ppm, across a range of different chemical classes. The NOS.E was then utilized in a simulated mass disaster scenario using donated human cadavers, where the system showed a significant difference between the known human donor and control samples from day 3 post-mortem. Overall, the NOS.E was advantageous: the system had low detection limits while offering portability, shorter sampling times, and lower costs than dogs and benchtop analytical instruments. [ABSTRACT FROM AUTHOR]

Soil classification stands as a pivotal aspect in the domain of agricultural practices and environmental research, wielding substantial influence over decisions related to real-time soil management and precision agriculture. Nevertheless, traditional methods of assessing soil conditions, primarily grounded in labor-intensive chemical analyses, confront formidable challenges marked by substantial resource demands and spatial coverage limitations. This study introduced a machine olfaction methodology crafted to emulate the capabilities of the human olfactory system, providing a cost-effective alternative. In the initial phase, volatile gases produced during soil pyrolysis were propelled into a sensor array comprising 10 distinct gas sensors to monitor changes in gas concentration. Following the transmission of response data, nine eigenvalues were derived from the response curve of each sensor. Given the disparate sample counts for the two distinct classification criteria, this computational procedure yields two distinct eigenspaces, characterized by dimensions of 112 or 114 soil samples, each multiplied by 10 sensors and nine eigenvalues. The determination of the optimal feature space was guided by the "overall feature information" derived from mutual information. Ultimately, the inclusion of random forest (RF), multi-layer perceptron (MLP), and multi-layer perceptron combined with random forest (MLP-RF) models was employed to classify soils under four treatments (tillage and straw management) and three fertility grades. The assessment of model performance involved metrics such as overall accuracy (OA) and the Kappa coefficient. The findings revealed that the optimal classification model, MLP-RF, achieved impeccable performance with an OA of 100.00% in classifying soils under both criteria, which showed almost perfect agreement with the actual results. The approach proposed in this study provided near-real-time data on the condition of the soil and opened up new possibilities for advancing precision agriculture management. [ABSTRACT FROM AUTHOR]

Sesame oil (SO), one of the most popular and expensive edible oils, is prone to adulteration. In this study, the fatty acid profiles of pure sesame seed oil and samples adulterated with two less expensive edible oils (canola and sunflower) were analyzed using Gas Chromatography. A dedicated e-nose system was developed and tested on 15 mixtures of sesame-canola and sesame-sunflower samples. Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Multi-Layered Perceptron (MLP) methods were utilized to identify adulteration through the evaluation of Volatile Organic Compound. Result of chromatography showed that most samples of sesame oil containing impurities at levels less than 30% were recognized incorrectly in the standard range of SO fatty acids. This is while the developed e-nose system was able to detect adulteration at much lower levels. According to the results, PCA and LDA methods can describe the data set variance with precision of 95.6% and 97%, respectively. The MLP model had better results compared to PCA and LDA, with high determination coefficient (R2 = 0.981) and low RMSE (0.0178). Results indicate that the e-nose system provided an effective non-destructive method to detect SO adulteration at levels as low as 5%, which GC was unable to detect. [ABSTRACT FROM AUTHOR]

The application of Instrumental Odor Monitoring Systems (IOMS) for odor concentration estimation in wastewater treatment plants remains a challenge. We present the optimization of a heterogeneous gas sensor array mounted on a small drone to be used in dynamic conditions. The proposed method is based on the use of feature selection during the estimation of the best calibration model. The results show that the selection of an optimal sensor array and the proper time window decreases the multiplicative error a 25%.

Soil classification stands as a pivotal aspect in the domain of agricultural practices and environmental research, wielding substantial influence over decisions related to real-time soil management and precision agriculture. Nevertheless, traditional methods of assessing soil conditions, primarily grounded in labor-intensive chemical analyses, confront formidable challenges marked by substantial resource demands and spatial coverage limitations. This study introduced a machine olfaction methodology crafted to emulate the capabilities of the human olfactory system, providing a cost-effective alternative. In the initial phase, volatile gases produced during soil pyrolysis were propelled into a sensor array comprising 10 distinct gas sensors to monitor changes in gas concentration. Following the transmission of response data, nine eigenvalues were derived from the response curve of each sensor. Given the disparate sample counts for the two distinct classification criteria, this computational procedure yields two distinct eigenspaces, characterized by dimensions of 112 or 114 soil samples, each multiplied by 10 sensors and nine eigenvalues. The determination of the optimal feature space was guided by the “overall feature information” derived from mutual information. Ultimately, the inclusion of random forest (RF), multi-layer perceptron (MLP), and multi-layer perceptron combined with random forest (MLP-RF) models was employed to classify soils under four treatments (tillage and straw management) and three fertility grades. The assessment of model performance involved metrics such as overall accuracy (OA) and the Kappa coefficient. The findings revealed that the optimal classification model, MLP-RF, achieved impeccable performance with an OA of 100.00% in classifying soils under both criteria, which showed almost perfect agreement with the actual results. The approach proposed in this study provided near-real-time data on the condition of the soil and opened up new possibilities for advancing precision agriculture management.

The utilization of corn silage in animal diets is becoming a challenge, due to the crop's reduced yield as a result of climate change. Alternative silage types, such as mixtures of Italian ryegrass and winter cereals, may be a good complement to corn silage in diet formulation. Therefore, it is important to investigate how these alternative sources influence milk fatty acid and odor profile, as well as how these quality parameters could be efficiently evaluated. In this study, a corn silage-based control (CTR) and four experimental (EXP) diets—which contained winter cereals (WC), as well as WC with Italian ryegrass (IRG) silages in different proportions—were fed to Holstein-Friesian cows (n = 32) in a single-blinded efficacy study during a series of 4-week periods, with 2 weeks of adaption to each feed before the main trial. Milk from each trial was subjected to fatty acid (FA) analysis and odor profiling through the utilization of gas chromatography and an electronic nose, respectively. The results show that milk FAs in the EXP-3 and EXP-4 groups (which contained mixed silages using WC) changed the most when compared with other groups. Moreover, with a 7 kg/day inclusion rate of WC + IRG and of the WC silages in the diets of the EXP-2 and EXP-3 groups, respectively, the milk from these groups had their n6:n3 ratio reduced, thus indicating possible health benefits to consumers. The odor variation between the milk of the WC + IRG and WC groups was greater than the variation between the milk of the CTR and EXP groups. The main volatile compound responsible for the odor of the CTR milk was ethyl-butyrate, whereas 2-propanol and butan-2-one dominated the WC milk; the milk samples of the WC + IRG groups were influenced largely by ethanol. The study proved that with a 7 kg/day inclusion of mixed silages including winter cereals plus Italian ryegrass, the FA and odor profile of bovine milk could be modified. [ABSTRACT FROM AUTHOR]

Machine olfactory perception (MOP) is a new type of intelligent perception technology that senses and describes odors. The difference between MOP and machine olfaction is that MOP describes odors by using some semantic labels. One of the challenges in realizing MOP is an appropriate multilabel classifier from the high-dimensional sensor responses. Here, we propose a novel aroma-type (AT) oriented MOP method, which is an MOP method of multiple AT. Wherein, the method designed an intelligent perception of multiple ATs based on a convolutional neural network (IPMAT-CNN), in which an olfactory information-shared mechanism was introduced to enhance the feature extraction of the network. In addition, by analyzing the molecular correlation between multiple ATs, a matrix addition method was designed in IPMAT-CNN to strengthen the information on adjacent ATs. These designs effectively improved the accuracy of model detection. At last, IPMAT-CNN successfully sensed and recognized seven ATs of 38 monomer flavors. The effectiveness of IPMAT-CNN was evaluated by four baseline models [classifier chain based on random forest classifier (CC-RF), label powerset based on random forest classifier (LP-RF), multilabel decision tree (ML-DT), and multilabel ${k}$ -nearest neighbor (ML-kNN)]. The results showed that the IPMAT-CNN had the best performance with a 0.0636 hamming loss, a 93.65% accuracy, and a 0.8149 mean average precision (mAP) value for classifying the seven ATs. It reveals that the IPMAT-CNN had a decent prediction performance and can be used as an effective reference method for the ATs classification. [ABSTRACT FROM AUTHOR]

In this study, we aimed to carry out the efficient fortification of vanilla milkshakes with micro-encapsulated microalgae oil (brand: S17-P100) without distorting the product's odor. A 10-step oil-enrichment protocol was developed using an inclusion rate of 0.2 to 2 w/w%. Fatty acid (FA) profile analysis was performed using methyl esters with the GC-MS technique, and the recovery of docosahexaenoic acid (C22:6 n3, DHA) was robust (r = 0.97, p < 0.001). The enrichment process increased the DHA level to 412 mg/100 g. Based on this finding, a flash-GC-based electronic nose (e-nose) was used to describe the product's odor. Applying principal component (PC) analysis to the acquired sensor data revealed that for the first four PCs, only PC3 (6.5%) showed a difference between the control and the supplemented products. However, no systematic pattern of odor profiles corresponding to the percentages of supplementation was observed within the PC planes. Similarly, when discriminant factor analysis (DFA) was applied, though a classification of the control and supplemented products, we obtained a validation score of 98%, and the classification pattern of the odor profiles did not follow a systematic format. Again, when a more targeted approach such as the partial least square regression (PLSR) was used on the most dominant sensors, a weak relationship (R2 = 0.50) was observed, indicating that there was no linear combination of the qualitative sensors' signals that could accurately describe the supplemented concentration variation. It can therefore be inferred that no detectable off-odor was present as a side effect of the increase in the oil concentration. Some volatile compounds of importance in regard to the odor, such as ethylacetate, ethyl-isobutarate, pentanal and pentyl butanoate, were found in the supplemented product. Although the presence of yeasts and molds was excluded from the product, ethanol was detected in all samples, but with an intensity that was insufficient to cause an off-odor. [ABSTRACT FROM AUTHOR]

Abstract Fungal decomposition of wood severely affects the soundness of timber constructions. The diagnosis of wood decay requires direct observations or sampling by skilled experts. Wood decay often occurs in obscure spaces, including the enclosed inner spaces of walls or under the floor. In this study, we examined the ability of machine olfaction to detect odors of fungi grown on common construction softwoods to provide a novel diagnostic method for wood construction soundness. The combination of a simple device equipped with semiconductor gas sensors (gas sensor array) and multivariate analysis discriminated a fungi-related odor from control odor without instrumental analysis (e.g., gas chromatography). This method is often referred to as machine olfaction or electronic nose. We measured the odor of wood test pieces that were infected with Fomitopsis palustris or Trametes versicolor and sound test pieces using a gas sensor array. The sensor responses of the specimens showed different patterns between the inoculated and control samples. Each specimen class formed independent groups in a principal component score plot, almost regardless of wood species, fungal species, or cultivation period. This method provides a new decay diagnosis method that is cost-effective and easy to operate.

2,4,6-trichloroanisole (TCA) is mainly responsible for cork taint in wine, which causes significant economic losses; therefore, the wine and cork industries demand an immediate, economic, noninvasive and on-the-spot solution. In this work, we present a novel prototype of an electronic nose (e-nose) using an array of digital and analog metal-oxide gas sensors with a total of 31 signals, capable of detecting TCA, and classifying cork samples with low TCA concentrations (≤15.1 ng/L). The results show that the device responds to low concentrations of TCA in laboratory conditions. It also differentiates among the inner and outer layers of cork bark (81.5% success) and distinguishes among six different samples of granulated cork (83.3% success). Finally, the device can predict the concentration of a new sample within a ±10% error margin. [ABSTRACT FROM AUTHOR]

Development of electronic technologies for precise identification of fruit crop cultivars in agricultural production provides an effective means for assuring product quality and authentication. The capabilities of discriminating between grape (Vitis vinifera L.) cultivars is essential for assuring certification of varieties sold in world markets. Machine olfaction, based on electronic-nose (e-nose) technologies, is readily available for rapid identification of fruit and vegetative agricultural products. This technology relies on detection of and discrimination between volatile organic compound (VOC) emissions from plant parts. It may be used in all stages of agricultural production to facilitate crop maintenance, cultivation, and harvesting decisions prior to marketing. An experimental e-nose device was constructed and tested in combination with five chemometric methods, including PCA, LDA, QDA, SVM, and ANN, as rapid, non-destructive tools for identification and classification of grape cultivars. An e-nose instrument equipped with nine metal oxide semiconductor (MOS) sensors was utilized to identify and classify five grape cultivars based on leaf VOC emissions using supervised and non-supervised methods. Grape leaf samples were first identified as belonging to specific cultivar types using PCA analyses, which are non-supervised classification methods, with the first two principal components (PC-1 and PC-2) accounting for 89% of the total variance. Four supervised statistical methods were further tested, including DA, QDA, SVM, and ANN, and provided effective discrimination accuracies of 98%, 99%, 92%, and 99%, respectively. These findings confirmed the suitable applicability of an MOS e-nose sensor array with supervised methods for accurate identification of grape cultivars, which is useful for authentication of vine cultivar types for commercial markets. [ABSTRACT FROM AUTHOR]

Introduction One the most important discussions of the world community is the importance and the role of edible oils in the nutrition and physical health of individuals, especially in the prevention of cardiovascular disease. One of these oils, used in cooking, is cow ghee. Cow ghee should be free of vegetable oil, animal fat, mineral oils, flavored additives and any other external ingredients. It is hard to find a technique that can easily and reliably measure the quality of the oil. So far, no special machine or system has been designed or built to distinguish the pure cow ghee from the adulterated ones. Electronic nose is a new method that has recently been considered by researchers in agriculture especially in the field of food quality. Because of high ability of e-nose system, in this research, this system was used for the detection of pure cow gee from the adulterants ones. Materials and Methods An olfactory machine system based on eight MOS sensors was designed to detect pure cow ghee from the adulterated with various proportions of vegetable oil and animal fat. Designed system includes data acquisition system, sensors, sensors chamber, sample box, power supply, connections, electric valves, air pump and air filter. The sensor array was consisted of the 8 MOS sensors that each of them react to specific volatile compounds. These sensors are widely used in olfactory machines because of their high chemical stability, high durability, low response to moisture and affordable prices. These are the most commonly used sensors in electronic nose system. To prepare samples with different percentages of adulteration, animal body fat and refined vegetable oils were added to pure cow ghee. In order to carry out the experiments, the sample was placed in sample box and in the baseline correction step (200 seconds), clean air was passed through the sensors to transmit the response of sensor array to steady state. At the injection step (180 seconds), the sample headspace was transmitted and passed through sensors chamber. Output voltage of each sensor depends on the type of sensor and its sensitivity. At the cleaning step (120 seconds) the clean air was passed through sensors to get the sensor array responsive to a stable state. Also, at this step the pump removed the odor remaining inside the sample container and system was prepared for the next test. The signals obtained from the sensors were recorded and then pre-processed. Results and Disscussion PCA and QDA analysis were used for detection the differences between pure cow ghee and adulterated ones. The data obtained from the signals processing with fractional method were used as input of PCA. The PCA results showed that the total variance between pure cow ghee and mixture of cow ghee with animal's fat was 97%. Also score plot of cow’s ghee and its mixture with vegetable oil showed the total variance of 96% between different samples. Sensors are the main components of an electronic nose system therefore it is necessary to select the best sensors to detect differences between samples. The loading plot was obtained to show the role of sensors in e-nose system and demonstrates that the selected sensors have a high degree of complementarity. Based on confusion matrix obtained from QDA analysis, pure samples were detected from vegetable oil and animal fat samples with correct classification rate of 95.24 and 97.15, respectively. Conclusion An eight-sensory olfactory machine system (MOS) was designed to detect pure cow ghee from the presence of vegetable oil and animal fat oil. In PCA analysis, the variance between samples was 97% and 98%, respectively. According to the results the radar graph of PCA analysis, it can be concluded that the sensors No 2 (TGS822), 3(MQ136), 4(MQ9) and 8(TGS2620) have the highest and sensor 6 (MQ135) has the lowest ability in classification. The MQ135 sensor reacts to the detection of ammonia, benzene, and sulfide. In other words these gases did not play important role in separating of cow ghee from other mixed oils.

The application of Instrumental Odor Monitoring Systems (IOMS) for odor concentration estimation in wastewater treatment plants remains a challenge. We present the optimization of a heterogeneous gas sensor array mounted on a small drone to be used in dynamic conditions. The proposed method is based on the use of feature selection during the estimation of the best calibration model. The results show that the selection of an optimal sensor array and the proper time window decreases the multiplicative error a 25%. [ABSTRACT FROM AUTHOR]

The utilization of corn silage in animal diets is becoming a challenge, due to the crop’s reduced yield as a result of climate change. Alternative silage types, such as mixtures of Italian ryegrass and winter cereals, may be a good complement to corn silage in diet formulation. Therefore, it is important to investigate how these alternative sources influence milk fatty acid and odor profile, as well as how these quality parameters could be efficiently evaluated. In this study, a corn silage-based control (CTR) and four experimental (EXP) diets—which contained winter cereals (WC), as well as WC with Italian ryegrass (IRG) silages in different proportions—were fed to Holstein-Friesian cows (n = 32) in a single-blinded efficacy study during a series of 4-week periods, with 2 weeks of adaption to each feed before the main trial. Milk from each trial was subjected to fatty acid (FA) analysis and odor profiling through the utilization of gas chromatography and an electronic nose, respectively. The results show that milk FAs in the EXP-3 and EXP-4 groups (which contained mixed silages using WC) changed the most when compared with other groups. Moreover, with a 7 kg/day inclusion rate of WC + IRG and of the WC silages in the diets of the EXP-2 and EXP-3 groups, respectively, the milk from these groups had their n6:n3 ratio reduced, thus indicating possible health benefits to consumers. The odor variation between the milk of the WC + IRG and WC groups was greater than the variation between the milk of the CTR and EXP groups. The main volatile compound responsible for the odor of the CTR milk was ethyl-butyrate, whereas 2-propanol and butan-2-one dominated the WC milk; the milk samples of the WC + IRG groups were influenced largely by ethanol. The study proved that with a 7 kg/day inclusion of mixed silages including winter cereals plus Italian ryegrass, the FA and odor profile of bovine milk could be modified.

In this work, we propose two deep learning-based architectures tailored for gas identification and quantification, which automatically tune hyper-parameters of the network for optimal performance. The immense success of deep learning in the field of computer vision and natural language processing inspired us to design deep learning-based gas identification and quantification network. The first architecture is proposed for gas quantification, which is based on 1D-CNN. It makes use of raw time-series gas sensor array data and provides the concentration of each gas in a mixture of gases. The second architecture is presented for gas quantification, which is based on a deep belief network combined with drift-aware feature adaptation strategy. The proposed models identify and quantify the gases with improved accuracy despite the presence of sensor drift. Additionally, hyper-parameters of both the networks are automatically tuned for optimal performance. Although several pattern recognition methods related to machine learning, fuzzy logic and hybrid models have been used to identify gas and quantify the gases in the mixture, the performances of these techniques enormously depend on the feature engineering and selection of hyper-parameters. Experimental results show that the proposed methods are an effective technique for identifying gases and quantifying the mixture of gases for e-nose data. We also present that the proposed methods outperforms various other methods and can provide higher identification and quantification accuracy in the pres-ence of sensor drift. [ABSTRACT FROM AUTHOR]

Fungal decomposition of wood severely affects the soundness of timber constructions. The diagnosis of wood decay requires direct observations or sampling by skilled experts. Wood decay often occurs in obscure spaces, including the enclosed inner spaces of walls or under the floor. In this study, we examined the ability of machine olfaction to detect odors of fungi grown on common construction softwoods to provide a novel diagnostic method for wood construction soundness. The combination of a simple device equipped with semiconductor gas sensors (gas sensor array) and multivariate analysis discriminated a fungi-related odor from control odor without instrumental analysis (e.g., gas chromatography). This method is often referred to as machine olfaction or electronic nose. We measured the odor of wood test pieces that were infected with Fomitopsis palustris or Trametes versicolor and sound test pieces using a gas sensor array. The sensor responses of the specimens showed different patterns between the inoculated and control samples. Each specimen class formed independent groups in a principal component score plot, almost regardless of wood species, fungal species, or cultivation period. This method provides a new decay diagnosis method that is cost-effective and easy to operate. [ABSTRACT FROM AUTHOR]

Metal Oxide (MOX) gas sensors rely on chemical reactions that occur efficiently at high temperatures, resulting in too-demanding power requirements for certain applications. Operating the sensor under a Pulsed-Temperature Operation (PTO), by which the sensor heater is switched ON and OFF periodically, is a common practice to reduce the power consumption. However, the sensor performance is degraded as the OFF periods become larger. Other research works studied, generally, PTO schemes applying waveforms to the heater with time periods of seconds and duty cycles above 20%. Here, instead, we explore the behaviour of PTO sensors working under aggressive schemes, reaching power savings of 99% and beyond with respect to continuous heater stimulation. Using sensor sensitivity and the limit of detection, we evaluated four Ultra Low Power (ULP) sensors under different PTO schemes exposed to ammonia, ethylene, and acetaldehyde. Results show that it is possible to operate the sensors with total power consumption in the range of microwatts. Despite the aggressive power reduction, sensor sensitivity suffers only a moderate decline and the limit of detection may degrade up to a factor five. This is, however, gas-dependent and should be explored on a case-by-case basis since, for example, the same degradation has not been observed for ammonia. Finally, the run-in time, i.e., the time required to get a stable response immediately after switching on the sensor, increases when reducing the power consumption, from 10 minutes to values in the range of 10-20 hours for power consumptions smaller than 200 microwatts.

In this study, we aimed to carry out the efficient fortification of vanilla milkshakes with micro-encapsulated microalgae oil (brand: S17-P100) without distorting the product’s odor. A 10-step oil-enrichment protocol was developed using an inclusion rate of 0.2 to 2 w/w%. Fatty acid (FA) profile analysis was performed using methyl esters with the GC-MS technique, and the recovery of docosahexaenoic acid (C22:6 n3, DHA) was robust (r = 0.97, p < 0.001). The enrichment process increased the DHA level to 412 mg/100 g. Based on this finding, a flash-GC-based electronic nose (e-nose) was used to describe the product’s odor. Applying principal component (PC) analysis to the acquired sensor data revealed that for the first four PCs, only PC3 (6.5%) showed a difference between the control and the supplemented products. However, no systematic pattern of odor profiles corresponding to the percentages of supplementation was observed within the PC planes. Similarly, when discriminant factor analysis (DFA) was applied, though a classification of the control and supplemented products, we obtained a validation score of 98%, and the classification pattern of the odor profiles did not follow a systematic format. Again, when a more targeted approach such as the partial least square regression (PLSR) was used on the most dominant sensors, a weak relationship (R2 = 0.50) was observed, indicating that there was no linear combination of the qualitative sensors’ signals that could accurately describe the supplemented concentration variation. It can therefore be inferred that no detectable off-odor was present as a side effect of the increase in the oil concentration. Some volatile compounds of importance in regard to the odor, such as ethylacetate, ethyl-isobutarate, pentanal and pentyl butanoate, were found in the supplemented product. Although the presence of yeasts and molds was excluded from the product, ethanol was detected in all samples, but with an intensity that was insufficient to cause an off-odor.

The human olfactory system remains one of the most challenging biological systems to replicate. Humans use it without thinking, where it can measure offer protection from harm and bring enjoyment in equal measure. It is the system’s real-time ability to detect and analyze complex odors that makes it difficult to replicate. The field of artificial olfaction has recruited and stimulated interdisciplinary research and commercial development for several applications that include malodor measurement, medical diagnostics, food and beverage quality, environment and security. Over the last century, innovative engineers and scientists have been focused on solving a range of problems associated with measurement and control of odor. The IEEE Sensors Journal has published Special Issues on olfaction in 2002 and 2012. Here we continue that coverage. In this article, we summarize early work in the 20th Century that served as the foundation upon which we have been building our odor-monitoring instrumental and measurement systems. We then examine the current state of the art that has been achieved over the last two decades as we have transitioned into the 21st Century. Much has been accomplished, but great progress is needed in sensor technology, system design, product manufacture and performance standards. In the final section, we predict levels of performance and ubiquitous applications that will be realized during in the mid to late 21st Century. [ABSTRACT FROM AUTHOR]

Development of electronic technologies for precise identification of fruit crop cultivars in agricultural production provides an effective means for assuring product quality and authentication. The capabilities of discriminating between grape (Vitis vinifera L.) cultivars is essential for assuring certification of varieties sold in world markets. Machine olfaction, based on electronic-nose (e-nose) technologies, is readily available for rapid identification of fruit and vegetative agricultural products. This technology relies on detection of and discrimination between volatile organic compound (VOC) emissions from plant parts. It may be used in all stages of agricultural production to facilitate crop maintenance, cultivation, and harvesting decisions prior to marketing. An experimental e-nose device was constructed and tested in combination with five chemometric methods, including PCA, LDA, QDA, SVM, and ANN, as rapid, non-destructive tools for identification and classification of grape cultivars. An e-nose instrument equipped with nine metal oxide semiconductor (MOS) sensors was utilized to identify and classify five grape cultivars based on leaf VOC emissions using supervised and non-supervised methods. Grape leaf samples were first identified as belonging to specific cultivar types using PCA analyses, which are non-supervised classification methods, with the first two principal components (PC-1 and PC-2) accounting for 89% of the total variance. Four supervised statistical methods were further tested, including DA, QDA, SVM, and ANN, and provided effective discrimination accuracies of 98%, 99%, 92%, and 99%, respectively. These findings confirmed the suitable applicability of an MOS e-nose sensor array with supervised methods for accurate identification of grape cultivars, which is useful for authentication of vine cultivar types for commercial markets.

• A real-time gas distribution mapping method, called GW-GMRF, is proposed. • This method estimates simultaneously a gas and a wind map for unexplored areas. • Each gas map has an associated uncertainty. • Very few observations can lead to reliable and accurate estimates. • Several experiments and comparisons with other methods are presented. This work addresses 2D gas and wind distribution mapping with a mobile robot for real-time applications. Our proposal seeks to estimate how gases released in the environment are distributed from a set of sparse and uncertain gas-concentration and wind-flow measurements; such that by exploiting the high correlation between these two magnitudes we may extrapolate their value for unexplored areas. Furthermore, because the air currents are completely conditioned by the environment, we assume a priori knowledge of static elements such as walls and obstacles when estimating both distribution maps. In particular, this joint estimation problem is modeled as a multivariate Gaussian Markov random field (GMRF), combining gas and wind observations under a common maximum a posteriori estimation problem. It considers two lattices of cells (a scalar gas-concentration field and a wind vector field) which are correlated following the physical laws of gas dispersal and fluid dynamics. Finally, we report various experiments in which our proposal is compared to other stochastic gas and gas-wind modeling methods under simulation, to evaluate their performance against a computer fluid-dynamics generated ground-truth, as well as under real and uncontrolled conditions. [ABSTRACT FROM AUTHOR]

Bladder cancer (BCa) and prostate cancer (PCa) are some of the most common cancers in the world. In both BCa and PCa, the diagnosis is often confirmed with an invasive technique that carries a risk to the patient. Consequently, a non-invasive diagnostic approach would be medically desirable and beneficial to the patient. The use of volatile organic compounds (VOCs) for disease diagnosis, including cancer, is a promising research area that could support the diagnosis process. In this study, we investigated the urinary VOC profiles in BCa, PCa patients and non-cancerous controls by using gas chromatography-ion mobility spectrometry (GC-IMS) and gas chromatography time-of-flight mass spectrometry (GC-TOF-MS) to analyse patient samples. GC-IMS separated BCa from PCa (area under the curve: AUC: 0.97 (0.93–1.00)), BCa vs. non-cancerous (AUC: 0.95 (0.90–0.99)) and PCa vs. non-cancerous (AUC: 0.89 (0.83–0.94)) whereas GC-TOF-MS differentiated BCa from PCa (AUC: 0.84 (0.73–0.93)), BCa vs. non-cancerous (AUC: 0.81 (0.70–0.90)) and PCa vs. non-cancerous (AUC: 0.94 (0.90–0.97)). According to our study, a total of 34 biomarkers were found using GC-TOF-MS data, of which 13 VOCs were associated with BCa, seven were associated with PCa, and 14 VOCs were found in the comparison of BCa and PCa.

Because of the low accuracy of the current machine olfactory algorithms in detecting two mixed gases, this study proposes a hybrid gas detection algorithm based on an extreme random tree to greatly improve the classification accuracy and time efficiency. The method mainly uses the dynamic time warping algorithm (DTW) to perform data pre-processing and then extracts the gas characteristics from gas signals at different concentrations by applying a principal component analysis (PCA). Finally, the model is established by using a new extreme random tree algorithm to achieve the target gas classification. The sample data collected by the experiment was verified by comparison experiments with the proposed algorithm. The analysis results show that the proposed DTW algorithm improves the gas classification accuracy by 26.87%. Compared with the random forest algorithm, extreme gradient boosting (XGBoost) algorithm and gradient boosting decision tree (GBDT) algorithm, the accuracy rate increased by 4.53%, 5.11% and 8.10%, respectively, reaching 99.28%. In terms of the time efficiency of the algorithms, the actual runtime of the extreme random tree algorithm is 66.85%, 90.27%, and 81.61% lower than that of the random forest algorithm, XGBoost algorithm, and GBDT algorithm, respectively, reaching 103.2568 s. [ABSTRACT FROM AUTHOR]

In this paper an electronic nose system is proposed, together with odor-related gas information data processing and recognizing methods and an optimal gas sensor combination selecting procedure. The constructed electronic nose system consists of three parts, including a gas sensor chamber, data collecting circuits loaded with gas sensors and odor-related information data processing AI-driving programs. Utilizing the constructed electronic nose system, we accomplish the classifying missions of most 7 fruits and 8 vegetables to classifying accuracy of 96.7% using SVM classification algorithm and 10 sensor units. All probable gas sensor combinations are checked by the standard of their classifying performance to find the gas sensor combination match best when working together. The outcome turned to find that a specified gas sensor combination composed of 4 sensor units work best in the fruits and vegetables classification. This outcome suggests that these 4 sensor units are most suitable utilizing in related fruits and vegetables classification mission. [Display omitted] • We utilized machine learning algorithm to check the performance of different gas sensor combinations, made it to decrease the quantity of gas sensor units utilized when good classification effect reached. • Machine learning algorithms including K-Nearest Neighbor, Support Vector Machine, Bagging Decision Tree are utilized and modified to complete the fruits and vegetables classification mission. • Adequate types of foods are selected in our food classification experiment including 7 fruits and 8 vegetables. We also utilized most 10 gas sensor units. [ABSTRACT FROM AUTHOR]

Practical applications of machine olfaction have been eagerly awaited. A free-hand measurement, in which a measurement device is manually exposed to sample odors, is expected to be a key technology to realize practical machine olfaction. To implement odor identification systems based on the free-hand measurement, the comprehensive development of a measurement system including hardware, measurement protocols, and data analysis is necessary. In this study, we developed palm-size wireless odor measurement devices equipped with Membrane-type Surface stress Sensors (MSS) and investigated the effect of measurement protocols and feature selection on odor identification. By using the device, we measured vapors of liquids as odor samples through the free-hand measurement in different protocols. From the measurement data obtained with these protocols, datasets of transfer function ratios (TFRs) were created and analyzed by clustering and machine learning classification. It has been revealed that TFRs in the low-frequency range below 1 Hz notably contributed to vapor identification because the frequency components in that range reflect the dynamics of the detection mechanism of MSS. We also showed the optimal measurement protocol for accurate classification. This study has shown a guideline of the free-hand measurement and will contribute to the practical implementation of machine olfaction in society.

A methodology to calculate analytical figures of merit is not well established for detection systems that are based on sensor arrays with low sensor selectivity. In this work, we present a practical approach to estimate the Resolving Power of a sensory system, considering non-linear sensors and heteroscedastic sensor noise. We use the definition introduced by Shannon in the field of communication theory to quantify the number of symbols in a noisy environment, and its version adapted by Gardner and Barlett for chemical sensor systems. Our method combines dimensionality reduction and the use of algorithms to compute the convex hull of the empirical data to estimate the data volume in the sensor response space. We validate our methodology with synthetic data and with actual data captured with temperature-modulated MOX gas sensors. Unlike other methodologies, our method does not require the intrinsic dimensionality of the sensor response to be smaller than the dimensionality of the input space. Moreover, our method circumvents the problem to obtain the sensitivity matrix, which usually is not known. Hence, our method is able to successfully compute the Resolving Power of actual chemical sensor arrays. We provide a relevant figure of merit, and a methodology to calculate it, that was missing in the literature to benchmark broad-response gas sensor arrays.

A chemical detection platform composed of 8 chemo-resistive gas sensors was exposed to turbulent gas mixtures generated naturally in a wind tunnel. The acquired time series of the sensors are provided. The experimental setup was designed to test gas sensors in realistic environments. Traditionally, chemical detection systems based on chemo-resistive sensors include a gas chamber to control the sample air flow and minimize turbulence. Instead, we utilized a wind tunnel with two independent gas sources that generate two gas plumes. The plumes get naturally mixed along a turbulent flow and reproduce the gas concentration fluctuations observed in natural environments. Hence, the gas sensors can capture the spatio-temporal information contained in the gas plumes. The sensor array was exposed to binary mixtures of ethylene with either methane or carbon monoxide. Volatiles were released at four different rates to induce different concentration levels in the vicinity of the sensor array. Each configuration was repeated 6 times, for a total of 180 measurements. The data is related to “Chemical Discrimination in Turbulent Gas Mixtures with MOX Sensors Validated by Gas Chromatography-Mass Spectrometry”, by Fonollosa et al. [1]. The dataset can be accessed publicly at the UCI repository upon citation of [1]: http://archive.ics.uci.edu/ml/datasets/Gas+senso+rarray+exposed+to+turbulent+gas+mixtures.

The dataset includes the acquired time series of a chemical detection platform exposed to different gas conditions in a turbulent wind tunnel. The chemo-sensory elements were sampling directly the environment. In contrast to traditional approaches that include measurement chambers, open sampling systems are sensitive to dispersion mechanisms of gaseous chemical analytes, namely diffusion, turbulence, and advection, making the identification and monitoring of chemical substances more challenging. The sensing platform included 72 metal-oxide gas sensors that were positioned at 6 different locations of the wind tunnel. At each location, 10 distinct chemical gases were released in the wind tunnel, the sensors were evaluated at 5 different operating temperatures, and 3 different wind speeds were generated in the wind tunnel to induce different levels of turbulence. Moreover, each configuration was repeated 20 times, yielding a dataset of 18,000 measurements. The dataset was collected over a period of 16 months. The data is related to “On the performance of gas sensor arrays in open sampling systems using Inhibitory Support Vector Machines”, by Vergara et al.[1]. The dataset can be accessed publicly at the UCI repository upon citation of [1]: http://archive.ics.uci.edu/ml/datasets/Gas+sensor+arrays+in+open+sampling+settings

To address drift in chemical sensing, an extensive dataset was collected over a period of three years. An array of 16 metal-oxide gas sensors was exposed to six different volatile organic compounds at different concentration levels under tightly-controlled operating conditions. Moreover, the generated dataset is suitable to tackle a variety of challenges in chemical sensing such as sensor drift, sensor failure or system calibration. The data is related to “Chemical gas sensor drift compensation using classifier ensembles”, by Vergara et al. [1], and “On the calibration of sensor arrays for pattern recognition using the minimal number of experiments”, by Rodriguez-Lujan et al. [2] The dataset can be accessed publicly at the UCI repository upon citation of: http://archive.ics.uci.edu/ml/datasets/Gas+Sensor+Array+Drift+Dataset+at+Different+Concentrations

Aroma is one of the most important sensory properties of fruits and is particularly sensitive to the changes in fruit compounds. Gases involved in aroma of fruits are produced from the metabolic activities during ripening, harvest, post-harvest and storage stages. Therefore, the emitted aroma of fruits changes during the shelf-life period. The electronic nose (machine olfaction) would simulate the human sense of smell to identify and realize the complex aromas by using an array of chemical sensors. In this research, a low cost electronic nose based on six metal oxide semiconductor (MOS) sensors were designed, developed and implemented and its ability for monitoring changes in aroma fingerprint during ripening of banana was studied. The main components are used in the e-nose system include sampling system, an array of gas sensors, data acquisition system and an appropriate pattern recognition algorithm. Linear Discriminant Analysis (LDA) technique was used for classification of the extracted features of e-nose signals. Based on the results, the classification accuracy of 97/3% was obtained. Results showed the high ability of e-nose for distinguishing between the stages of ripening. It is concluded that the system can be considered as a nondestructive tool for quality control during banana shelf-life.

This study addresses the development of a miniaturized (60 × 60 mm) Wireless Sensing Module (WSM) for environmental application and air quality detection. The proposed prototype has six sensors: one for humidity, one for ambient temperature (SHT21 from Sensirion), and four for gas detection (MiCS-4514, MiCS-5526 and MiCS-5914 from SGX Sensortech). The core of the system is based on a high performance 8-bit microcontroller, model PIC18F46K80, from Microchip. The obtained data values were transmitted to the Smartphone through a Bluetooth communication module and a home-developed Android app. The discrimination capability of the module is tested with 10 volatile organic compounds (acetone, acetic acid, benzene, ethanol, ethyl acetate, ethylbenzene, formaldehyde, toluene, xylene, and dimethylacetamide) and the effect of humidity and drift of the sensors is also studied. Results show that 88.33% and 92.22% success rates in classification stage are obtained using Multilayer Perceptron with BackPropagation Learning algorithm and Radial-Basis based Neural Networks, respectively. [ABSTRACT FROM AUTHOR]

Inherent sensor variability limits mass-production applications for metal oxide (MOX) gas sensor arrays because calibration for replicas of a sensor array needs to be performed individually. Recently, calibration transfer strategies have been proposed to alleviate calibration costs of new replicas, but they still require the acquisition of transfer samples. In this work, we present calibration models that can be extended to uncalibrated replicas of sensor arrays without acquiring new samples, i.e., general or global calibration models. The developed methodology consists in including multiple replicas of a sensor array in the calibration process such that sensor variability is rejected by the general model. Our approach was tested using replicas of a MOX sensor array in the classification task of six gases and synthetic air, presented at different background humidity and concentration levels. Results showed that direct transfer of individual calibration models provides poor classification accuracy. However, we also found that general calibration models kept predictive performance when were applied directly to new copies of the sensor array. Moreover, we explored, through feature selection, whether particular combinations of sensors and operating temperatures can provide predictive performances equivalent to the calibration model with the complete array, favoring thereby the existence of more robust calibration models. [ABSTRACT FROM AUTHOR]

Copyright of Cotton Textile Technology is the property of Cotton Textile Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Capacitive polymer sensors present a promising approach for machine olfaction arrays capable of detecting and classifying various analytes. In this study, a comprehensive analysis of factors influencing capacitive vapor sensors is performed. An in-depth analysis of performance of sensing polymers with a wide range of solubility interactions and dielectric constants is performed providing a foundation for sensor design principles. Unique frequency-dependent signal-to-noise behavior was observed for each polymer-analyte pair due to variations in polarization mechanisms, which was in turn used to tune the array for a better sensitivity. Film thickness and background humidity on array sensitivity was also explored. Design principles based on this study are used to optimize sensor arrays for the classification and quantification of analytes exhibiting distinct solubility interactions (alcohol, ketone, ester, and two hydrocarbons). Electrochemical impedance spectroscopy analysis provides valuable insight into the different physical processes and polarization mechanisms for each sensing polymer. The design principles explored have broad implications for other dielectric-based sensing systems, including integrated circuit-based arrays such as field-effect transistors. [Display omitted] • Dielectric values and solubility interactions inform sensing polymer choice. • Nyquist and Bode plots guide optimal frequency for max signal-to-noise. • Sensing layer thickness optimized by balancing sensitivity, response time. • Impact of background humidity on sensor sensitivity investigated. • Finite element simulations predict capacitive response and optimal thickness. [ABSTRACT FROM AUTHOR]

Many residential environments have been equipped with sensing technologies both to provide assistance to older people who have opted for aging-in-place and to provide information to caregivers and family. However, such technologies are often accompanied by physical discomfort, privacy concerns, and complexity of use. We explored the feasibility of monitoring home activity using chemical sensors that pose fewer privacy concerns than, for example, video-cameras and which do not suffer from blind spots. We built a monitoring device that integrates a sensor array and IoT capabilities to gather the necessary data about a resident in his/her living space. Over a period of 3 months, we uninterruptedly measured the living space of a typical elder person living on his/her own. To record the level of activity during the same period and obtain a ground truth for the activity, a set of motion sensors were also deployed in the house. Home activity was extracted from a PCA space moving-window which translated sensor data into the event space; this also compensated for environmental and sensor drift. Our results show that it is possible to monitor the person's home activity and detect sudden deviations from it using a low-cost, non-invasive, system based on gas sensors that gather data on the air composition in the living space. We made the dataset publicly available at a data repository https://doi.org/10.24432/C5762W. • Development of a system based on gas sensors to monitor home activity for the elderly • Deployment of the system in a home while an elder performed his activities • Building a pattern of activity and detecting deviations from the regular pattern • Validation of the unobtrusive and non-invasive system to monitor home activities [ABSTRACT FROM AUTHOR]

Because of the low accuracy of the current machine olfactory algorithms in detecting two mixed gases, this study proposes a hybrid gas detection algorithm based on an extreme random tree to greatly improve the classification accuracy and time efficiency. The method mainly uses the dynamic time warping algorithm (DTW) to perform data pre-processing and then extracts the gas characteristics from gas signals at different concentrations by applying a principal component analysis (PCA). Finally, the model is established by using a new extreme random tree algorithm to achieve the target gas classification. The sample data collected by the experiment was verified by comparison experiments with the proposed algorithm. The analysis results show that the proposed DTW algorithm improves the gas classification accuracy by 26.87%. Compared with the random forest algorithm, extreme gradient boosting (XGBoost) algorithm and gradient boosting decision tree (GBDT) algorithm, the accuracy rate increased by 4.53%, 5.11% and 8.10%, respectively, reaching 99.28%. In terms of the time efficiency of the algorithms, the actual runtime of the extreme random tree algorithm is 66.85%, 90.27%, and 81.61% lower than that of the random forest algorithm, XGBoost algorithm, and GBDT algorithm, respectively, reaching 103.2568 s.

Domain adaptation algorithms are useful when the distributions of the training and the test data are different. In this paper, we focus on the problem of instrumental variation and time-varying drift in the field of sensors and measurement, which can be viewed as discrete and continuous distributional change in the feature space. We propose maximum independence domain adaptation (MIDA) and semi-supervised MIDA to address this problem. Domain features are first defined to describe the background information of a sample, such as the device label and acquisition time. Then, MIDA learns a subspace which has maximum independence with the domain features, so as to reduce the interdomain discrepancy in distributions. A feature augmentation strategy is also designed to project samples according to their backgrounds so as to improve the adaptation. The proposed algorithms are flexible and fast. Their effectiveness is verified by experiments on synthetic datasets and four real-world ones on sensors, measurement, and computer vision. They can greatly enhance the practicability of sensor systems, as well as extend the application scope of existing domain adaptation algorithms by uniformly handling different kinds of distributional change. [ABSTRACT FROM PUBLISHER]

When instruments and sensor systems are used to measure signals, the posterior distribution of test samples often drifts from that of the training ones, which invalidates the initially trained classification or regression models. This may be caused by instrumental variation, sensor aging, and environmental change. We introduce transfer-sample-based multitask learning (TMTL) to address this problem, with a special focus on applications in machine olfaction. Data collected with each device or in each time period define a domain. Transfer samples are the same group of samples measured in every domain. They are used by our method to share knowledge across domains. Two paradigms, parallel and serial transfer, are designed to deal with different types of drift. A dynamic model strategy is proposed to predict samples with known acquisition time. Experiments on three real-world data sets confirm the efficacy of the proposed methods. They achieve good accuracy compared with traditional feature-level drift correction algorithms and typical labeled-sample-based MTL methods, with few transfer samples needed. TMTL is a practical algorithm framework which can greatly enhance the robustness of sensor systems with complex drift. [ABSTRACT FROM PUBLISHER]

We present the estimation of a likelihood map for the location of the source of a chemical plume dispersed under atmospheric turbulence under uniform wind conditions. The main contribution of this work is to extend previous proposals based on Bayesian inference with binary detections to the use of concentration information while at the same time being robust against the presence of background chemical noise. For that, the algorithm builds a background model with robust statistics measurements to assess the posterior probability that a given chemical concentration reading comes from the background or from a source emitting at a distance with a specific release rate. In addition, our algorithm allows multiple mobile gas sensors to be used. Ten realistic simulations and ten real data experiments are used for evaluation purposes. For the simulations, we have supposed that sensors are mounted on cars which do not have among its main tasks navigating toward the source. To collect the real dataset, a special arena with induced wind is built, and an autonomous vehicle equipped with several sensors, including a photo ionization detector (PID) for sensing chemical concentration, is used. Simulation results show that our algorithm, provides a better estimation of the source location even for a low background level that benefits the performance of binary version. The improvement is clear for the synthetic data while for real data the estimation is only slightly better, probably because our exploration arena is not able to provide uniform wind conditions. Finally, an estimation of the computational cost of the algorithmic proposal is presented. [ABSTRACT FROM AUTHOR]

We propose a method for building a simple electronic nose based on commercially available sensors used to sniff in the market and identify spoiled/contaminated meat stocked for sale in butcher shops. Using a metal oxide semiconductor-based electronic nose, we measured the smell signature from two of the most common meat foods (beef and fish) stored at room temperature. Food samples were divided into two groups: fresh beef with decayed fish and fresh fish with decayed beef. The prime objective was to identify the decayed item using the developed electronic nose. Additionally, we tested the electronic nose using three pattern classification algorithms (artificial neural network, support vector machine and k-nearest neighbor), and compared them based on accuracy, sensitivity, and specificity. The results demonstrate that the k-nearest neighbor algorithm has the highest accuracy.