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

Abstract

Abstract-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 -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.

Gas Sensing Supported by Pattern Recognition

“…The features were selected by means of filter approach. The employed search strategy was based on the plus-L minus-R selection algorithm (LRS) [7,8], with the independent component analysis (ICA) as a dimensionality reduction technique [9]. In our software the JADE implementation of the ICA algorithm was used [10].…”

Multivariate Analysis in Gas Sensing Applications

“…The reduction was performed using the feature subset selection (FSS) method based on filter approach. The employed search strategy was based on plus-l minus-r selection (LRS) [10], with independent component analysis (ICA) [11] as a dimensionality reduction tech- Fig. 1.…”

Additional thermodynamic feature extraction from chemoresistive carbon black-polymer composite sensors by temperature modulation

“…6 shows a PCA plot calculated from only the chemoresistive sensor responses given in Table 1, corresponding to the case of γ = 0 in Eq. (6). It is represented by the two most important principal coordinates, PC1 and PC2, with the variances of 81.4% and 12.5%, respectively.…”

“…By the advancement in microelectronic devices and microfabrication technologies, a small and intelligent E-Nose system could become a promising digital component, possibly integrating into personal mobile phones as the digital cameras have done. Several studies had been performed to achieve the personalized E-Nose system [4][5][6][7][8][9]. They mainly focused on fabricating an array of chemical sensors with the requirements of small size, low-power consumption, and sufficiently sensitive, selective sensing ability.…”