Search results

The University of Southampton has been active in the area of thick‐film sensors since their initial conception through to the present. Recent research at the university has concerned the use of thick‐film sensor arrays for the discrimination of chemical species in both gaseous and dissolved form. In addition, the detection of many physical parameters is now being addressed through the use of arrays of sensing elements with a view to improving on factors such as noise immunity, environmental cross‐sensitivity and long‐term accuracy. In the area of chemical sensing, extensive use has been made of thick‐film technology to allow low‐cost arrays of chemical sensors to be fabricated. The lack of specificity exhibited by the individual sensing elements has been demonstrably overcome through the use of signal processing techniques applied to the outputs of the array of sensors. Thick‐film chemical sensor research currently under way at Southampton includes a UK DTI/SERC funded LINK project concerning dissolved species monitoring for water quality assessment. Additionally, gas sensor arrays for the detection of toxic and flammable gases are being explored as part of a well established ongoing research programme. The use of thick‐film technology for the fabrication of physical sensors has been extensively documented. Current research at the University of Southampton includes an industrially sponsored project involving the use of thick‐film strain sensing resistors in the design of an accelerometer. The use of Z‐axis piezoresistivity and an array approach to solving noise and drift problems is seen as a significant novelty in this work.

The purpose of this paper is to construct an array of sensors using polypyrrole–zinc oxide (PPy–ZnO) and PPy–vanadium (V; chemical formula: V₂O₅) fibers. To test responses of sensors, a central composite design (CCD) has been used. The results of the CCD technique revealed that the developed sensors are orthogonally sensitive to diacetyl, lactic acid and acetic acid. In total, 20 different mixtures of diacetyl, lactic acid and acetic acid were prepared, and the responses of the array sensors were recorded for each mixture.

A response surface regression analysis has been used for correlating the responses of the sensors to diacetyl, lactic acid and acetic acid concentrations during the gas phase in food samples. The developed multivariate model was used for simultaneous determination of diacetyl, lactic acid and acetic acid concentrations. Some food samples with unknown concentrations of diacetyl, lactic acid and acetic acid were provided, and the responses of array sensors to each were recorded.

The responses of each sensor were considered as target response in a response optimizer, and by an overall composite desirability, the concentration of each analyte was predicted. The present work suggests the applicability of the response surface regression analysis as a modeling technique for correlating the responses of sensor arrays to concentration profiles of diacetyl, lactic acid and acetic acid in food samples.

The PPy–ZnO and PPy–V₂O₅ nanocomposite fibers were synthesized by chemical polymerization. The provided conducting fibers, PPy–ZnO and PPy–V₂O₅, were used in an array gas sensor system for the analysis of volatile compounds (diacetyl, lactic acid and acetic acid) added to yogurt and milk samples.

This paper aims to study different possibilities for implementing easy-to-use and cost-effective micro-systems to detect and trace expelled gases from rotten food. The paper covers various radio-frequency identification (RFID) technologies and gas sensors as the two promoting feasibilities for the tracing of packaged food. Monitoring and maintaining quality and safety of food in transport and storage from producer to consumer are the most important concerns in food industry. Many toxin gases, even in parts per billion ranges, are produced from corrupted and rotten food and can endanger the consumers’ health. To overcome the issues, intelligent traceability of food products, specifically the packaged ones, in terms of temperature, humidity, atmospheric conditions, etc., has been paid attention to by many researchers.

Food poisoning is a serious problem that affects thousands of people every year. Poisoning food must be recognized early to prevent a serious health problem.

Contaminated food is usually detectable by odor. A small gas sensors and low-cost tailored to the type of food packaging and a communication device for transmitting alarm output to the consumer are key factors in achieving intelligent packaging.

Conducting polymer composite, intrinsically conducting polymer and metal oxide conductivity gas sensors, metal–oxide–semiconductor field-effect transistor (MOSFET) gas sensors offer excellent discrimination and lead the way for a new generation of “smart sensors” which will mould the future commercial markets for gas sensors.

Small size, low power consumption, short response time, wide operating temperature, high efficiency and small area are most important features of introduced system for using in package food.

The electronic nose is an array of chemical or gas sensors and associated with a pattern-recognition framework competent in identifying and classifying odorant or non-odorant and simple or complex gases. Despite more than 30 years of research, the robust e-nose device is still limited. Most of the challenges towards reliable e-nose devices are associated with the non-stationary environment and non-stationary sensor behaviour. Data distribution of sensor array response evolves with time, referred to as non-stationarity. The purpose of this paper is to provide a comprehensive introduction to challenges related to non-stationarity in e-nose design and to review the existing literature from an application, system and algorithm perspective to provide an integrated and practical view.

The authors discuss the non-stationary data in general and the challenges related to the non-stationarity environment in e-nose design or non-stationary sensor behaviour. The challenges are categorised and discussed with the perspective of learning with data obtained from the sensor systems. Later, the e-nose technology is reviewed with the system, application and algorithmic point of view to discuss the current status.

The discussed challenges in e-nose design will be beneficial for researchers, as well as practitioners as it presents a comprehensive view on multiple aspects of non-stationary learning, system, algorithms and applications for e-nose. The paper presents a review of the pattern-recognition techniques, public data sets that are commonly referred to as olfactory research. Generic techniques for learning in the non-stationary environment are also presented. The authors discuss the future direction of research and major open problems related to handling non-stationarity in e-nose design.

The authors first time review the existing literature related to learning with e-nose in a non-stationary environment and existing generic pattern-recognition algorithms for learning in the non-stationary environment to bridge the gap between these two. The authors also present details of publicly available sensor array data sets, which will benefit the upcoming researchers in this field. The authors further emphasise several open problems and future directions, which should be considered to provide efficient solutions that can handle non-stationarity to make e-nose the next everyday device.

The purpose of this paper is to design and validate an electronic nose (E-nose) prototype using commercially available metal oxide gas sensors (MOX). This prototype has a sensor array board that integrates eight different MOX gas sensors to handle multi-purpose applications. The number of sensors can be adapted to match different requirements and classification cases. The paper presents the validation of this E-nose prototype when used to identify three gas samples, namely, alcohol, butane and cigarette smoke. At the same time, it discusses the discriminative abilities of the prototype for the identification of alcohol, acetone and a mixture of them. In this respect, the selection of the appropriate type and number of gas sensors, as well as obtaining excellent discriminative abilities with a miniaturized design and minimal computation time, are all drivers for such implementation.

The suggested prototype contains two main parts: hardware (low-cost components) and software (Machine Learning). An interconnection printed circuit board, a Raspberry Pi and a sensor chamber with the sensor array board make up the first part. Eight sensors were put to the test to see how effective and feasible they were for the classification task at hand, and then the bare minimum of sensors was chosen. The second part consists of machine learning algorithms designed to ensure data acquisition and processing. These algorithms include feature extraction, dimensionality reduction and classification. To perform the classification task, two features taken from the sensors’ transient response were used.

Results reveal that the system presents high discriminative ability. The K-nearest neighbor (KNN) and support vector machine radial basis function based (SVM-RBF) classifiers both achieved 97.81% and 98.44% mean accuracy, respectively. These results were obtained after data dimensionality reduction using linear discriminant analysis, which is more effective in terms of discrimination power than principal component analysis. A repeated stratified K-cross validation was used to train and test five different machine learning classifiers. The classifiers were each tested on sets of data to determine their accuracy. The SVM-RBF model had high, stable and consistent accuracy over many repeats and different data splits. The total execution time for detection and identification is about 10 s.

Using information extracted from transient response of the sensors, the system proved to be able to accurately classify the gas types only in three out of the eight MQ-X gas sensors. The training and validation results of the SVM-RBF classifier show a good bias-variance trade-off. This proves that the two transient features are sufficiently efficient for this classification purpose. Moreover, all data processing tasks are performed by the Raspberry Pi, which shows real-time data processing with miniaturized architecture and low prices.

This paper reviews the range of sensors used in electronic nose (e‐nose) systems to date. It outlines the operating principles and fabrication methods of each sensor type as well as the applications in which the different sensors have been utilised. It also outlines the advantages and disadvantages of each sensor for application in a cost‐effective low‐power handheld e‐nose system.

The purpose of this paper is to deal with the classification improvement of pollutant using WO3 gases sensors. To evaluate the discrimination capacity, some experiments were achieved using three gases: ozone, ethanol, acetone and a mixture of ozone and ethanol via four WO3 sensors.

To improve the classification accuracy and enhance selectivity, some combined features that were configured through the principal component analysis were used. First, evaluate the discrimination capacity; some experiments were performed using three gases: ozone, ethanol, acetone and a mixture of ozone and ethanol, via four WO3 sensors. To this end, three features that are derivate, integral and the time corresponding to the peak derivate have been extracted from each transient sensor response according to four WO3 gas sensors used. Then these extracted parameters were used in a combined array.

The results show that the proposed feature extraction method could extract robust information. The Extreme Learning Machine (ELM) was used to identify the studied gases. In addition, ELM was compared with the Support Vector Machine (SVM). The experimental results prove the superiority of the combined features method in our E-nose application, as this method achieves the highest classification rate of 90% using the ELM and 93.03% using the SVM based on Radial Basis Kernel Function SVM-RBF.

Combined features have been configured from transient response to improve the classification accuracy. The achieved results show that the proposed feature extraction method could extract robust information. The ELM and SVM were used to identify the studied gases.

Amperometric gas sensors are commonly used in air quality monitoring in long-term measurements. Baseline shift of sensor responses and power failure may occur over time, which is an obstacle for reliable operation of the entire system. The purpose of this study is to check the possibility of using PCA method to detect defected samples, identify faulty sensor and correct the responses of the sensor identified as faulty.

In this work, the authors present the results obtained with six amperometric sensors. An array of sensors was exposed to sulfur dioxide at the following concentrations: 0 ppm (synthetic air), 50 ppb, 100 ppb, 250 ppb, 500 ppb and 1000 ppb. The damage simulation consisted in adding to the sensor response a value of 0.05 and 0.1 µA and replacing the responses of one of sensors with a constant value of 0 and 0.15 µA. Sensor validity index was used to identify a damaged sensor in the matrix, and its responses were corrected via iteration method.

The results show that the methods used in this work can be potentially applied to detect faulty sensor responses. In the case of simulation of damage by baseline shift, it was possible to achieve 100% accuracy in damage detection and identification of the damaged sensor. The method was not very successful in simulating faults by replacing the sensor response with a value of 0 µA, due to the fact that the sensors mostly gave responses close to 0 µA, as long as they did not detect SO₂ concentrations below 250 ppb and the failure was treated as a correct response.

This work was inspired by methods of simulating the most common failures that occurs in amperometric gas sensors. For this purpose, simulations of the baseline shift and faults related to a power failure or a decrease in sensitivity were performed.

Atmospheric dependent, gas sensitive resistors seem to be good candidates for detecting critical air pollution levels. Recently, great progress has been made in the development of various sensor types, but less attention seems to be paid to the integration of sensor elements with different characteristics. The aim of this international project is to develop a smart hybrid gas multi‐sensor module for environmental applications, i.e. by combining classical thick‐ and thin‐film elements with polymer‐film based sensors and also a signal processing ASIC within a single package, which should be useful for all sensor types. The module should enable multi‐sensor operation as well, when connected to an intelligent signal‐processing unit.

The purpose of this paper is to improve the performance of E-nose in the detection of wound infection. Feature extraction and selection methods have a strong impact on the performance of pattern classification of electronic nose (E-nose). A new hybrid feature matrix construction method and multi-objective binary quantum-behaved particle swarm optimization (BQPSO) have been proposed for feature extraction and selection of sensor array.

A hybrid feature matrix constructed by maximum value and wavelet coefficients is proposed to realize feature extraction. Multi-objective BQPSO whose fitness function contains classification accuracy and a number of selected sensors is used for feature selection. Quantum-behaved particle swarm optimization (QPSO) is used for synchronization optimization of selected features and parameter of classifier. Radical basis function (RBF) network is used for classification.

E-nose obtains the highest classification accuracy when the maximum value and db 5 wavelet coefficients are extracted as the hybrid features and only six sensors are selected for classification. All results make it clear that the proposed method is an ideal feature extraction and selection method of E-nose in the detection of wound infection.

The innovative concept improves the performance of E-nose in wound monitoring, and is beneficial for realizing the clinical application of E-nose.