Journal of Sensor Science and Technology (센서학회지)

The Korean Sensors Society (한국센서학회)
권호 표지
DOI QR코드

DOI QR Code

Signal Processing Techniques Based on Adaptive Radial Basis Function Networks for Chemical Sensor Arrays

  • Byun, Hyung-Gi (Division of Electronics, Information&Communication Engineering, Kangwon National University)
  • Received : 2016.05.19
  • Accepted : 2016.05.28
  • Published : 2016.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

The use of a chemical sensor array can help discriminate between chemicals when comparing one sample with another. The ability to classify pattern characteristics from relatively small pieces of information has led to growing interest in methods of sensor recognition. A variety of pattern recognition algorithms, including the adaptive radial basis function network (RBFN), may be applicable to gas and/ or odor classification. In this paper, we provide a broad review of approaches for various types of gas and/or odor identification techniques based on RBFN and drift compensation techniques caused by sensor poisoning and aging.

Keywords

References

  1. J. Moody and C. Darken, "Fast learning in networks of locally-tuned processing units", Neural computation, Vol. 1, pp. 281-294, 1989. https://doi.org/10.1162/neco.1989.1.2.281
  2. M. Musavi, W. Ahmed, K. Chan, K. Faris, and D. Hummels, "On the training of radial basis function classifiers", Neural Networks, Vol. 5, pp. 595-603, 1992. https://doi.org/10.1016/S0893-6080(05)80038-3
  3. T. Kohonen, "Self-Organization and Associative Memory", Springer-Verlag, 3rd ed., pp. 199-202, 1989.
  4. K. C. Persaud and H-G. Byun, "Classification of complex odours using conducting polymer arrays and neural networks", Industrial applications of neural networks, Eds. Fogelman Soulie, World Scientific, Singapore, New Jersey, pp. 85-90, 1998.
  5. D-H. Lee, J. S. Payne, H-G. Byun, and K. C. Persaud, "Application of radial basis neural networks to odour sensing using a broad specificity array of conducting polymers", Lecture Notes in Computer Science (Eds. C. Von der Malsburg, W. von Seelen, J. C. Vorbroggen, B. Sendhoff), Vol. 1112, pp. 299-304, 1996.
  6. H. Byun, N. Kim, K. Persaud, J. Huh, and D. Lee, "Application of adaptive RBF networks to odor classification using conducting polymer sensor array", Proceedings of ISOEN'2000, Washington D.C., U.S.A., Brighton, pp. 121-126, 2000.
  7. H. Byun, N. Kim, K. Persaud, J. Huh, and D. Lee, "Application of adaptive RBF network for odour classification under drift effect using conducting polymer sensor array", Proceedings of Electrochemical Society, pp. 176-180, 2001.
  8. I. Cha, and S. Kassam, "Interference cancellation using radial basis function networks", Signal Processing, Vol. 47, pp. 247-268, 1995. https://doi.org/10.1016/0165-1684(95)00113-1
  9. K. Kwon, N. Kim, H. Byun, and K. Persaud, "On training neural network algorithms for odor identification for future multimedia communication systems", Proceedings of 2006 IEEE International Conference on Multimedia, pp. 1309-1312, 2006.
  10. N. Kim, H. Byun, and K. Persaud, "Normalization approach to the stochastic gradient radial basis function network algorithm for odor sensing systems", Sensors and Actuators B, pp. 407-412, 2007.
  11. P Pelosi and K. Persaud, "Toward an artificial nose", Sensors and Sensory Systems for Advanced Robots, NATO ASI Series, Vol. F43, pp. 49-70, 1998.
  12. J. W. Gardner et al., Electronic Noses Principles and Applications, Oxford University Press, 1999.
  13. M. Zuppa et al., "Drift counteraction with multiple selforganising maps for an electronic nose", Sensors and Actuators B, pp. 305-317, 2004.
  14. N. Kim, H. Byun, K. Persaud, and J. Huh, "Sensor drift compensation algorithm based on PDF distance minimization", Proceedings of ISOEN 2009, Vol. 1137, pp. 554-557, 2009.
  15. J. Principe, D. Xu, and J. Fisher, "Information Theoretic Learning"' in: S. Haykin, Unsupervised Adaptive Filtering, New York, Wiley, pp. 265-319, 2000.
  16. D. Erdogmus and J. Principe, "An Entropy minimization algorithm for supervised training of nonlinear systems", IEEE Trans. Signal Processing, Vol. 50, pp. 1780-1786, 2002. https://doi.org/10.1109/TSP.2002.1011217
  17. D. Erdogmus, Y. Rao, and J. Principe, "Supervised training of adaptive systems with partially labeled data", Proceedings of the International Conference on ASSP, pp. v321-v324, 2005.
  18. K. Jeong, J. Xu, D. Erdogmus, and J. Principe, "A new classifier based on information theoretic learning with unlabeled data", Neural Networks, Vol. 18, pp. 719-726, 2005. https://doi.org/10.1016/j.neunet.2005.06.018
  19. N. Kim, H. Byun, and K. Persaud, "Novel signal processing techniques based on PDF information for sensor-drift compensation", Sensor Letters, Vol. 9, No. 1, pp. 439-443, 2011. https://doi.org/10.1166/sl.2011.1495
  20. N. Kim, H. Byun, K. Kwon, K. Persaud, and O.J. Lim, "Unsupervised adjustment of centers in RBF networks for sensor drift compensation", Proceedings of IMCS 2012, pp. 1802-1804, 2012.
  21. I. Santamaria, P. Pokharel, and J. Principe, "Generalized correlation function: Definition, properties, and application to blind equalization", IEEE Trans. Signal Processing, Vol. 54, pp. 2187-2197, 2006. https://doi.org/10.1109/TSP.2006.872524
  22. N. Kim, H. Byun, and K. Persaud, "A new compensation method for sensor-drift effect based on the cross-correntropy concept", Sensor Letters, Vol. 9, No. 2, pp. 710-713, 2011. https://doi.org/10.1166/sl.2011.1598
  23. V. Vapnik, The Nature of Statistical Learning Theory, New York, Springer Verlag, 1995.
  24. W. Liu, P. Pokharel, and J. Principe, "Correntropy: Properties and applications in non-Gaussian signal processing", IEEE Trans. on Signal Processing, Vol. 55, No. 6, pp. 2187-2198, 2007.