A Parametric Study of Humann in Relation to the Noise: Application for the Identification of Compounds of Environmental Interest

In this paper we present a parametric study of a hierarchical unsupervised modular adaptive neural network (HUMANN), in dealing with noise. HUMANN is a biologically plausible feedforward neural architecture which has the capacity for working in domains with noise and overlapping classes, with no priori information of the number of different classes in the data, with highly non-linear boundary class and with high dimensionality data vectors. It is appropriate for classification processes performing blind clustering. The study has been accomplished round the two most noise-dependent HUMANN parameters, λ and ρ, using synthesized databases (sinusoidal signals with Gaussian noise). We show that HUMANN is highly resistant to noise, improving the performance of different neural architectures such as ART2 and DIGNET. We also present the application of HUMANN for the identification of pollutants in the environment. Specifically it has been tested with Polychlorinated dibenzofurans (PCDFs), some of the most hazardous pollutants of the environment.

[1]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[2]  F. Nottebohm,et al.  Targeted Neuronal Death Affects Neuronal Replacement and Vocal Behavior in Adult Songbirds , 2000, Neuron.

[3]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[4]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[5]  Manuel Rodrı́guez,et al.  Unsupervised classification of neural spikes with a hybrid multilayer artificial neural network , 1998, Journal of Neuroscience Methods.

[6]  Mohamad T. Musavi,et al.  On the training of radial basis function classifiers , 1992, Neural Networks.

[7]  H. Atwood,et al.  Silent synapses in neural plasticity: current evidence. , 1999, Learning & memory.

[8]  Junying Yuan,et al.  Apoptosis in the nervous system , 2000, Nature.

[9]  S. Grossberg,et al.  ART 2: self-organization of stable category recognition codes for analog input patterns. , 1987, Applied optics.

[10]  S. Cabaniss.  Theory of variable-angle synchronous fluorescence spectra , 1991 .

[11]  I. Evett,et al.  Prediction of peak wavelengths and intensities in synchronously excited fluorescence emission spectra , 1977 .

[12]  Chin-Der Wann,et al.  A Comparative Study of Self-organizing Clustering Algorithms Dignet and ART2 , 1997, Neural Networks.

[13]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[14]  J. Makhoul,et al.  Vector quantization in speech coding , 1985, Proceedings of the IEEE.

[15]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[16]  C. P. S. Araujo,et al.  SPECTROFLUORIMETRIC IDENTIFICATION OF POLYCHLORINATED BIPHENYLS USING AN UNSUPERVISED MODULAR ARTIFICIAL NEURAL NETWORK , 1999 .

[17]  Stelios C. A. Thomopoulos,et al.  Dignet: an unsupervised-learning clustering algorithm for clustering and data fusion , 1995 .