Independent Component Analysis of Multiple-Component Gaseous Photoacoustic Spectroscopy to Determine Feature Absorption

Abstract:

A blind source separation model out of statistical information principle is applied to “decode” multi-gas photoacoustic spectroscopy from mixing signal into a couple of single independent component based on samples from a given detection experiment and A FastICA algorithm with used in the mode is introduced to separate the spectroscopy of low molecule mass by a feature extraction or to track that of higher-mass volatile molecule by a pattern recognition, such as acetone or its similar-species molecules. The research has exhibited its glamour by successfully extracting ammonia feature absorption in the real-time detection of breath ammonia in vivo.

• Periodical: Advanced Materials Research (Volumes 518-523)
• Pages: 1544-1551
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.518-523.1544
• Online since: May 2012
• Authors: Zhi Ying Wu, Nan Nan Gai
• Keywords: Feature Absorption, Gas Photoacoustic Spectroscopy Detection, Independent Component Analysis (ICA)

References

[1] Wang Zhang, Zhiying Wu, Qingxu Yu: Photoacoustic spectroscopy for fast and sensitive ammonia detection. Chin. Opt. Lett, 2007, 5(11): p.677～679.

[2] Zhang, W., Li, L., Yu, Q. : Breath ammonia detection based on tunable fiber laser photoacoustic spectroscopy. Applied Physics B Vol.103(2011), pp.263-269.

DOI: 10.1007/s00340-011-4550-z

[3] L. Zhang, J. Mei: Shaping up simple cell's receptive field of animal vision by ICA and its application in navigation system. Neural Networks 2003, vol. 16, issues 5-6, p.609–615.

DOI: 10.1016/s0893-6080(03)00133-3

[4] Pulkkinen J, Häkkinen AM, Lundbom N, Paetau A, Kauppinen RA, Hiltunen Y: spectroscopic imaging data of human brain tumours. in European Journal of Radiology, 2005, vol. 56, issue 2, pp.160-164.

DOI: 10.1016/j.ejrad.2005.03.018

[5] A. D. Back and A. S. Weigend: A first application of independent component analysis to extracting structure from stock returns. Int. J. on Neural Systems ,1997 , vol. 8, issue 4, p.473–484.

DOI: 10.1142/s0129065797000458

[6] V. D. Calhoun, T. Adali, G. D. Pearlson, P. C. M. van Zijl, and J. J.Pekar: Independent component analysis of fMRI data in the complex domain. in Magnetic Resonance in Medicine, 2002, vol. 48, pp.180-192.

DOI: 10.1002/mrm.10202

[7] T. Ristaniemi, and J. Joutsensalo: On the performance of blind source separation in CDMA downlink. in Proc. Int. Workshop on Independent Component Analysis and Signal Separation (ICA'99), Aussois, France,1999, p.437–441.

DOI: 10.1109/glocom.1999.831657

[8] M. Heikkinen, A. Sarpola, H. Hellman, J. Rämö, and Y. Hiltunen: Independent Component Analysis to Mass Spectra of Aluminium Sulphate. World Academy of Science, Engineering and Technology, Vol.26, 2007, pp.173-177.

[9] over and Thomas, 1991; Papoulis, 1991: Entropy, Relative Entropy and Mutual Information. Print ISBN 0-471-06259-6 Online ISBN 0-471-20061-1).

[10] Aapo Hyvärinen and Erkki Oja: Independent Component Analysis: Algorithms and Applications. Neural Networks, 2000, Vol. 13, NO.4- NO.5, pp.411-430.

DOI: 10.1016/s0893-6080(00)00026-5

[11] MILES J. WEIDA: A Brief Comparison of 2f and Broadly Swept Detection Techniques. 2007, Inc., 13029 Danielson St., Poway, CA 92064.

[12] YU Qing-xu,LI Sao-cheng,SONG Chang-lie,et al: Computer controlled laser photoacoustic spectrometer. Chinese journal of laser, 2001, 28(5), pp.451-454.

[13] J. T. C. Liu, J. B. Jeffries, and R. K. Hanson: Large-modulation-depth 2f spectroscopy with diode lasers for rapid temperature and species measurements in gases with blended and broadened spectra. Appl. Opt. 43(2004), pp.6500-6509.

DOI: 10.1364/ao.43.006500

[14] G. B. Rieker, J. B. Jeffries, and R. K. Hanson: Measurements of high-pressure CO2 absorption near 2.0 μm and implications on tunable diode laser sensor design. Appl. Phys. B 94(2009), pp.51-63.

DOI: 10.1007/s00340-008-3280-3

[15] L. I. Gurinovich, V. P. Duraev, V. A. Ivanov, N. K. Nikeenko, and G. M. Zabello: USE OF LASER DIODES IN THE CIRCUIT OF AN OPTICAL DETECTOR OF IGNITION SITES. Journal of Applied Spectroscopy, Vol.59, No. 3-4(1993), pp.677-681.

DOI: 10.1007/bf00661799

[16] J. Reid and D. Labrie: Second-harmonic detection with tunable diode lasers—comparison of experiment and theory. Appl. Phys. B 26(1981), p.203–210.

DOI: 10.1007/bf00692448

[17] S. Amari, A. Cichocki, and H.H. Yang: A new learning algorithm for blind source separation. In Advances in Neural Information Processing 8(1996), Cambridge, MA: MIT Press, pp.757-763.

[18] A. Hyvärinen and E. Oja, E: Independent Component Analysis by general non-linear Hebbian-like learning rules. Signal Processing ,vol.64(1998), p.301 – 313.

DOI: 10.1016/s0165-1684(97)00197-7

[19] A. Back and A.Weigend: First application of Independent Component Analysis to extracting structure from stock returns. Int. J. Neural Systems 8(1997), pp.473-484.

DOI: 10.1142/s0129065797000458

[20] Shaocheng Li: Research and Application on Photoacoustic Spectroscopy and Cavity Enhanced Absorption Spectroscopy Techniques. PhD thesis, Dalian University of Technology, Dalian, China CNKI:SUN:JGZZ.2001-04-004.