ICTACT Journal on Soft Computing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Four-Layer Spherical Self-Organized Maps Neural Networks Trained by Recirculation to Simulate Perception and Abstraction Activity-Application to Patterns of Rainfall Global Reanalysis


Affiliations
1 Group of Mechanical Vibrations, National Technological University - Delta Regional Faculty, Argentina
     

   Subscribe/Renew Journal


This work is intended to organize a big set of time series. To do that a self-organized map is implemented in four spherical layers trained by recirculation. This way tries to simulate aspects of perception and abstraction. The methodology and the fundamentals are described. About the fundamentals, both from the problem point of view and the neural aspects as brain functioning, perception and abstraction concepts, psycho genetics and grouping ideas, and from the architecture of the network, scheme of training, spherical layers of the maps and algorithms involved in the iterative training. Then, it is used to organize a big set of time series of rainfall reanalysis on grid point around the Earth to show how it functions. After removing the average from the series, the annual cycle in shape and amplitude is the main criterion for organization. It is shown how the successive layers contain more general abstractions, their representativeness around the Globe and in regional scale. It is compared with individual series in some points of grid. A possible change of behaviour is found in global scale around 1973 and with a variant in the methodology a possible change in the annual cycle the same year.

Keywords

Neural Networks, Spherical Self-Organized Maps, Recirculation, Perception, Abstraction, Psycho Genetics, Rainfall Reanalysis, Climate Variability.
Subscription Login to verify subscription
User
Notifications
Font Size

  • R. Vautard and M. Ghil, “Singular Spectrum Analysis in Nonlinear Dynamics, with Applications to Paleoclimatic Time Series”, Physica D. Nonlinear Phenomena, Vol. 35, No. 3, pp. 395-424, 1989.

  • T. Kohonen, “Self Organizing Maps”, 3rd Edition, Springer, 2001.

  • Bonifacio Martin Del Brio and Alfredo Sanz Molina, “Neural Networks and Blurred Systems”, 3rd Edition, Ra-Ma Editorial, 2006.

  • Martinez Hernando and Victor Jose, “Artificial Neural Networks: Fundamentals, Models and Applications”, Addison Wesley, 1995.

  • J.A. Freeman and D.M. Skapura, “Neural Networks Algorithms, Applications and Programming Techniques”, Addison Wesley, 1993.

  • Martin T. Hagan and Howard B. Mark, “Neural Network Design”, PWS Publishing Company, 1995.

  • James A. Anderson, “Redes Neuronales”, Alfaomega Group Editor, 2007.

  • J.P. Boulanger, F. Martinez and E.C. Segura, “Projection of Future Climate Change Conditions using IPCC Simulations, Neural Networks and Bayesian Statistics. Part 1: Temperature Mean State and Seasonal Cycle in South America”, Climate Dynamics, Vol. 27, No. 2-3, pp. 233-259, 2006.

  • J.P. Boulanger, F. Martinez and E.C. Segura, “Projection of Future Climate Change Conditions using IPCC Simulations, Neural Networks and Bayesian Statistics. Part 2: Precipitation Mean State and Seasonal Cycle in South America”, Climate Dynamics, Vol. 28, No. 2-3, pp. 255-271, 2007.

  • M.W. Gardner and S.R. Dorling, “Artificial Neural Networks (The Multilayer Perceptron) - A Review of Applications in the Atmospheric Sciences”, Atmospheric Environment, Vol. 32, No. 14-15, pp. 2627-2636, 1998.

  • I. Turiasa, M. Gonzalez and P. Galindoa, “A Competitive Neural Network Approach for Meteorological Situation Clustering”, Atmospheric Environment, Vol. 40, No. 3, pp. 532-541, 2006.

  • B.A. Malmgren and A. Winter, “Climate Zonation in Puerto Rico Based on Principal Components Analysis and an Artificial Neural Network”, Journal of Climate, Vol. 12, pp. 977-985, 1999.

  • M. Hall, A. Minns and A. Ashrafuzzaman, “The Application of Data Mining Techniques for the Regionalisation of Hydrological Variables”, Hydrology and Earth System Sciences, Vol. 6, No. 4, pp. 685-694, 2002.

  • A. Steynor and B. Hewitson, “The Use of Kohonen Self-Organising Maps in Assessing the Impact of Global Climate Change on the Runoff of the Breede River in South Africa”, Geophysical Research Abstracts, Vol. 8, pp. 429-442, 2006.

  • J. Fayos and C. Fayos, “Wind Data Mining by Kohonen Neural Networks”, PLoS ONE, Vol. 2, No. 2, pp. 1-11, 2007.

  • D. Kilpatrick and R. Williams, “Unsupervised Classification of Antarctic Satellite Imagery using Kohonen Self-Organising Feature Map”, Proceedings IEEE International Conference on Neural Networks, pp. 32-36, 1995.

  • S. Michaelides and C. Pattichis, “Classification of Rainfall Distributions with the use of Artificial Neural Networks”, Proceedings of 4th International Conference on Meteorology, Climatology and Atmospheric Physics, pp. 251-256, 1998.

  • M. Britos Cogliati and R. Garcia-Martinez, “Analysis of Agrometeorological Variables in Frost Nights using Auto Organized Maps and Induction Algorithms”, Master Thesis, Department of Agrarian and Forestry Sciences, National University of La Plata, 2006.

  • E. Kandel and T.S. Jessell, “Neuroscience and Conduct”, Prentice Hall, 1997.

  • P.A.A. Alessandro and D.A. Huggenberger, “Identification and Characterization of Blocking Situations through an Auto Organized Map of Neural Networks”, Proceedings of 15th Brazilian Congress of Meteorology, pp. 13-19, 2010.

  • Dario A. Huggenberger and Walter M. Vargas, “Evolucion De Una Oscilacion Casi Cuadrienal En La Precipitacion a Través De Un Mapa Auto Organizado De Redes Neuronales”, Acta De Trabajos Completos, pp. 217-227, 2012.

  • F. Boudjemai, P.B. Enberg and J.G. Postaire, “Self Organizing Spherical Map Architecture for 3D Object Modelling”, Proceedings of International Workshop on Self-Organizing Maps, pp. 111-117, 2003.

  • Hirokazu Nishio, Md. Altaf-Ul-Amin, Ken Kurokawa and Shigehiko Kanaya, “Spherical SOM and Arrangement of Neurons using Helix on Sphere”, IPSJ Digital Courier, Vol. 2, pp. 133-137, 2006.

  • Y. Wu and M. Takatsuka, “Fast Spherical Self Organizing Map-Use of Indexed Geodesic Data Structure”, Proceedings of Workshop on Self-Organizing Maps, pp. 5-8, 2005.

  • Y. Wu and M. Takatsuka, “Spherical Self-Organizing Map using Efficient Indexed Geodesic Data Structure”, Neural Networks, Vol. 19, No. 6, pp. 900-910, 2006.

  • F. Bacao, V. Lobo and M. Painho, “Geo-Self-Organizing Map (Geo-SOM) for Building and Exploring Homogeneous Regions”, Available at: https://pdfs.semanticscholar.org/706a/b4e6110a3765ec0cedf2f197fe79f18c217f.pdf.

  • F. Bacao, V. Lobo and M. Painho, “The self-Organizing Map, the Geo-SOM, and Relevant Variants for Geosciences”, Computers and Geosciences, Vol. 31, pp. 155-163, 2005.

  • Jorge M.L. Gorricha and Victor J.A.S. Lobo, “On the Use of Three-Dimensional Self-Organizing Maps for Visualizing Clusters in Georeferenced Data”, Proceedings of International Conference on Information Fusion and Geographic Information Systems, pp. 61-75, 2011.

  • A.P. Sangole and G.K Knopf, “Visualization or Randomly Ordered Numeric Data Sets using Spherical Self-Organizing Feature Maps”, Computer and Graphics, Vol. 27, No. 6, pp. 963-976, 2003.

  • A.P. Sangole and A. Leontitsis, “A Spherical Self-Organizing Feature Map: An Introductory Review”, International Journal of Bifurcation and Chaos, Vol. 16, No. 11, pp. 3195-3206, 2006.

  • A.P. Sangole and A. Leontitsis, “Estimating an Optimal Neighborhood Size in the Spherical Self-Organizing Feature Map”, International Journal of Computational Intelligence, Vol. 18, No. 35, pp. 192-196, 2006.

  • H. Wu, “Spherical Topology Self-Organizing Map Neuron Network for Visualization of Complex Data”, Master Thesis, Department of Computing, Australian National University, 2011.

  • G.E. Hinton and J.L. McClelland, “Learning Representation by Recirculation American Institute of Physics”, Proceedings of IEEE Conference on Neural Information Processing Systems, pp. 358-366, 1988.

  • E. Arsuaga Uriarte and F. Diaz Martin, “Topology Preservation in SOM”, World Academy of Science, Engineering and Technology, Vol. 21, No. 9, pp. 991-994, 2008.

  • E. Kalnay et al., “The NCEP/NCAR 40-Year Reanalysis Project”, American Meteorological Society, Vol. 77, pp. 437-470, 1996.


Abstract Views: 261

PDF Views: 2




  • Four-Layer Spherical Self-Organized Maps Neural Networks Trained by Recirculation to Simulate Perception and Abstraction Activity-Application to Patterns of Rainfall Global Reanalysis

Abstract Views: 261  |  PDF Views: 2

Authors

Dario Alberto Huggenberger
Group of Mechanical Vibrations, National Technological University - Delta Regional Faculty, Argentina

Abstract


This work is intended to organize a big set of time series. To do that a self-organized map is implemented in four spherical layers trained by recirculation. This way tries to simulate aspects of perception and abstraction. The methodology and the fundamentals are described. About the fundamentals, both from the problem point of view and the neural aspects as brain functioning, perception and abstraction concepts, psycho genetics and grouping ideas, and from the architecture of the network, scheme of training, spherical layers of the maps and algorithms involved in the iterative training. Then, it is used to organize a big set of time series of rainfall reanalysis on grid point around the Earth to show how it functions. After removing the average from the series, the annual cycle in shape and amplitude is the main criterion for organization. It is shown how the successive layers contain more general abstractions, their representativeness around the Globe and in regional scale. It is compared with individual series in some points of grid. A possible change of behaviour is found in global scale around 1973 and with a variant in the methodology a possible change in the annual cycle the same year.

Keywords


Neural Networks, Spherical Self-Organized Maps, Recirculation, Perception, Abstraction, Psycho Genetics, Rainfall Reanalysis, Climate Variability.

References