A Blind Source Separation Based Micro Gas Sensor Array Modeling Method

Blind Source Separation (BSS) has been a strong method to extract the unknown independent source signals from sensor measurements which are unknown combinations of the source signals. In this paper, a BSS based modeling method is proposed and analyzed for a micro gas sensor array, which is fabricated with surface micromachining technology and is applied to detect the gas mixture of CO and CH4. Two widely used BSS methods–Independent Component Analysis (ICA) and Nonlinear Principal Component Analysis (NLPCA) are applied to obtain the gas concentration signals. The analyzing results demonstrate that BSS is an efficient way to extract the components which corresponding to the gas concentration signals.

[1]  P.C.H. Chan,et al.  An integrated gas sensor technology using surface micro-machining , 2002, Technical Digest. MEMS 2001. 14th IEEE International Conference on Micro Electro Mechanical Systems (Cat. No.01CH37090).

[2]  Pietro Siciliano,et al.  Analysis of CO and CH4 gas mixtures by using a micromachined sensor array , 2001 .

[3]  Aapo Hyvärinen,et al.  A Fast Fixed-Point Algorithm for Independent Component Analysis , 1997, Neural Computation.

[4]  Bernard Chalmond,et al.  Nonlinear Modeling of Scattered Multivariate Data and Its Application to Shape Change , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Julian W. Gardner,et al.  Electronic noses: a review of signal processing techniques , 1999 .

[6]  Timothy C. Pearce,et al.  Odor to sensor space transformations in biological and artificial noses , 2000, Neurocomputing.

[7]  Christian Jutten,et al.  Source separation based processing for integrated Hall sensor arrays , 2002 .

[8]  Christian Jutten,et al.  Source separation in post-nonlinear mixtures , 1999, IEEE Trans. Signal Process..

[9]  Wolfgang Niehsen,et al.  Generalized Gaussian modeling of correlated signal sources , 1999, IEEE Trans. Signal Process..

[10]  Pascal Boilot,et al.  Electronic noses inter-comparison, data fusion and sensor selection in discrimination of standard fruit solutions , 2003 .

[11]  Eugenio Martinelli,et al.  Counteraction of environmental disturbances of electronic nose data by independent component analysis , 2002 .

[12]  E. Oja,et al.  Independent Component Analysis , 2013 .

[13]  Oliver Tomic,et al.  Independent component analysis applied on gas sensor array measurement data , 2003 .

[14]  Ada Fort,et al.  Tin oxide gas sensing: comparison among different measurement techniques for gas mixture classification , 2003, IEEE Trans. Instrum. Meas..

[15]  Jean-Francois Cardoso,et al.  Blind signal separation: statistical principles , 1998, Proc. IEEE.

[16]  Shun-ichi Amari,et al.  Adaptive blind signal processing-neural network approaches , 1998, Proc. IEEE.

[17]  Kazuo Tanaka,et al.  Modeling and control of carbon monoxide concentration using a neuro-fuzzy technique , 1995, IEEE Trans. Fuzzy Syst..

[18]  Ingemar Lundström,et al.  Gas mixture analysis using a distributed chemical sensor system , 1999 .