Detection of Organic Pollutions Using Artificial Neural Networks and Domain Transform Techniques

Abstract:

This paper presented a novel method for detection of organic pollutions based on artificial neural networks combining domain transform techniques. Domain transform techniques are mathematical methods that allow the direct mapping of information from one domain to another. The most effectively used domain transform technique is wavelet packet transform (WPT). Wavelet packet representations of signals provided a local timefrequency description and separation ability between information and noise. The quality of the noise removal can be further improved by using best-basis algorithm and thresholding operation. Artificial neural network (ANN) is a form of artificial intelligence that mathematically simulates biological nervous system. Generalized regression neural network (GRNN) is a kind of ANN and is applied for overcoming the convergence problem met in back propagation training and facilitating nonlinear calculation. In the case a method named WPT-based generalized regression neural network (WPTGRNN) was used for analyzing overlapping spectra.

• Periodical: Applied Mechanics and Materials (Volume 610)
• Pages: 279-282
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.610.279
• Online since: August 2014
• Authors: Ling Gao*, Shou Xin Ren
• Keywords: Artificial Neural Network (ANN), Detection of Organic Pollutions, Domain Transform Techniques, Generalized Regression Neural Network, Wavelet Packet Transform

References

[1] S. Ren , L. Gao, Simultaneous quantitative analysis of overlapping spectrophotometric signals using wavelet multiresolution analysis and partial least squares, Talanta, 50(6)(2000) 1163–1173.

DOI: 10.1016/s0039-9140(99)00226-x

[2] S. G. Mallat, Multiresolution approximations and wavelet orthonormal bases of L2(R), Transactions of the American Mathematical Society, 315 (1) (1989) 69–87.

DOI: 10.2307/2001373

[3] S. Ren, L. Gao, Resolve of overlapping voltammetric signals in using a wavelet packet transform based Elman recurrent neural network, Journal of Electroanalytical Chemistry, 586 (2006) 23-30.

DOI: 10.1016/j.jelechem.2005.09.018

[4] R. R. Coifmanand, M. V. Wickerhauser, Entropy-based algorithms for best basis selection, IEEE Transactions on Information Theory, 38 (2) (1992) 713–718.

DOI: 10.1109/18.119732

[5] L. Gao, S. Ren, Combining orthogonal signal correction and wavelet packet transform with radial basis function neural network for multicomponent determination, Chemometrics and Intelligent Laboratory Systems, 100 (2010) 57-65.

DOI: 10.1016/j.chemolab.2009.11.001

[6] R. Linker, Spectrum analysis by recursively pruned extended auto-associative neural network, Journal of Chemometrics, 19 (2005) 492-499.

DOI: 10.1002/cem.955

[7] D. F. Specht, Probabilistic neural networks, Neural Networks, 3 (1990) 109-118.