Advertisement

Asynchronous Synthesis of a Neural Network Applied on Head Load Prediction

  • P. VařachaEmail author
Conference paper
  • 1.2k Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 192)

Abstract

This paper introduces innovative method of an artificial neural network (ANN) optimization (synthesis) by means of Analytic Programming (AP). New asynchronous implementation of Self-Organizing Migration Algorithm (SOMA), which provides effective increase of AP computing potential, is introduced here for time as well as original strategy of communication between SOMA and AP that further contribute towards efficiency in search for optimal ANN solution. The whole ANN synthesis algorithm is applied on the real case of heating plant model identification. The heating plant is located in the town of Most, Czech Republic.

The method proves itself to be especially effective when formally identified non-neural parts of the heating plant model need to be made more accurate. Asynchronous distribution plays the key role here as the heating plant behavior data has to be acquired from a very large database and therefore learning of ANN may require a lot of computation time.

Keywords

Genetic Algorithm Artificial Neural Network Artificial Neuron Artificial Neural Network Structure Heating Plant 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Garis, H.: Genetic Programming Building Nanobrains with Genetically Programmed Neural Network Modules. In: IEEE International Joint Conference on Neural Networks, New York, vol. 3, pp. 511–516 (1990)Google Scholar
  2. Whitley, D., Starkweather, T., Bogard, C.: Genetic Algorithms and Neural Networks: Optimizing Connections and Connectivity. Parallel Computing 14, 347–361 (1990)CrossRefGoogle Scholar
  3. Montana, D.J.: Automated Parameter Tuning for Interpretation of Synthetic Images. In: Handbook of Genetic Algorithms, pp. 202–221 (1991)Google Scholar
  4. Boers, E.J.W., Kuiper, H.: Biological Metaphors and Design of Modular Artificial Neural Networks, Technical report, Department of Computer Science and Experimental and Theoretical Psychology, Leiden University, The Netherlands (1992)Google Scholar
  5. Lohmann, R.: Structure Evolution in Neural Systems, Dynamic, Genetic and Chaotic Programming, ch. 15 (1992)Google Scholar
  6. Nix, A.E., Vose, M.D.: Modelling Genetic Algorithms with Markov Chains. Annals of Mathematics and Artificial Inteligence 5, 79–88 (1992)MathSciNetzbMATHCrossRefGoogle Scholar
  7. Braun, H., Weisborod, J.: Evolving Neural Feedforward Networks. In: International Conference on Artificial Neural Nets and Genetic Algorithms (ANNGA 1993), Innsbruck, Austria, pp. 25–32 (1993)Google Scholar
  8. Dasgupta, D., McGregor, D.R.: sGA: A Structured Genetic Algorithm, Technical Report: IKBS-11-93, Department of Computer Science, University of Strathclyde, Glasgow (1993)Google Scholar
  9. McDonnell, J.R., Waagen, D.: Evolving Neural Network Connectivity. In: IEE International Conference on Neural Networks, San Francisco (1993)Google Scholar
  10. Munro, P.W.: Genetic Search for Optimal Representations in Neural Networks. In: International Conference on Artificial Neural Nets and Genetic Algorithms (ANNGA 1993), Innsbruck, Austria, pp. 628–634 (1993)Google Scholar
  11. Angelia, P.J., Saunders, G.M., Pollack, J.M.: An Evolutionary Algorithm that Constructs Recurrent Neural Networks. IEEE Transactions on Neural Networks 5 (1994)Google Scholar
  12. Gruau, F.: Genetic Microprogramming of Neural Networks. Advances in Genetic Programming. MIT Press (1994)Google Scholar
  13. Maniezzo, V.: Genetic Evolution of the Topology and Weight Distribution of Neural Networks. IEEE Transaction on Neural Networks 5 (1994)Google Scholar
  14. Prechelt, L.: Proben1—A Set of Neural Network Benchmark Problems and Benchmarking Rules. Universität Karlsruhe, Germany (1994)Google Scholar
  15. Lund, H.H., Parisi, D.: Simulations with an Evolvable Fitness Formula, Technical Report PCIA-1-94, C.N.R, Rome (1994)Google Scholar
  16. Happel, B.L.M., Murrer, J.M.J.: Deign and Evolution of Modular Neural Network Architectures. Neural Networks 7, 985–1004 (1994)CrossRefGoogle Scholar
  17. Kitano, H.: Neurogenetic Learning: An Integrated Method of Designing and Training Neural Networks Using Genetic Algorithms. Physica D 75, 225–228 (1994)zbMATHCrossRefGoogle Scholar
  18. Hassoun, M.H.: Fundamentals of Artificial Neural Networks. MIT Press (1995)Google Scholar
  19. Gurney, K.: An Introduction to Neural Networks. Routledge, London (1997)CrossRefGoogle Scholar
  20. Vonk, E., Jain, L.C., Jjohnson, R.P.: Automatic Generation of Neural Network Architecture Using Evolutionary Computation. Advances in Fuzzy Systems – Applications and Theory, vol. 14. World Science (1997)Google Scholar
  21. Koza, J.R.: Genetic Programming. MIT Press (1998)Google Scholar
  22. Kkoza, J.R., et al.: Genetic Programming III; Darwinian Invention and problem Solving. Morgan Kaufmann Publisher (1999)Google Scholar
  23. Zelinka, I.: Analytic Programming by means of Soma Algorithm. In: First International Conference on Intelligent Computing and Information Systems, Egypt, Cairo (2002)Google Scholar
  24. Zelinka, I.: SOMA - Self Organizing Migrating Algoritm. In: Batu, B.V., Onwubolu, G. (eds.) New Optimization Techniques in Engineering, ch. 7, p. 33. Springer (2004)Google Scholar
  25. Oplatková, Z., Zelinka, I.: Investigation on Artificial Ant using Analytic Programming. In: Genetic and Evolutionary Computation Conference. The Association for Computing Machinery, USA (2006)Google Scholar
  26. Vařacha, P., Zelinka, I.: Synthesis of artificial neural networks by of evolutionary methods. In: Workshop ETID 2007 in DEXA 2007. IEEE Computer Society (2007a)Google Scholar
  27. Vařacha, P., Zelinka, I.: Distributed Self-Organizing Migrating Algorithm (DISOMA). In: 8th International Carpathian Control Conference, Slovak Republic, Košice (2007b)Google Scholar
  28. Volna, E.: Forming neural networks design through evolution. In: Artificial Neural Networks and Intelligent Information Processing, pp. 13–20 (2007) ISBN: 978-972-8865-86-3Google Scholar
  29. Oplatková, Z., Zelinka, I.: Creating evolutionary algorithms by means of analytic programming - design of new cost function. In: European Council for Modelling and Simulation, ECMS 2007, pp. 271–276 (2007)Google Scholar
  30. Tsoulog, I., Gavrilis, D., Glavas, E.: Neural network construction and training using grammatical evolution. Neurocomputing 72(1-3), 269–277 (2008)CrossRefGoogle Scholar
  31. Hu, X.: Applications of the general projection neural network in solving extended linear-quadratic programming problems with linear constraints. Neurocomputing 72 (2009)Google Scholar
  32. Chramcov, B., Balátě, J.: Model-building for time series of heat demand. In: Proceedings of the 20th International DAAAM Symposium Intelligent Manufacturing and Automation: Focus on Theory, Practice and Education. DAAAM International Vienna, Vienna (2009)Google Scholar
  33. Vařacha, P.: Impact of Weather Inputs on Heating Plant - Agglomeration Modeling. In: Proceedings of the 10th WSEAS Ing. Conf. on Neural Networks, pp. 159–162. WSEAS World Science and Engineering Academy and Science, Athens (2009)Google Scholar
  34. Turner, S.D., Dudek, S.M., Ritchie, M.D.: Grammatical Evolution of Neural Networks for Discovering Epistasis among Quantitative Trait Loci. In: Pizzuti, C., Ritchie, M.D., Giacobini, M. (eds.) EvoBIO 2010. LNCS, vol. 6023, pp. 86–97. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  35. Gisario, A., et al.: Springback control in sheet metal bending by laser-assisted bending: Experimental analysis, empirical and neural network modelling. Optic and Lasers in Engineering 49(12) (2011)Google Scholar
  36. Turner, E., Jacobson, D.J., Taylo, J.W.: Genetic Architecture of a Reinforced, Postmating, Reproductive Isolation Barrier between Neurospora Species Indicates Evolution via Natural Selection. Plos Genetics 7(8) (2011)Google Scholar
  37. Vařacha, P.: Neural network synthesis dealing with classification problem. In: Recent Researches in Automatic Control: Proceedings of the 13th WSEAS International Conference on Automatic Control, Modelling & Simulation (ACMOS), pp. 377–382. WSEAS Press, Lanzarote (2011)Google Scholar
  38. Král, E., et al.: Usage of peak functions in heat load modeling of district heating system. In: Recent Researches in Automatic Control: Proceedings of the 13th WSEAS International Conference on Automatic Control, Modelling & Simulation (ACMOS), pp. 404–406. WSEAS Press, Lanzarote (2011)Google Scholar
  39. Šenkeřík, R., Oplatková, Z., Zelinka, I., Davendra, D.: Synthesis of feedback controller for three selected chaotic systems by means of evolutionary techniques: Analytic programming. Mathematical and Computer Modelling (May 27, 2011) ISSN 0895-7177, doi:10.1016/j.mcm.2011.05.030Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Faculty of Applied InformaticsTomas Bata University in ZlínZlínCzech Republic

Personalised recommendations