Gas Mixture Recognition Method with New Hybrid Architecture

Abstract:

The quantification accuracy of the gas mixture recognizing is greatly dependent on the gas sensor array signal processing method. The paper reports the new hybrid architecture with two main stages for gas mixture recognition. The first stage combine the principal component analysis (PCA) and back propagation neural network (BPNN) to qualitative identify the gas mixture, and the second stage composed of the independent component analysis (ICA) and BP sub networks to quantify the gas concentrations. The hybrid architecture and three other commonly used methods of PCA+BPNN, ICA+BPNN, and ICA+BP sub networks were respectively applied in binary gas mixture quantification based on the same gas sensor array, and results show that the hybrid architecture has the lowest quantitative recognition errors and fast converge speed comparing with the other methods.

• Periodical: Applied Mechanics and Materials (Volumes 40-41)
• Pages: 604-609
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.40-41.604
• Online since: November 2010
• Authors: Shuang Yan Zhang, Jun Yu, Guang Fen Wei, Zhen An Tang, Yi Chen, Yuan Hui Cui
• Keywords: BP Neural Network (BPNN), Gas Mixture Recognition, Gas Sensor Array, Independent Component Analysis (ICA), Principal Component Analysis (PCA)

References

[1] Krishna Persaud and George Dodd; Journal of Nature Vol. 299 (1982), pp.352-354.

[2] J.W. Gardner and P.N. Bartlett; Journal of Sensor Actuators B Vol. 18 (1994), pp.211-220.

[3] H. Troy Nagle1, Susan S. Schiffman and Ricardo Gutierrez Osuna1; Journal of Spectrum IEEE Vol. 35 (1998) pp.22-34.

[4] S. Ampuero and J. O. Bosset; Journal of Sensors and Actuators B: Chemical Vol. 94 (2003), pp.1-12.

[5] Lin-nan Yang, Lin Peng, Li-min Zhang, Li-lian Zhang and Shi-sheng Yang; Journal of Computers and Electronics in Agriculture Vol. 68 (2009), pp.200-206.

[6] A.K. Jain, R.P.W. Duin and J. Mao; Journal of IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 22(2000), pp.4-37.

[7] Gutierrez-Osuna, R; Journal of IEEE sensors Vol. 2(2002), pp.189-202.

[8] Aapo Hyvarinen and Erkki Oja; Journal of Neural Networks Vol. 13 (2000), pp.411-430.

[9] Aapo Hyvarinen; Journal of Neural Computing Surveys Vol. 2 (1999), pp.94-128.

[10] Karhunen J; Journal of IEEE Trans Neural Network Vol. 8 (1997), pp.486-504.

[11] S. Balasubramanian, S. Panigrahi, C.M. Logue, C. Doetkott, M. Marchello and J.S. Sherwood; Journal of Food Control Vol. 19 (2008), pp.236-246.

DOI: 10.1016/j.foodcont.2007.03.007

[12] He Xiaochuan, Wei Shoushui and Wang Ruiqing; 2nd International Conference on Bioinformatics and Biomedical Engineering (ICBBE 08), Inst. of Elec. and Elec. Eng. Computer Society Press (2008), pp.490-493.

[13] S.M. Moore, J.W. Gardner and E.L. Hines; Journal of Sensors and Actuators B Vol. 15 (1993), pp.344-348.

[14] Xiu-Kun Wang and Xiao-Feng Zhang; Journal of Computer Science Vol. 28 (2001), pp.61-63.

[15] R. Martín Negri and S. Reich; Journal of Sensor Actuators B: Chem Vol. 75 (2001), pp.172-178.

[16] J Yu, ZA Tang, GZ Yan, P.C.H. Chan and Z.X. Huang; Journal of Sensor Actuators B Vol. 139 (2009), pp.346-352.

[17] Hyva¨rinen; Journal of IEEE Transactions on Neural Networks Vol. 10 (1999), pp.626-634.