A portable electronic nose based on embedded PC technology and GNU/Linux: hardware, software and applications

IEEE Sensors Journal - Tập 2 Số 3 - Trang 235-246 - 2002
A. Perera1, T. Sundic1, A. Pardo1, R. Gutierrez-Osuna2, S. Marco1
1Sistemes dInstrumentacio i Communicacions, Departament dElectronica, Universitat Barcelona, Barcelona, Spain
2Department of Computer Science, Wright State University, Dayton, USA

Tóm tắt

This paper describes a portable electronic nose based on embedded PC technology. The instrument combines a small footprint with the versatility offered by embedded technology in terms of software development and digital communications services. A summary of the proposed hardware and software solutions is provided with an emphasis on data processing. Data evaluation procedures available in the instrument include automatic feature selection by means of SFFS, feature extraction with linear discriminant analysis (LDA) and principal component analysis (PCA), multi-component analysis with partial least squares (PLS) and classification through k-NN and Gaussian mixture models. In terms of instrumentation, the instrument makes use of temperature modulation to improve the selectivity of commercial metal oxide gas sensors. Field applications of the instrument, including experimental results, are also presented.

Từ khóa

#Electronic noses #Linux #Hardware #Embedded software #Application software #Instruments #Linear discriminant analysis #Principal component analysis #Programming #Digital communication

Tài liệu tham khảo

10.1016/S0303-2647(96)01660-7 10.1109/19.728841 10.1016/S0003-2670(98)00739-9 10.1109/34.574797 10.1016/S0167-8655(99)00083-5 10.1109/4235.850656 pardo, 2000, methods for sensors selection in pattern regognition, Proc ISOEN, 83 titterington, 1985, Statistical Analysis of Finite Mixture Distributions mclachlan, 1988, Mixture Models Inference and Applications to Clustering dempster, 1977, maximum likelihood from incomplete data via em algorithm, J Roy Statist Soc B, 39, 1 10.1016/S0098-1354(00)00527-5 perera, 0, ipnose: a portable electronic nose nose based on embedded technology for intensive computation and time dependent signal processing, Int Symp Electron Noses (ISOEN2001) abs 1082 10.1016/S0169-7439(02)00069-2 0 marco, 2001, opportunities for smart noses: what signal processing can do for you?, Proceedings EURODEUR 10.1016/0925-4005(92)80213-H jain, 1987, dimensionality and sample size considerations in pattern recognition practice, Handbook of Statistics, 2, 835, 10.1016/S0169-7161(82)02042-2 10.1016/S0925-4005(99)00249-X orfanidis, 1996, Introduction to Signal Processing gardner, 1999, Electronic Noses Principles and Applications haiking, 1991, Adaptive Filter Theory 10.1021/ar970064n 10.1111/1467-9868.00095 10.1109/ICPR.2000.906151 bishop, 1999, Neural Networks for Pattern Recognition friedman, 1996, building classifiers using bayesian networks, Proc Nat Conf Artif Intell, 1277 10.1214/aos/1176346060 wold, 1975, soft modeling by latent variables: the nonlinear iterative partial least squares approach, Perspectives in Probability and Statistics 10.2307/2283149