Electronic Nose

Humic Acid (HA) and Fulvic Acid (FA) contribute prominently to soil fertility. They are aromatic in nature and hence can be determined by sensory array. This is apparently the first report on the employment of Electronic nose (E-nose) to detect HA and FA extracted from soil. The aim was to evaluate the E-nose sensor response to HA and FA chemically extracted from different agricultural soils. Humic acid and Fulvic acid were extracted from collected agricultural soils and the aroma was measured by E-nose from each of the seven soils. Their presence was confirmed by fluorescence spectroscopy. The Norm Aroma Index (NAI) was measured for: soil, soil after heat treatment, heat treated soil amended with extracted HA, heat treated soil amended with extracted FA, extracted HA and extracted FA. The NAI values were descending in the order: heat treated soil amended with extracted HA/FA, extracted HA/FA, soil (untreated) and heat treated soil. This indicates that HA and FA are detected by E-no...

In process like coal mining, foundry, sewage systems or the like, just to mention a few. There is a production of complex mixtures of toxic and non-toxic gases which may affect human health. Among these gases we can consider Hydrogen sulfide, ammonia, methane, carbon dioxide, sulfur dioxide and nitrogen oxides. These gases can be detected by the human olfactory sense in concentrations as low as parts per billion and an exposition to low levels of these chemicals are potential health risks.

This paper presents an IoT based load forecasting and management system for distribution grids using Raspberry Pi. The proposed system integrates with real time data acquisition, statistical forecasting, and intelligent load management to enhance grid reliability. IoT enabled sensors are employed to capture real time electrical parameters, which are processed by Raspberry Pi and transmitted to the cloud for monitoring and control. The forecasting methodology incorporates statistical and time-series models, including Linear Regression, Multiple Regression, Polynomial Regression, ARIMA means Auto regressive Integrated Moving Average, SARIMA means Seasonal ARIMA, and Holt Winters, implemented in MATLAB Simulink. Two categories of features, based on historical demand patterns and calendar effects, are used to train the forecasting models. Furthermore, the influence of model selection on forecasting accuracy and scalability is analysed. Finally, an intelligent load management strategy is proposed to reduce peak demand stress, maximize operational efficiency, and provide a cost effective solution for distribution networks. The developed system shows improved accuracy, adaptability, and scalability, making it suitable for real time smart grid applications.

Electronic nose systems are used to deliver a pattern response to a listed odor, and pattern recognition software is used to perform odor recognition and discrimination by using a series of sensors. The method of electronic noses generally includes time taking measurements in a non-standard test and error process. The sensory panel problem can be solved by electronic nose. For this purpose, a sensor model is used to design sensor array. The generated signal of these sensor array is used further to classify a mixture of two gases using principle component analysis (PCA)-based classification analysis. During classification, the efficiency of PCA classification has been checked over the different signal preprocessing technique. Continuous real monitoring of odor is done at specific sites in the field over hours, days, weeks, or even months. An electronic machine can also avoid many other troubles linked with the employ of human panels. Each and every variability, adaptation (becoming m...

An artificial nose system for the recognition and classification of gas-phase analytes and its application in identifying common industrial gases is reported. The sensing mechanism of the device comprises the measurement of infrared absorption of volatile analytes inside the hollow cores of optofluidic Bragg fibers. An array of six fibers is used, where each fiber targets a different region of the mid-infrared in the range of 2-14 μm with transmission bandwidths of about 1-3 μm. The quenching in the transmission of each fiber due to the presence of analyte molecules in the hollow core is measured separately and the cross response of the array allows the identification of virtually any volatile organic compound (VOC). The device was used for the identification of seven industrial VOC vapors with high selectivity using a standard blackbody source and an infrared detector. The array response is registered as a unique six digit binary code for each analyte by assigning a threshold value to the fiber transmissions. The developed prototype is a comprehensive and versatile artificial nose that is applicable to a wide range of analytes.

An electronic nose (EN) device was used to detect microbial and viral contaminations in a variety of animal cell culture systems. The emission of volatile components from the cultures accumulated in the bioreactor headspace, was sampled and subsequently analysed by the EN device. The EN, which was equipped with an array of 17 chemical gas sensors of varying selectivity towards the sampled volatile molecules, generated response patterns of up to 85 computed signals. Each 15 or 20 min a new gas sample was taken generating a new response pattern. A software evaluation tool visualised the data mainly by using principal component analysis. The EN was first used to detect microbial contaminations in a Chinese hamster ovary (CHO) cell line producing a recombinant human macrophage colony stimulating factor (rhM-CSF). The CHO cell culture was contaminated by Escherichia coli, Pseudomonas aeruginosa, Staphylococcus aureus and Candida utilis which all were detected. The response patterns from the CHO cell culture were compared with monoculture references of the microorganisms. Second, contaminations were studied in an Sf-9 insect cell culture producing another recombinant protein (VP2 protein). Contaminants were detected from E. coli, a filamentous fungus and a baculovirus. Third, contamination of a human cell line, HEK-293, infected with E. coli exhibited comparable results. Fourth, bacterial contaminations could also be detected in cultures of a MLV vector producer cell line. Based on the overall experiences in this study it is concluded that the EN method has in a number of cases the potential to be developed into a useful on-line contamination alarm in order to support safety and economical operation for industrial cultivation.

Coffee is an agricultural product highly favored by the majority of the Indonesian population. Coffee comes in various types, each with a distinct aroma. Currently, differentiating coffee types relies on conventional methods, using the human nose, which is shubjective and dependent on individual conditions. This approach is less effective. To address this, researcher have developed a machine learning based system using Arduino Mega 2560 as the microcontroller, gas sensor MQ4, MQ7, MQ135, as the aroma detection tools, and the Linear Discriminant Analysis (LDA) algorithm as the classification method. The results of this system can classify 5 types of coffee with an accuracy rate of 90%.

The aim of this study, carried out within the NOVOROD project (PSR Campania 2007-2013 Misura 124 HC), was to evaluate the aromatic profile of milk and dairy products of dairy cows supplemented with destoned olive cake (DOC). Two techniques for the headspace aroma profile analysis: the thermal desorption by gas chromatography with a mass selective (GC/MS) detector and the electronic nose were compared. The trial was performed into a dairy cow farm. Ten dairy cows were allotted into two homogenous groups: control and experimental. Animals received the same diet, while in the experimental group the concentrate supplementation (15% dry matter) was replaced with DOC. After two weeks of adaptation, animals were fed with the experimental diet for other 15 days. During the experimental period, the milk was collected and cumulatively processed in Caciotta cheese (a soft cheese, 25 days ripened) and in Semicotto cheese (hard cheese, 3 months ripened) for 13 times for each group. Milk and chee...

In this study, the microbial characteristics (such as Total Viable Bacterial Count (TVBC), Coliform bacteria, E.coli, Staphylococcus aureus, Clostridium perfringens and Salmonella) of the processed meat at Khartoum state were investigated. The results revealed that the significant differences in TVBC (P≤0.05) were detected among the meat samples. Minced beef, beef sausage, beef burger, beef balls, chicken burger and beef cubes samples had TVBC of 0.58, 2.40, 3.26, 1, 3.21 and 2.40 log10cfu/g, respectively. No significant differences (p ≥ 0.05) were observed in coliform bacteria among meat samples 140 MPN. Fifty percent of processed meat collected from Khartoum state (minced meat and meat cubes) was E. coli present. It worth nothing that, frankfurter and martadella were E.coli free. It worth noted that, Staphylococcus aureus and Clostridium perfringens were not detected among all processed beef sample. In contrast, Salmonella were positive test among all processed meat.

Accurate classification of fresh fruit types is essential in the agricultural sector for ensuring quality control, minimizing waste, and enhancing food safety across the supply chain. This study evaluates the performance of four machine learning algorithms-artificial neural network (ANN), K-nearest neighbors (KNN), logistic regression (LR), and random forest (RF)-in classifying fruit freshness based on data obtained from electronic noses equipped with MQ array sensors. Experiments were conducted using a comprehensive dataset comprising various fruit combinations, and model performance was assessed using accuracy, precision, recall, and F1 score metrics. Results indicate that the RF algorithm achieved the highest accuracy (100%) and precision (1.00), demonstrating superior performance in both classification accuracy and computational efficiency. ANN and KNN also performed well, with accuracies of 96.80% and 97.10%, respectively, while LR yielded a lower but still effective accuracy of 91.16%. Statistical analysis confirms that RF's superior performance is statistically significant when compared to the other algorithms. These findings suggest that RF is the most effective algorithm for fruit freshness classification using electronic nose data, offering fast and reliable results that are well-suited for integration into real-time monitoring systems in agricultural and food retail applications.

Introduction:Recent advances in electronic nose technology, and successful clinical applications, are facilitating the development of new methods for rapid, bedside diagnosis of disease. There is a real clinical need for such new diagnostic tools in otolaryngology.Materials and methods:We present a critical review of recent advances in electronic nose technology and current applications in otolaryngology.Results:The literature reports evidence of accurate diagnosis of common otolaryngological conditions such as sinusitis (acute and chronic), chronic suppurative otitis media, otitis externa and nasal vestibulitis. A significant recent development is the successful identification of biofilm-producing versus non-biofilm-producing pseudomonas and staphylococcus species.Conclusion:Electronic nose technology holds significant potential for enabling rapid, non-invasive, bedside diagnosis of otolaryngological disease.

Food adulteration involving the mixing of non-halal meat into halal products is a sensitive issue in Indonesia. Wild boar meat (Sus scrofa vittatus) is often found to be used in such practices, making it essential to identify its volatile compound profile. This study aims to identify volatile compounds in wild boar meat processed through boiling, frying, and roasting, using Solid-Phase Microextraction (SPME) combined with Gas Chromatography-Mass Spectrometry (GC-MS). The research was conducted qualitatively with three treatments and five replications for each cooking method. The analysis showed that boiled wild boar meat contained 156 volatile compounds, fried meat 142 compounds, and roasted meat 163 compounds, with total intensities of 779, 691, and 819, respectively. Principal Component Analysis (PCA) yielded an R²X value of 0.842 and a cumulative Q² of 0.747, indicating clear separation between samples. The main contributing volatile compounds were 2-Octenal (E)-, Longifolene, and Cyclopropyl carbinol.

Due to the emergence of new microbreweries in the Brazilian market, there is a need to construct equipment to quickly and accurately identify the alcohol content in beverages, together with a reduced marketing cost. Towards this purpose, the electronic noses prove to be the most suitable equipment for this situation. In this work, a prototype was developed to detect the concentration of ethanol in a high spectrum of beers presents in the market. It was used cheap and easy-to-acquire 13 gas sensors made with a metal oxide semiconductor (MOS). Samples with 15 predetermined alcohol contents were used for the training and construction of the models. For validation, seven different commercial beverages were used. The correlation (R 2 ) of 0.888 for the MLR (RMSE = 0.45) and the error of 5.47% for the ELM (RMSE = 0.33) demonstrate that the equipment can be an effective tool for detecting the levels of alcohol contained in beverages.

An electronic nose (e-nose) is a device that mimics the function of the human nose and is able to recognize odours using gas sensors. The e-nose consists of a sampling system, a sensor array (in the detection system), with data acquisition and pattern recognition algorithm for computing system. The sensing chamber in an e-nose plays an important role in the detection system for any types of application. The design of the sensing chambers will determine several performance characteristics of the sensor's response signals which include the response time, stagnant region and gas to the sensor contact area. Several sensing chambers (rectangular, hemisphere & cylindrical) were designed using SolidWorks and printed (in 3-dimensional (3D)) to characterize and determine the design which is able to provide the optimum performance. Data analysis of the response time and parameters such as concentration and pressure were analyzed using NI LabView. Results show that the hemisphere shaped sensing chamber displayed the best performance in terms of a small stagnant region and a large gas to the sensor contact area even though the time response between sensing chambers is almost the same. The performance was due to the flow of the gas from the inlet to the outlet and the volume of the sensing chamber

Holeta has different peach fruit varieties that can be used for various purposes. However, their fruit quality characteristics were not fully identified. Studies have indicated that the physicochemical qualities of peach fruits are influenced by a number of factors, with the varietal factor being one of the most important. Limited information regarding the factors that affect these qualities is available in the country, specifically at Holeta. Therefore, this study was initiated to evaluate the physicochemical quality properties of peach fruit varieties. Their physical quality traits, such as fruit length, fruit diameter, fruit shape index, and average fruit weight, as well as chemical quality parameters, such as TSS, specific gravity, TA, ripening index, ascorbic acid content, and pH, were evaluated. The results revealed that both physical and chemical quality parameters were significantly affected by varietal factors. Among cultivars, 'Bonny Gold' had the longest fruit length, and 'Florida Down' had the largest fruit diameter. As far as average fruit weight is concerned, 88-18 W had the highest weight with 111.98 g, while Transvalia had the highest TSS and specific gravity. However, the 'Summer Sun' and 9A-35C varieties had the highest TA and ripening index, respectively. Thus, the physicochemical quality properties of the fruit were highly altered with peach varieties. Cuvinte cheie: fruct, fizico-chimic, calitate, soiuri, SST, AT, index de maturare.

Book may be reproduced in any form -by photo-print, microfilm, or any other means -nor transmitted or translated into a machine language without the permission in writing of the publisher. Only single copies of contributions, or parts thereof, may be reproduced for personal use.

Manufacturing of black tea is a complex process consisting of plucking, withering, curling, fermenting, drying, determining of quality, and packaging stages. Nowadays, tea quality is determined by two methods. Either chemical analysis method is used or tea tasters give quality scores by tasting, smelling, and visual inspection. By means of recent studies, tea quality can also be determined by electronic nose technology. The quality of tea is generally related with the fermentation stage. In this work, an electronic nose, which determines the quality of tea during the fermentation process in real time from only its odour, was made, and the fermentation band was controlled by this electronic nose. Fermentation bands of a tea factory in the Çayeli District of Rize, Turkey have been simulated and controlled via LabVIEW simulation software by using real odour values measured in the factory with the electronic nose. In the study, a new fermentation band system has been designed to function with the electronic nose. This section of the study has been performed in the simulation environment due to the high cost of physical system setup. With the method proposed in this study, tea factories will be able to increase their production capacity with higher quality.

In this research, a compact electronic nose (e-nose) based on a shear horizontal surface acoustic wave (SH-SAW) sensor array is proposed for the NO2 detection, classification and discrimination among some of the most relevant surrounding toxic chemicals, such as carbon monoxide (CO), ammonia (NH3), benzene (C6H6) and acetone (C3H6O). Carbon-based nanostructured materials (CBNm), such as mesoporous carbon (MC), reduced graphene oxide (rGO), graphene oxide (GO) and polydopamine/reduced graphene oxide (PDA/rGO) are deposited as a sensitive layer with controlled spray and Langmuir–Blodgett techniques. We show the potential of the mass loading and elastic effects of the CBNm to enhance the detection, the classification and the discrimination of NO2 among different gases by using Machine Learning (ML) techniques (e.g., PCA, LDA and KNN). The small dimensions and low cost make this analytical system a promising candidate for the on-site discrimination of sub-ppm NO2.

This study aimed to design a controlled sample display system on an electronic nose and test its performance for classifying synthetic flavors. There are four primary components to the electronic nose design. They are a controlled sample display system, detector, signal conditioning and preprocessing, and pattern recognition software. The sample display system consists of six vials. The sample room temperature setpoint is set to 40 ℃. The controlled sample display system has one heater and two fans to even the room temperature. The one-time data collection process consists of flushing (120 s), collecting (180 s), and purging (180 s). The samples for the performance test were synthetic flavors with four different aromas; durian, mocca, orange, and strawberry. Data analysis of gas sensor response was done through two stages; pre-treatment data processing and principal component analysis (PCA). The four samples were clearly different from others, according to the PCA results. The score...

Electronic nose (e-nose) has been developed and implemented in a wide area, included in food industries. This study was conducted to investigate the performance of an e-nose that utilizes a packed gas chromatography column and a gas sensor for classification of synthetic flavor products. There were six aroma variants of synthetic flavor evaluated, namely durian, jackfruit, ambonese banana, melon, orange and lemon. The e-nose was designed with four main parts, namely aroma provider, column and detector room, microcontroller, and data acquisition system. The device was operated automatically at a stable temperature of 60 °C. Collected data consisted of ten data of each sample was preprocessed by baseline equalization and normalization, extracted its distinctive feature and then were analyzed through pattern recognition analysis. There were two kinds of methods used to analyzed the patterns of the data, namely a fuzzy c-means clustering and an artificial neural network (ANN). With the fuzzy c-means clustering, the result was six data clusters with an unbalanced number of members, indicated that this analysis could not classify samples properly. Meanwhile, analysis with the ANN could classify properly the samples with the level of accuracy of 70%.

Classification and identification of synthetic flavor become routine activities in the flavor and food industry due to its application. As a modern olfactory technology, electronic nose (e-nose) has the possibility to be applied in these activities. This study aimed to evaluate an e-nose for classifying synthetic flavors. In this study, an e-nose was designed with an array of gases sensors as the main sensing component and principal component analysis (PCA) for the pattern recognition software. This research was started with preparation of the hardware, continued with preparation of sample, data collection, and analysis. There were nine samples of synthetic flavors with different aroma, namely: grapes, strawberry, mocha, pandanus, mango, jackfruit, orange, melon, and durian. The data collection process includes three stages, i.e. flushing, collecting, and purging of 2 min, 3 min, 2 min respectively. These sensor responses were then analyzed for forming aroma patterns. Four pre-treat...

This study evaluates an e-nose based on gas sensors to measure the freshness of tilapia. The device consists of a series of semiconductor sensors as detector, a combination of valve-vial-oxygen as sample delivery system, a microcontroller as interface and controller, and a computer for data recording and processing. The e-nose was firstly used to classify the fresh and non-fresh tilapia. A total of 48 samples of fresh tilapia and 50 samples of non-fresh tilapia were prepared and measured using the e-nose through three stages, namely: flushing, collecting, and purging. The sensor responses were processed into aroma patterns, then classified by two pattern classification softwares of principal component analysis (PCA) and neural network (NN). There were four methods for aroma patterns formation being evaluated: absolute data, normalized absolute data, relative data, normalized relative data. The results showed that the normalized absolute data method provides the best classification w...

Coconut oil, prized for its health benefits, faces quality threats from adulteration, particularly with cheaper palm oil. This not only degrades the quality but also poses health risks. Traditional detection methods are often laborintensive, destructive, and time-consuming. This study addresses the issue by applying multispectral imaging technology combined with machine learning to detect palm oil adulteration in coconut oil. We selected four machine learning algorithms-Support Vector Machines (SVM), Quadratic Discriminant Analysis (QDA), K-Nearest Neighbors (KNN), and Bagging-due to their robustness in handling complex datasets. These models achieved classification accuracies of up to 100 %, far surpassing traditional chemical tests, which are slower and dependent on tester expertise. To further enhance detection accuracy, we employed both hard-and soft-voting mechanisms, integrating the strengths of individual models to improve overall reliability. This research marks a significant advancement in detecting coconut oil adulteration, offering a faster, more efficient solution to ensure product quality and consumer health.

Artificial Neural Networks (ANNs) have surfaced as a potent transformative influence in smart agriculture, significantly improving soil, crop, irrigation, disease, pest, weed management, and decision support systems. ANNs excel at recognizing non-linearity and intricate relationships among variables such as soil nutrients, soil temperature, whether temperature and leaf characteristics help to detect and predict crop health. Crop suitability concerning soil characteristics, crop yields, soil fertility level, irrigation and fertilizer time tables, weed and disease prediction are the other areas where these models find immense usage.. Combining ANN models with cutting-edge remote sensing technologies, like UAVs fitted with high-resolution cameras, spectral sensors, and IoT devices, enhances their predictive precision. This results in more reliable outcomes for farmers and helps to minimize all pre-harvesting losses.Through continuous research and development, ANNs were set to take on an increasingly crucial role in revolutionizing agricultural methods, boosting efficiency, and improving productivity for a sustainable future.ANN models in farming is aligned with SDGs established under national agriculture mission of our nation for 2021-2025, Tamil Nadu precision farming mission and national AI mission. This review paper fills the gap between soil health, crop prediction, crop yield, scientific irrigation, and fertilizer uses.It directly and indirectly contributes towards enhancing soil fertility that can lead to sustainable agriculture. Keywords:-Artificial Neural Networks (ANNs), Soil health management, Crop prediction , Crop yield, Sustainable Agriculture 1.INTRODUCTION Agriculture is fundamental to economic activity, food security, and sustainable development. However, it has become unsustainable due to traditional practices, including excessive use of fertilizers, pesticides, unscientific irrigation, and cultivating crops unsuitable for specific soils with continuously increasing food demand. These methods harm soil health, the nutrient value of crops, and lead to major consequences such as crop yield ,environment sustainability and ultimately affecting human health. Additionally, burning, slash-and-burn, and climate change effects such as altered growing seasons and water scarcity threaten crop yields and food security.

Introduction: Tuberculosis (TB) is the leading cause of death due to an infectious disease worldwide. Especially in low-income countries, new diagnostic techniques that are accessible, inexpensive and easy-to-use, are needed to shorten transmission time and initiate treatment earlier. Objective: We conducted a study with a handheld, point-of-care electronic nose (eNose) device to diagnose TB through exhaled breath. Setting: This study includes a total of 110 patients and visitors of an expert centre of respiratory diseases in Asunción, Paraguay. TB diagnosis was established by culture of Mycobacterium tuberculosis complex and compared with the eNose results in two phases. The calibration phase, including only culture confirmed TB cases versus healthy people, demonstrated a sensitivity and specificity of 91% and 93% respectively. The confirmation phase, including all participants, showed a sensitivity of 88% and a specificity of 92%. The eNose showed high acceptance rate among participants, and was easy to operate.

Exhaled human breath contains a rich mixture of volatile organic compounds (VOCs) whose concentration can vary in response to disease or other stressors. Using simulated odorant-binding proteins (OBPs) and machine learning methods, we designed a multiplex of short VOC- and carbon-binding peptide probes that detect the characteristic "VOC fingerprint". Specifically, we target VOCs associated with COVID-19 in a compact, molecular sensor array that directly transduces vapor composition into multi-channel electrical signals. Rapidly synthesizable, chimeric VOC- and solid-binding peptides were derived from selected OBPs using multi-sequence alignment with protein database structures. Selective peptide binding to targeted VOCs and sensor surfaces was validated using surface plasmon resonance spectroscopy and quartz crystal microbalance. VOC sensing was demonstrated by peptide-sensitized, exposed-channel carbon nanotube transistors. The data-to-device pipeline enables the develop...

Holeta has different peach fruit varieties that can be used for various purposes. However, their fruit quality characteristics were not fully identified. Studies have indicated that the physicochemical qualities of peach fruits are influenced by a number of factors, with the varietal factor being one of the most important. Limited information regarding the factors that affect these qualities is available in the country, specifically at Holeta. Therefore, this study was initiated to evaluate the physicochemical quality properties of peach fruit varieties. Their physical quality traits, such as fruit length, fruit diameter, fruit shape index, and average fruit weight, as well as chemical quality parameters, such as TSS, specific gravity, TA, ripening index, ascorbic acid content, and pH, were evaluated. The results revealed that both physical and chemical quality parameters were significantly affected by varietal factors. Among cultivars, 'Bonny Gold' had the longest fruit length, and 'Florida Down' had the largest fruit diameter. As far as average fruit weight is concerned, 88-18 W had the highest weight with 111.98 g, while Transvalia had the highest TSS and specific gravity. However, the 'Summer Sun' and 9A-35C varieties had the highest TA and ripening index, respectively. Thus, the physicochemical quality properties of the fruit were highly altered with peach varieties. Cuvinte cheie: fruct, fizico-chimic, calitate, soiuri, SST, AT, index de maturare.

Analysis of odor components about biochemicals find the wide space in the evaluation of flavor parameters and anchovies as biological materials. Food dye solutions as printer's inks were sprayed on to the fabric throughout the printing operation and skin oil vapors of anchovy were simultaneously sent to the paper hopper of printer intensely via a nebulizer device. Before and after dyeing process, images of tela fabric were taken by smartphone and analyzed by software in the smartphone for the purpose of determination of colorimetric fragrance component concentrations and visual odor profile in range of visible region. The ten major ingredient contents (with relative percentages) (aldehyde compounds intensely such as 2,4-heptadienal (23%), (E,E)-2,4-nonadienal (17%)) of anchovy skin essential oils were determined. For colorimetric printing analysis via smartphone, LOD and LOQ were 1 ppm and 3 ppm, respectively. Methodology can be used in the analysis of toxic components that inte...

Odor classification by a robot equipped with an electronic nose (e-nose) is a challenging task for pattern recognition since volatiles have to be classified quickly and reliably even in the case of short measurement sequences, gathered under operation in the field. Signals obtained in these circumstances are characterized by a high-dimensionality, which limits the use of classical classification techniques based on unsupervised and semi-supervised settings, and where predictive variables can be only identified using wrapper or post-processing techniques. In this paper, we consider generative topographic mapping through time (GTM-TT) as an unsupervised model for time-series inspection, based on hidden Markov models regularized by topographic constraints. We further extend the model such that supervised classification and relevance learning can be integrated, resulting in supervised GTM-TT. Then, we evaluate the suitability of this new technique for the odor classification problem in robotics applications. The performance is compared with classical techniques as nearest neighbor, as an absolute baseline, support vector machine and a recent time-series kernel approach, demonstrating the eligibility of our approach for high-dimensional data. Additionally, we exploit the learning system introduced in this work, providing a measure of the relevance of each sensor and individual time points in the classification process, from which important information can be extracted.

Background: There is an increasing interest in employing electronic nose technology in the diagnosis and monitoring of lung diseases. Interstitial lung diseases (ILD) are challenging in regard to setting an accurate diagnosis in a timely manner. Thus, there is a high unmet need in non-invasive diagnostic tests. This single-center explorative study aimed to evaluate the usefulness of electronic nose (Aeonose®) in the diagnosis of ILDs. Methods: Exhaled volatile organic compound (VOC) signatures were obtained by Aeonose® in 174 ILD patients, 23 patients with chronic obstructive pulmonary disease (COPD), and 33 healthy controls (HC). Results: By dichotomous comparison of VOC’s between ILD, COPD, and HC, a discriminating algorithm was established. In addition, direct analyses between the ILD subgroups, e.g., cryptogenic organizing pneumonia (COP, n = 28), idiopathic pulmonary fibrosis (IPF, n = 51), and connective tissue disease-associated ILD (CTD-ILD, n = 25) were performed. Area unde...

Grapefruit and lemon were exposed to phytosanitary irradiation doses of 0, 0.4, and 1 kGy, and then electronic-sensing screening of irradiation status and identification of radiation-induced ESR markers were conducted during 20 days storage. Codex standard photostimulated luminescence measurement (PSL 1 ) was not a reliable indicator of irradiation status. Electronic tongue and electronic nose, however, showed potential as screening tools for discriminating irradiated fruits from non-irradiated counterparts based on principal component analysis of taste attributes and flavor patterns. Calibrated PSL approach clearly distinguished irradiated from nonirradiated samples based on the PSL ratio (PSL 2 /PSL 1 ). Verification of irradiation status by electron spin resonance spectroscopy revealed clear paramagnetic centers from both irradiated fruits samples and ethanol-vacuum drying pretreatment improved radiation-induced ESR signal detection; not prominent enough in 0.4 kGy-irradiated commodities during 20 days of storage. Peel parts of both fruits showed high limonene which proportionally increased with irradiation doses (p \ 0.05 kGy).

2017 under Grant 779, and in part by the Universidad Pedagógica y Tecnológica de Colombia (UPTC) through the DIN 14th of 2018 ''Estímulo económico para jóvenes investigadores UPTC'' of UPTC Young Researcher for the research group ''Grupo de investigación en Energía y Nuevas TEcnologías -GENTE'' under Contract 456.

Rapid detection of bacterial foodborne pathogens is crucial in reducing the incidence of diseases associated with food contaminated with pathogens and toxins. This article presents a classification model of support vector machine (SVM) together with a metaheuristic framework using genetic algorithm (GA), particle swarm optimization (PSO), and grid searching (GS) optimization algorithms for bacterial foodborne pathogen classification and differentiation. LDA and SVM showed classification accuracies of training (90.3% and 91%) and prediction (89.5% and 90.6%), respectively using the Matlab classification learner app. Optimization of the modeling parameters c and g for SVM were performed to increase efficiency and classification accuracy. Simulated results show classification accuracies of 100% (training set) and 98.95% (prediction set) for five selected bacterial pathogens acquired using electronic nose dataset and PSO‐SVM model. Electronic nose recognition system made up of 12 metal ...

The primary issues in collecting biochemical information in a large area using chemical laboratory procedures are low throughput, hard work, time-consuming, and requiring several samples. Thus, real-time and precise estimation of biochemical variables of various fruits using a proximal remote sensing based on spectral reflectance is critical for harvest time, artificial ripening, and food processing, which might be beneficial economically and ecologically. The main goal of this study was to assess the biochemical parameters of banana fruits such as chlorophyll a (Chl a), chlorophyll b (Chl b), respiration rate, total soluble solids (TSS), and firmness using published and newly developed spectral reflectance indices (SRIs), integrated with machine learning modeling (Artificial Neural Networks; ANN and support vector machine regression; SVMR) at different ripening degrees. The results demonstrated that there were evident and significant differences in values of SRIs at different ripen...

The spacc charge bcliavior of snnie pnlyvinylchloride (PVC) samplcs with different iniolecular microstructures, obtained through chcniical inodiiicalion of i'vc has been analyzcd by iiieans of tlie thermal stcp (TS) and the thermally stimulated discharge current (TSIIC) techniques. The tnagnitude of the spicc cliargc distribution has been shown to be lower as thc dcgrcc of chemical modification increases. Combiniiig the 'IS and the TSIK tiicthods allowed its tu study niinority carriers, which could not be observed by a singlc TS nieasorement,

Recent research on volatile organic compounds (VOC) released by the heated vegetation has shown that, under specific conditions (e.g., extreme heat, humidity, wind, and topography), VOC might foster wildfire ignition sources and explain sudden changes in fire behavior, particularly in the most susceptible and flammable forests (eucalypt forests). This work aims to develop an electronic nose (e-nose) based on a sensor's array to monitor the concentration of eucalyptol, the major VOC compound of the Eucalyptus globulus tree. The detection of this target compound was achieved by measuring the impedance spectra of layer-by-layer developed thin films based on polyethyleneimine, poly(allylamine hydrochloride), and graphene oxide, by injecting the analyte into a custom-made vacuum chamber system. The obtained results were analyzed by the principal component analysis method. The developed e-nose sensor was able to distinguish different concentrations in a range from 411 to 1095 ppm.

The effect of the applied voltage on impedance spectra, measured on sensors based on solid supports with interdigitated electrodes (IDE) that are either covered or not with a layer-by-layer film prepared with polyethylenimine and poly (sodium 4-styrenesulfonate), was analyzed to detect 17α-ethinylestradiol(EE2) in mineral water and tap water. The results show that the sensor response is strongly affected by the applied voltage, the presence of film, and the water matrix, meaning that electrochemical reactions develop near the IDE. However, for low values of applied voltage, the sensor response is reproducible with negligible electrochemical reactions, allowing us to conclude that 25 mV is the appropriate voltage.

The stochastic component of the sensor signal in commercial semiconductor gas sensors during exposure to different gases has been studied. The resistance fluctuation measurements have been carried out using different concentrations of ethanol, CO, NO x , H 2 and SO 2 in dry synthetic air. The analysis of the stochastic resistance fluctuations in gas sensors during exposure to gases enables an enhanced sensitivity and selectivity. The normalized power spectrum is characteristic for each sensor, and each gas induces a new characteristic power spectrum. In many cases, sensors can be used even for different gases than the gas they were originally designed for.

There has been rapidly accelerating interest in the utilization of volatile organic compounds (VOCs) as non-invasive methods for rapid point-of-care medical diagnostics. There is widespread variation in analytical methods and protocols, with little understanding of the effects of sample storage on VOC profiles. This study aimed to determine the effects on VOC profiles of different storage times, at room temperature, prior to freezing, of sealed urine samples from healthy individuals. Analysis using Field Asymmetric Ion Motility Spectrometry (FAIMS) determined the alterations in VOC and total ion count profiles as a result of increasing room temperature storage times. Results indicated that increasing exposure time to room temperature prior to freezing had a threefold effect. Firstly, increased urinary VOC profile variability, with a plateau phase between 12 and 48 hours, before further degradation. Secondly, an increase in total ion count with time exposed to room temperature. Finally, a deterioration in VOCs with each sample run during the analysis process. This provides new insight into the effect of storage of urine samples for VOC analysis using FAIMS technology. Results of this study provide a recommendation for a 12-hour maximum duration at room temperature prior to storage.

photocoagulation therapy for their AE. On logistic regression, factors associated with a subsequent change in management included the indication of OB (p = 0.03), the presence of comorbidity (p = 0.03), transfusion dependence (p = 0.02) and the presence of AE (p < 0.001) on the CE. In 14% of patients, significant lesions were found outside the SB (upper GI tract 12% and colon 2%). Conclusion This is the largest series on the use of CE in OGB in the published literature. A significant number of patients with a positive DY had a change in management. Factors that were more likely to predict an alteration of outcome were the presence of comorbidity, transfusion dependence and the presence of AE. Although, the DY did not differ significantly between those with IDA and OB, management was more likely to be altered in those with OB. Disclosure of Interest None Declared.

This study aimed to determine if exhaled volatile organic compounds (VOCs), analysed with electronic nose (eNose) and gas chromatograph -ion mobility spectrometer (GC-IMS) technology, can be used to distinguish inflammatory bowel disease (IBD) from controls and Crohn's disease (CD) from ulcerative colitis (UC).

Defects are often symbolised as deformity in material that deteriorate its performance. However in nanoscale regime, defects lead to generate a useful and novel material for device applications. In the present report, the vacancy defects i.e. single vacancy and double vacancy defects (with different symmetry) on graphene sheet have been analysed to understand the electronic as well as transport properties using density functional theory and NEGF approach. Conductance, current-voltage and sensitivity analysis, these defected graphene sheet have been examined for its suitability for gas sensing application particularly for ammonia gas. The study observes that a single vacancy defected graphene is a good candidate for ammonia molecule sensing, in comparison to double vacancy.

Electronic noses have been used for fast characterization of diverse species of samples. One of the major drawbacks of electronic noses is the lack of knowledge about the chemical species that are actually detected. On the other hand, mass spectrometers are emerging as fast and sensitive methods for real time analysis of gaseous samples. In this paper, these two analytical approaches are connected together in order to fully characterize samples and to ascertain the origin of the electronic nose performance.

Biosensors can find application in meat and meat products testing for safety, including microbial and other contaminants, and quality, including meat freshness, beef tenderness and pork quality defects. The available biosensors enable the evaluation of freshness, the classification of tenderness of meat products, the evaluation of the glycolysis extent and the presence of the microbial and other contaminants. Since biosensors depend on receptor types, the expansion of knowledge on metabolic transformations occurring in meat contributes to the development of new potential markers and indicators. Examples include assays for glucose, lactates, hypoxanthines, calpastastins, microbial and other contaminants in meat products, augmenting conventional methods. At the same time, biosensors rely on transducers for detection, requiring achievement in many fields including nanotechnology and optics, among others. Biosensors have potential to become a fundamental tool for monitoring and controll...

Abstract: An asymmetrical factorial experiment approach was used for improved gas/odor discrimination using thick film gas sensor data. The results revealed that the gases/odors(G), sensors(S), concentrations of gases(C), and interactions between GXS were found to be significant at 1 % level of significance while the interaction between GXC was significant at 5 % level. It indicated that the gas/odor, Methanol (CH3OH) and Acetone (CH3COCH3) were at par while Propanol (C3H7OH) was different at 1 % level of significance. Among the sensors S2 and S4 were at par while S1 and S3 differed significantly at 1 % level. The initial concentrations differed significantly while they did not differ at the later stages. Among the interaction of GXS, the sensor S1 and S4 were at par under Methanol, S2 and S3 were at par under Propanol and S2 and S4 were at par under Acetone respectively.

In this paper a novel approach for performing discriminative test in food quality control is reported. The method is based on the use of an electronic nose equipped with 10 Metal Oxide Semiconductor Field Effect Transistor (MOSFET) sensors, 12 Metal Oxide Semiconductor (MOS) sensors and one humidity sensor. The pattern of the sensor responses generated by the electronic nose has been used for performing "objective" triangle tests in several food products. The results were compared with the data obtained by using standard methodology (triangle test) of sensory analysis (UNI ISO 4120 Norm). The e-nose is able to classify correctly all the samples under study, while the sensory panel is able to correctly perform the test only in 50% of the cases. As compared with the sensory test, the electronic nose methodology is simple, rapid and results suggest that it can be useful tool for performing discriminative testing.