• DocumentCode
    2869579
  • Title

    The Evaluation Model of Knowledge Management Based on Information Entropy and RBF Neural Network (IE-RBF)

  • Author

    Chen, Yu

  • Author_Institution
    Dept. of Comput. & Modern Educ. Technol., Chongqing Educ. Coll., Chongqing, China
  • Volume
    1
  • fYear
    2009
  • fDate
    18-19 July 2009
  • Firstpage
    11
  • Lastpage
    13
  • Abstract
    Knowledge management is a complex systems engineering, so the evaluation of knowledge management is of non-linear characteristics. Neural network with the ability of adaptive learning is an excellent tool to deal with the issue of non-linear. This paper analyzed the essence of knowledge and knowledge management. We proposed an evaluation model of knowledge management based on the theory of information entropy and RBF neural network. After reduction of the indices system with information entropy to reduce, we would evaluate the knowledge management with RBF neural network. After empirical research with MATLAB7.0, it is had been proved that the method is validity and practicality. And then it did not only overcome the traditional methodspsila shortcoming which is too subjective, but also avoided complex process of the traditional evaluation method.
  • Keywords
    entropy; knowledge management; learning (artificial intelligence); radial basis function networks; RBF neural network; adaptive learning; evaluation model; information entropy; knowledge management; nonlinear characteristic; radial basis function network; Computer networks; Computer science education; Information entropy; Information management; Information processing; Information theory; Knowledge management; Mathematical model; Neural networks; Systems engineering education; Information Entropy; Knowledge Management; Neural Network;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Information Processing, 2009. APCIP 2009. Asia-Pacific Conference on
  • Conference_Location
    Shenzhen
  • Print_ISBN
    978-0-7695-3699-6
  • Type

    conf

  • DOI
    10.1109/APCIP.2009.10
  • Filename
    5196982