Bacteria classification using Cyranose 320 electronic nose

The electronic nose (e-nose) is an instrument that has been developed as a simplified model of the human olfactory system. Cyranose 320, a portable electronic nose, comprises an array of thirty two polymer carbon black composite sensors. In this study, it has been used to identify of four bacteria species (E. coli, S. aureus, P. aeruginosa, S. pneumoniae). The objective of this analysis was to establish simple classes for the different bacteria species in order to examine whether or not the data clusters could be separated in preparation for the pattern recognition stage. Principal component analysis (PCA) is an effective linear method for discriminating between the e-nose responses to simple and complex odours. Three of the bacteria species were classified successively using PCA. Then multi layer perceptron (MLP) was used to classify these groups.

IEEE Sensors Journal, 2002

The Cyranose 320 (Cyrano Sciences Inc., USA), comprising an array of 32 polymer carbon black composite sensors, has been used to identify species of bacteria commonly associated with medical conditions. Results from two experiments are presented, one on bacteria causing eye infections and one on a new series of tests on bacteria responsible for some ear, nose, and throat (ENT) diseases. For the eye bacteria tests, pure lab cultures were used and the electronic nose (EN) was used to sample the headspace of sterile glass vials containing a fixed volume of bacteria in suspension. For the ENT bacteria, the system was taken a step closer toward medical application, as readings were taken from the headspace of the same blood agar plates used to culture real samples collected from patients. After preprocessing, principal component analysis (PCA) was used as an exploratory technique to investigate the clustering of vectors in multi-sensor space. Artificial neural networks (ANNs) were then used as predictors, multilayer perceptron (MLP) trained with back-propagation (BP) and with Levenberg-Marquardt was used to identify the different bacteria. The optimal MLP was found to correctly classify 97.3% of the six eye bacteria of interest and 97.6% of the four ENT bacteria including two sub-species. A radial basis function (RBF) network was able to discriminate between the six eye bacteria species, even in the lowest state of concentration, with 92.8% accuracy. These results show the potential application of the Cyranose together with neural network-based predictors, for rapid screening and early detection of bacteria associated with these medical conditions, and the possible development of this EN system as a near-patient tool in primary medical healthcare.

Journal of Food Process Engineering, 2019

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 oxide semiconductor sensors produced different distinctive response signals for each bacterial and could differentiate Escherichia coli, Escherichia coli O157: H7, Listeria monocytogenes, Salmonella enteritidis, and Salmonella Typhimurium. PSO-SVM algorithm can be efficiently used in bacterial discrimination at the species and strain level by electronic nose and has the good ability both in learning and in generalization. Practical Applications Existing microbial methods depend on traditional culture-based methods which are time-wise lengthy, require trained and qualified personnel, and are not suitable as point-of-use (POU) sensing devices. The application of electronic nose for the detection and classification of bacterial foodborne pathogens have shown great promise and proven to be effective with increasing sensitivity and selectivity as compared to traditional methods. The ability for E-nose to discriminate between individual bacteria colonies at both species and strain level is of great public health importance since most bacteria have many strains. Virulence and pathogenicity are often associated with only a subset of these strains and it is essential for a method to be able to differentiate between pathogenic and nonpathogenic strains during a foodborne outbreak.

Journal of Telecommunication, Electronic and Computer Engineering, 2017

Electronic nose (E-nose) known as gas sensor array is a device that analyze the odor measurement give the fast response and less time consuming for clinical diagnosis. Many bacterial pathogens could lead to life threatening infections. Accurate and rapid diagnosis is crucial for the successful management of these infections disease. The conventional method need more time to detect the growth of bacterial. Alternatively, the bacteria are Pseudomonas aeruginosa and Shigella cultured on different media agar can be detected and classifies according to the volatile compound in shorter time using electronic nose (E-nose). Then, the data from electronic nose (E-nose) is processed using statistical method which is principal component analysis (PCA). The study shows the capability of electronic nose (E-nose) for early screening for bacterial infection in human stomach.

Sensors and Actuators B: Chemical, 2005

An electronic nose (e-nose), the Cyrano Sciences' Cyranose 320 (C-320), comprising an array of 32 polymer carbon black composite sensors has been used to identify two species of Staphylococcus aureus bacteria, namely methicillin-resistant S. aureus (MRSA) and methicillinsusceptible S. aureus (MSSA) responsible for ear nose and throat (ENT) infections when present in standard agar solution in the hospital environment. C-320 e-nose has also been used to identify coagulase-negative staphylococci (C-NS) in the hospital environment. Swab samples were collected from the infected areas of the ENT patients' ear, nose and throat regions. Gathered data were a very complex mixture of different chemical compounds. An innovative object-oriented data clustering approach was investigated for these groups of S. aureus data by combining the principal component analysis (PCA) based three-dimensional scatter plot, Fuzzy C Means (FCM) and self-organizing map (SOM) network. Using these three data clustering algorithms simultaneously better 'classification' of three bacteria subclasses were represented. Then three supervised classifiers, namely multi-layer perceptron (MLP), probabilistic neural network (PNN) and radial basis function network (RBF), were used to classify the three classes. A comparative evaluation of the classifiers was conducted for this application. The best results suggest that we are able to identify three bacteria subclasses with up to 99.69% accuracy with the application of the RBF network along with C-320. This type of bacteria data analysis and feature extraction is very difficult. But we can conclude that this preliminary study proves that e-nose based approach can provide very strong solution for identifying S. aureus infections in hospital environment and early detection.

Computer Methods and Programs in Biomedicine, 2005

This paper demonstrates the application of chemical headspace analysis to the problem of classifying the presence of bacteria in biomedical samples by using computational tools. Blood and urine samples of disparate forms were analysed using a Cyrano Sciences C320 electronic nose together with an Agilent 4440 Chemosensor. The high dimensional data sets resulting from these devices present computational problems for parameter estimation of discriminant models. A variety of data reduction and pattern recognition techniques were employed in an attempt to optimise the classification process. A 100% successful classification rate for the blood data from the Agilent 4440 was achieved by combining a Sammon mapping with a radial basis function neural network. In comparison a successful classification rate of 80% was achieved for the urine data from the C320 which were analysed using a novel nonlinear time series model.

1998

Data evaluation and classification have been made on measurements by an electronic nose on the headspace of samples of different types of bacteria growing on petri dishes. The chosen groups were: Escherichia coli, Enterococcus sp., Proteus mirabilis, Pseudomonas aeruginosa, and Staphylococcus saprophytica. An approximation of the response curve by time was made and the parameters in the curve fit were taken as important features of the data set. A classification tree was used to extract the most important features. These features were then used in an artificial neural network for classification. Using the 'leave-one-out' method for validating the model, a classification rate of 76% was obtained.

Sensors and Actuators B …, 1997

The detection and simultaneous identification of a range of microorganisms by measuring the volatile compounds produced from plate cultures has been carried out using an electronic nose and a neural network classifier. Headspace samples were taken from ...

Applied Mechanics and Materials, 2013

Array based gas sensor technology namely Electronic Nose (E-nose) now offers the potential of a rapid and robust analytical approach to odor measurement for medical use. Wounds become infected when a microorganism which is bacteria from the environment or patients body enters the open wound and multiply. The conventional method consumes more time to detect the bacteria growth. However, by using this E-Nose, the bacteria can be detected and classified according to their volatile organic compound (VOC) in shorter time. Readings were taken from headspace of samples by manually introducing the portable e-nose system into a special container that containing a volume of bacteria in suspension. The data will be processed by using statistical analysis which is Principle Component Analysis (PCA) and Linear Discriminant Analysis (LDA) methods. The most common bacteria in diabetic foot are Staphylococcus aureus, Escherchia coli, Pseudomonas aeruginosa, and many more.