• DocumentCode
    2917771
  • Title

    Study of Recognition Approach for Specific Sample Points in High Dimension Space

  • Author

    Yarong, Gao ; Jianxiao, Guo ; Hongli, Wang ; Xianglan, Chi ; Yushu, Zhang

  • Author_Institution
    Dept. of Basis Courses Teaching, Tianjin Foreign Studies Univ., Tianjin, China
  • Volume
    3
  • fYear
    2009
  • fDate
    21-22 Nov. 2009
  • Firstpage
    259
  • Lastpage
    262
  • Abstract
    Based on secondary analysis techniques to identify specific sample point using partial least-squares analysis method, the recognition method of specific sample point of two-dimensional floor plan of ellipse T2 was extended to three-dimensional figure of ellipsoid T2 and high-dimensional space of hyper- ellipsoid T2. Another Identification method of specific sample point making use of hierarchical diagram in high-dimensional space based on hierarchical clustering method was proposed at the same time. The recognition method of specific sample point had great significance on research areas of data mining, machine learning and pattern recognition while eliminating samples generated due to random factors and refining mathematical models. Empirical analysis of the five kinds of identification method was accomplished using ecological data of the 56 observation sites along the Bohai Sea coastal zone.
  • Keywords
    computational geometry; data mining; learning (artificial intelligence); least squares approximations; pattern recognition; random processes; 2D floor plan; data mining; hierarchical clustering method; hierarchical diagram; high dimension space; hyper- ellipsoid T2; machine learning; mathematical models; partial least-squares analysis method; pattern recognition; random factors; recognition approach; recognition method; secondary analysis techniques; specific sample point; Data mining; Ellipsoids; Equations; Independent component analysis; Information technology; Least squares methods; Mathematical model; Pattern recognition; Regression analysis; Space technology; data mining; hierarchical diagram; high dimension space; partial least-squares; pattern recognition; specific sample point;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Information Technology Application, 2009. IITA 2009. Third International Symposium on
  • Conference_Location
    Nanchang
  • Print_ISBN
    978-0-7695-3859-4
  • Type

    conf

  • DOI
    10.1109/IITA.2009.248
  • Filename
    5369453