• DocumentCode
    2464508
  • Title

    Intelligent Scheme Design of High-Rise Structure for K-Means-Based Case Retrieval

  • Author

    Zhang, Shihai ; Wang, Changyong ; Liu, Shujun

  • Author_Institution
    Sch. of Civil Eng., Harbin Inst. of Technol., Harbin, China
  • Volume
    3
  • fYear
    2010
  • fDate
    16-17 Dec. 2010
  • Firstpage
    241
  • Lastpage
    244
  • Abstract
    In the basic idea of k-means clustering algorithm and its criterion function, step process, the cluster analysis theory and method into intelligent design of high-rise structure was introduced in this paper, the high-rise structure of intelligent design case retrieval method based on the K-Means clustering analysis method was established, and by the given engineering application, the process of clustering results and their spatial distribution, the evaluation function JW with the curves of the increase in the number of iterations and JW monotonically decreasing curve with k( the number of clusters k changes from 2 to 10) were obtained, the weaknesses of the method were pointed out, and the further improvement was given. Practice shows that: k-means cluster analysis method can be effectively used to design case retrieval system in high-rise structures intelligent scheme, and has opened up new ways for the high-rise building intelligent design.
  • Keywords
    information retrieval; pattern clustering; structural engineering computing; case retrieval method; evaluation function; intelligent scheme design; k-means clustering algorithm; spatial distribution; Algorithm design and analysis; Artificial intelligence; Buildings; Classification algorithms; Clustering algorithms; Design methodology; Electron tubes; case retrieval; cluster analysis; high-rise building; k-means algorithm; structural intelligent scheme design;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Systems (GCIS), 2010 Second WRI Global Congress on
  • Conference_Location
    Wuhan
  • Print_ISBN
    978-1-4244-9247-3
  • Type

    conf

  • DOI
    10.1109/GCIS.2010.31
  • Filename
    5709365