Chemical Gas Sensor Array Research Articles

Improved deep bidirectional recurrent neural network for learning the cross-sensitivity rules of gas sensor array

Cross-sensitivity among chemical gas sensors leads to inaccurate identification of mixed gas. Pattern recognition algorithms are usually applied to improve the recognition accuracy. However, the abilities of current methods to process sequence property of response data are not strong enough. Especially, they cannot deal with bidirectional cross-sensitive issue, leading to recognition errors. Bidirectional Recurrent Neural Network (BRNN) could well learn bidirectional association features between word sequences in natural language processing field, which is similar to the bidirectional interaction of cross-sensitivity. In this study, an improved deep BRNN model was constructed to solve the cross-sensitivity problem of chemical gas sensor array. A chemical gas sensor array with four units was fabricated and response data was thoroughly obtained. Data preprocessing methods, model structure hyperparameters and optimizers were studied. Finally, an improved deep BRNN model was developed with 3 layers and 100 hidden_size, training with Adamax optimizer. A recognition accuracy of 98.93% was achieved, attributing to the model’s excellent learning ability to the bidirectional cross-sensitivity rules among gas sensors. This improved BRNN model provided a novel idea to eliminate cross-sensitivity, exhibiting good potential for recognizing mixed gas analyte accurately.

Detection of COPD and Lung Cancer with electronic nose using ensemble learning methods

Background and aimsThe chemical gas sensor array based electronic-nose (e-nose) devices with machine learning algorithms can detect and differentiate expelled breath samples of patients with various respiratory ailments and controls. It is by the recognition of levels and variations of volatile organic compounds (VOC) in the exhaled air. Here, we aimed to differentiate chronic obstructive pulmonary disease (COPD) and lung cancer from controls. Materials and methodsThis work presents the details of the developed e-nose system, selection of the study subjects, exhaled breath sampling method and detection, and the data analysis algorithms. The developed device is tested in 199 participants including 93 controls, 55 COPD patients, and 51 lung cancer patients. The main advantage of the device is robustness and portability and cost-effectiveness. ResultsIn the training phase and model validation phase, the ensemble learning method XGBoost outperformed the other two models. In the prediction of lung cancer, XGBoost method attained a classification accuracy of 79.31%. In COPD prediction also the same method had given the better results with 76.67% accuracy. ConclusionThe e-nose system developed with TGS gas sensors was portable, low cost, and gave a rapid response. It has been demonstrated that the VOC profiles of patients with pulmonary diseases and healthy controls are different and hence the e-nose system can be used as a potential diagnostic device for patients with lung diseases.

A mixed-kernel, variable-dimension memristive CNN for electronic nose recognition

Due to the dynamic characteristics, memristors have great potential for implementing various neural network training and applications. By applying memristors to neural networks as a strategy, the hardware architecture can be taken full advantage of to accelerate matrix operations. A mixed-kernel, variable-dimension memristive convolutional neural network (MixVMCNN), which can identify and classify six gases detected by the electronic nose, is proposed. To generate better gas recognition technique, we provide various receptive fields for the network by using different sizes of convolutional kernels in the same layer. We propose a novel variable-dimension convolutional approach that extracts features in different dimensions. Furthermore, we make use of memristor arrays to make the most of the hardware structure to speed up calculation. Experimental results indicate that the designed network, using only 56 weights, achieves the electronic nose gas classification with high accuracy of 99.72%, based on the Chemical gas sensor array dataset. To further exam the effectiveness of the model, supplemental experiments show that this model has stronger noise-robustness than other networks.

Discriminative power of independent component analysis applied to an electronic nose

Electronic noses have been developed to analyze gas composition in many applications. The potential analytical power of an electronic nose needs to be investigated with regard to detection in a complicated gas environment. To date, principal component analysis (PCA) has been a popular analytical tool for use with electronic noses; however, PCA reaches its limits when the measurement data exhibit non-Gaussian behavior. Components extracted by independent component analysis (ICA) are expected to have a high discriminative power, conducive to improving the performance of an electronic nose. To verify this hypothesis, the performance of principal components (PCs) and independent components (ICs) in classification and regression tasks is compared. The data were obtained from a chemical gas sensor array for volatile organic compounds (VOCs). In the classification task, silhouette coefficients and K-means are employed to measure the performance of ICs and PCs. ICs have evident classification advantages over PCs because of their higher accuracy. In the regression task, ICs and PCs are applied via a neural network to predict the concentration of four VOCs. The errors in the prediction are calculated and analyzed, and it is found that ICs continue to outperform PCs during the regression task. The results of this study demonstrate the potential and ability of ICA to extract features when used with an electronic nose in a complicated gas environment.

Iterative complex network approach for chemical gas sensor array characterisation

Gas sensor arrays, also known as e-noses, are used in several heterogeneous fields, ranging from environmental monitoring to food quality control. Often, these measurement systems operate within dynamic environments and are subject to conditions which may dramatically vary over time. Furthermore, the response of an e-nose is influenced by several parameters, whose interactions may be complex and highly non-linear. Therefore, in this study, the authors propose a complex network approach to model the overall interaction pattern of e-noses. They show that this approach can significantly improve the understanding of the overall behaviour of e-noses, and can be used as a basis to optimise the design of these measurement systems.

Dataset from chemical gas sensor array in turbulent wind tunnel.

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

Experimental use of electronic nose for odour detection

An electronic nose is an intelligent system for discrimination of odours and used to mimic the human nose of smell. Tin oxide semiconductor gas sensors are used for the development of electronic nose. It employs an array of chemical gas sensors, a sample handling system and a pattern recognition system. These techniques allow the system for a high degree of selectivity and reversibility. The ideal gas sensor has properties like reversibility, selectivity, robustness, sensitivity and reliability. After signal processing and feature extraction, a unique 'smell print' of the substance is obtained for classification, concentration measurement and to judge the quality. This paper describes the function of electronic nose, its applications and detecting the smell of particular volatile organic compound like benzene, acetone and ethanol at different concentrations. The obtained characteristics and response from electronic nose indicates that it can be used for distinct applications like pharmaceutics, defence and security industries.

Desarrollo de un sistema embebido con tecnología DSP para un sistema multisensorial (Nariz electrónica)<br />Development of embedded system with DSP technology for multisensor system (Electronic nose)

This article consists in the development of an embedded system with DSP technology to be applied to a multi-sensory system (i.e. Electronic Nose). The idea of the present study was to improve the efficiency of these multisensory systems in portable applications, using different algorithms to classify three-class of volatile compounds, detected by a chemical gas sensor array. The Code Composer Studio (CCS) software was coupled with Matlab for programming the DSP TMS320F28335 card of Texas Instruments. The results were obtained from samples of wine of three different denominations (i.e., apple, red and Locker), which were then classified by processing algorithms (i.e. artificial neural networks). The system was validated by the technique of principal component analysis (PCA), to verify repeatability and selectivity of the measurement system. In the results, 83.4% of success rate in classification of the measures was obtained using DSP Hardware, through the implementation of an Artificial Neuronal Network (ANN).

Customized vic-dioximes and their metal complexes for enhanced chemical sensing of polar organic molecules

Vic-dioximes and their nickel and palladium complexes were customized with fluorinated substituents including moieties capable of hydrogen bonding to improve selectivity in chemical sensing of polar analytes. Many analytes of interest in applications as diverse as food stuff or air quality analysis are of polar chemical nature. Such compounds, e.g., ketones, esters or alcohols contribute to the aroma of fruits and food products, but are also in industrial use as solvents in paints or in the production of plastic products. The gas sensing properties of the new compounds are demonstrated using the quartz crystal microbalance and selected volatile organic compounds as analytes.The results illustrate that fluorinated alkylamino and arylamino substituents efficiently enhance and direct the sorption preferences of vic-dioxime metal complexes toward polar analytes. High sensor responses to polar analytes including high vapor pressure analytes like acetone and methanol were observed, whereas the responses to aromatic hydrocarbons are low. Besides, the individual sensor responses were only little affected by water vapor. H bonding activities of the NH group are identified as the source for the observed selectivity patterns. The vic-dioximes are considered excellent sensing materials for practical use in chemical gas sensor arrays for sensing of polar compounds.

Metal complexes of vic-dioximes for chemical gas sensing

Metal complexes of vic-dioximes are characterized as new candidate materials for volatile organic compound sensing with sorption based chemical gas sensors. They are proposed as an interesting alternative to conventional sensing materials with metal ion centers such as phthalocyanines or porphyrins. Besides, they are considered an appealing platform to study metal effects on analyte sorption and sensor performance due to a high variety in possible metal centers. In this work, the sensing properties are explored with the quartz crystal microbalance on the basis of a set of vic-dioximes complexes varied in their metal ion centers (Ni 2+, Pd 2+, Cu 2+, Co 2+) and substituents (alkyl chain lengths from C 3H 7 up to C 7H 15) and twelve selected analytes. Depending on the metal center and substituents widely diverging selectivity patterns were observed indicating preferences for alcohols, amines, and aromatic compounds. The results presented in this work show that the proposed metal complexes of vic-dioximes are excellent sensing materials and very promising for the use in chemical gas sensor array applications.

Vic-dioximes: A new class of sensitive materials for chemical gas sensing

Vic-dioximes, a class of organic chemical compounds, are proposed and characterized for the first time as sensitive materials for volatile organic compound sensing with sorption based chemical gas sensors. Their peculiar sensing properties described in this work originate in the oxime functional group which is a powerful H bond donor interacting strongly but reversibly with H bond acceptors. These specific interactions result in a high preferential enrichment of analyte molecules with H bonding acceptor capabilities in the sensitive material. Accordingly, sensitivity and selectivity for these compounds of vic-dioxime based sensors are high. The advantageous sensing properties are demonstrated in this work with quartz crystal microbalance sensors using 11 selected volatile organic compounds and a set of vic-dioximes varied in their substituents. Vic-dioximes with short alkylthiol substituents were found highly sensitive to such H bond acceptors as organic amines, alcohols, and esters with partition coefficients up to 26,000. At the same time they showed low affinity for aromatic compounds and chlorocarbons. Vic-dioximes are considered powerful sensing materials and interesting for practical use in chemical gas sensor arrays.

Transforming a Laser Micromachiner into a Direct-Write Tool for Electronic Materials

A conventional laser micromachining system is configured for use as a matrix-assisted pulsed laser evaporation direct-write (MAPLE-DW) system in a straightforward and cost-effective manner. The simplicity of the method is illustrated by highlighting the process for MAPLE-DW of polymer composites used in chemical gas sensor arrays. Important aspects are considered, including ribbon preparation, ribbon aging, and computerized process control for rapid prototyping.

Data analysis for electronic nose systems

Electronic noses (e-noses) employ an array of chemical gas sensors and have been widely used for the analysis of volatile organic compounds. Pattern recognition provides a higher degree of selectivity and reversibility to the systems leading to an extensive range of applications. These range from the food and medical industry to environmental monitoring and process control. Many types of data analysis techniques have been used on the data produced. This review covers aspects of analysis from data normalisation methods to pattern recognition and classification techniques. An overview of data visualisation such as non-linear mapping and multivariate statistical techniques is given. Focus is then on the use of artificial intelligence techniques such as neural networks and fuzzy logic for classification and genetic algorithms for feature (sensor) selection. Application areas are covered with examples of the types of systems and analysis methods currently in use. Future trends in the analysis of sensor array data are discussed.

Gas sensor arrays based on polymer-carbon black to detect organic vapors at low concentration

A novel chemical gas sensor array composed of polymer-carbon black is successfully fabricated. Poly(4-vinyl phenol) (PVPH), poly(ethylene oxide) (PEO), polycaprolactone (PCL) mixed with carbon black 2000 are employed as the sensing materials which are immobilized on the array of the interdigitated microelectrode pairs. The resistance changes with the organic gases (acetone, ethanol, toluene, methanol Tetrahydrofuran) and their mixed gases at low concentration have been examined. By the pattern recognition analysis of the responses of microsensors, five single gases and their mixed gases can be easily identified at the concentrations between 200 and 2000 ppm. The measurement data show that this configuration of interdigitated microelectrodes is a good choice to detect the low concentration of organic gases

필드 스크린을 위한 휴대용 전자코 시스템의 구현

There is currently much interest in the development of instruments that emulate the senses of humans. Increasingly, there is demand for mimicking the human sense of smell, which is a sophisticated chemosensory system. An electronic nose system is applicable to a large area of industries including environmental monitoring. We have designed a protable electronic nose system using an array of commercial chemical gas sensors for recognizing and analyzing the various odours. In this paper, we have implemented a portable electronic nose system using an array of gas sensors for recognizing and analyzing VOCs (Volatile Organic Compounds) in the field. The accuracy of a portable electronic nose system may be lower than an instrument such as GC/MS (Gas Chromatography/Mass Spectrometer). However, a portable electronic nose system could be used on the field and showed fast response to pollutants in the field. Several different algorithms for odours recognition were used such as BP (Back-Propagation) or LM-BP (Levenberq-Marquardt Back-Propagation). We applied RBF (Radial Basis Function) Network for recognition and quantifying of odours, which has simpler and faster compared to the previously used algorithms such as BP and LM-BP.

Monitoring growth of the methanogenic archaea Methanobacterium formicicum using an electronic nose

Growth of the methanogenic archaea, Methanobacterium formicicum, in pure culture was monitored by analysing samples from the gas phase with an array of chemical gas sensors (an 'electronic nose'). Analyses of the methane and protein formation rates were used as independent parameters of growth, and the data obtained from the electronic nose were evaluated using principal component analysis (PCA). We found that different growth phases can be distinguished with the electronic nose followed by PCA evaluation. The fast response of the sensors in combination with the high correlations with other parameters measuring growth show that the electronic nose can be a useful tool to rapidly determine methanogenic growth.

Micromachined polymer-based chemical gas sensor array

We have developed a miniature polymer-based chemical gas sensor array on silicon using micromachining technology. The sensors are polymer–carbon black composite films, which swell reversibly and cause a resistance change upon exposure to a wide variety of gases. We have fabricated two types of devices which can measure this resistance change using a “well” design. These “wells” contain the polymer–carbon black–solvent liquid volume present during deposition and allow the sensor film to be placed reproducibly in a specific and well-constrained area. After deposition, the solvents evaporate and leave behind a polymer–carbon black residue crust between metal leads on each side of the “well”. Two types of devices, a bulk micromachined sensor and a patterned thick-film sensor, have been fabricated, ranging in size from 500 μm×600 μm to 100 μm×100 μm. Since the composite film sensors are not specific to any one gas, an array of these sensors, each with a different sensing film, is used to identify gases and gas mixtures through the pattern response of the array. Six polymer–carbon black composite films were deposited into the sensor array and exposed to three chemical gases at five different concentration levels. The sensors were able to uniquely detect these gas vapors and demonstrated a linear response to concentration levels between 2000 and 10,000 ppm. Results also indicate that a reduction in sensor area by an order of magnitude (from 4.32 to 0.30 mm 2) does not reduce sensor response. This design allows the integration of circuits to process the changes in resistance which will permit the realization of a completely integrated miniature gas sensor.

Electronic noses for bioreactor monitoring.

Electronic noses provide new possibilities for monitor the state of a cultivation non-invasively in real-time. The electronic nose uses an array of chemical gas sensors that monitors the off-gas from the bioreactor. By taking advantage of the off-gas components' different affinities towards the sensors in the array it is possible with the help of pattern recognition methods to extract valuable information from the culture in a way similar to the human nose. For example, with artificial neural networks, metabolite and biomass concentration can be predicted, the fermentability of a medium before starting the fermentation estimated, and the growth and production stages of the culture visualized. In this review these and other recent results with electronic noses from monitoring microbial and cell cultures in bioreactors are described.

Odour discrimination with an electronic nose

Smell is probably the least understood and exploited of the principal human senses, yet it is clearly important to both product and process control in many industries, such as foodstuffs, beverages, tobacco and perfumery. Advances in the field of integrated microelectronic devices have led to new instruments, robots, capable of vision and complex touch or taction, but not yet of smell. This paper reviews the research effort that has been carried out at Warwick University over recent years into the development of an electronic instrument that can mimic the human sense of smell. The approach that we have adopted is to construct a microprocessor-controlled system comprising an array of solid-state chemical gas sensors (with overlapping partial sensitivities to odorants) and associated signal processing and pattern recognition. This electronic system is based upon our present knowledge of the biological system. Our earliest electronic nose consisted of an array of only three to twelve tin dioxide thick-film sensors, yet it can discriminate between alcohols, beverages, tobacco blends and coffees. Current efforts are reported towards the fabrication of an integrated microsensor metal oxide array, the development of other electronic devices using polymeric materials, and the implementation of various pattern-recognition techniques, including correlation, principal-component analysis, cluster analysis and artificial neural networks. Finally, the application areas most likely to arouse widespread interest in the next decade are discussed.