Context Neural Network for Temporal Correlation and Prediction

  • L. F. Mingo
  • L. Aslanyan
  • J. Castellanos
  • V. Riazanov
  • M. A. Díaz


This paper is focused on the application of Enhanced Neural Networks to the load demand forecasting. These nets can be considered as Context Networks since they are able to process the pattern set in order to obtain a valid context according to the input presented to the net, the context data are expressed in the weights of a neural network. Concerning the load demand forecasting, classical methods require two stages, first stage is a classification net to organize data, and second stage is a forecasting net to output desired response. With Context Neural Networks, only one stage is required. The net will perform a classifation and a forecasting process at the same time. Results of Context Networks against classical neural methods are compared, showing the improvement of proposed networks.


Hide Layer Neural Network Architecture Load Demand Connection Type Context Network 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Barbizet, J. & Duizabo, Ph.: Manual de Neuropsicología. Barcelona: Toray-Masson S.A. Translate from Abrege de Neuropsychologie. Paris: Masson S.A. pp. 17–21. (1978).Google Scholar
  2. [2]
    Delacour, J.: Apprentissage et Memoire: Une Approache Neurobiologique. Masson Ed.) September. (1987).Google Scholar
  3. [3]
    Mingo L.F. Giménez V. Castellanos J.: A New kind of Neural Networks and its Learning Algorithm. 7th Intenational Conference on Information Processing and Management of Uncertainty in Knowledge-based Systems. IPMU’98. France. July (1998). pp: 1913–1914.Google Scholar
  4. [4]
    Mingo L.F. Arroyo F. Luengo C. & Castellanos J.: Learning HyperSurfaces with Neural Networks. 11th Scandinavian Conference on Image Analysis. SCIA’99. Greenland. June (1999).Google Scholar
  5. [5]
    Carpintero A. Castellanos J. Leiva S. Mingo L.F. Rios J.; Short-Term Load Demand with a Mixed Neural Network Systems. International Conference on Intelligence and Cognitive Systems, ICICS 96. Tehran — Iran. Sept. pp:60–63. 1996.Google Scholar
  6. [6]
    Baumann T. & Germond A.J., Application of The Kohonen Network To Short-Term Load Forecasting in Proceedings of the ANNPS International Forum, 1993.Google Scholar
  7. [7]
    Ligomenides P. Daw-Tung L., Adaptive TimeDelay Nn For Temporal Correlation And Prediction. Proceedings of SPIE’92. Boston. 1992.Google Scholar
  8. [8]
    Cosculluela M.J. Dominguez M.J. Montes R. 0 Garca Tejedor A.J., Day Type Identification For Electric Hourly Load Demand Forecasting Using Selforganized Maps. In Proceedings of NeuroNimes 1993.Google Scholar

Copyright information

© Springer-Verlag Wien 2001

Authors and Affiliations

  • L. F. Mingo
    • 1
  • L. Aslanyan
    • 2
  • J. Castellanos
    • 3
  • V. Riazanov
    • 4
  • M. A. Díaz
    • 1
  1. 1.Dpto. Organización y Estructura de la InformaciónEscuela Universitaria de InformáticaMadridSpain
  2. 2.Laboratory of Discrete Analysis and Modelling TechnologiesInstitute for Informatics and Automation ProblemsYerevanArmenia
  3. 3.Facultad de InformáticaDpto. Inteligencia Artificial. UPM. Campus de MontegancedoMadridSpain
  4. 4.Dept. of Recognition Problems and Combinatorial AnalysisComputing CentreMoscowRussia

Personalised recommendations