Select Language






Data Type:

所需积分:15 去赚积分?
  • 248浏览
  • 2下载
  • 0点赞
  • 收藏
  • 分享

Data Preview ? 41K

    Data Structure ?


    Data Set Information:

    托儿所数据库源于最初开发用于对托儿所应用程序进行排序的分层决策模型。20世纪80年代,斯洛文尼亚卢布尔雅那的这些学校入学人数过多,被拒绝的申请常常需要客观的解释。最终决定取决于三个子问题:父母和儿童托儿所的职业、家庭结构和财务状况以及家庭的社会和健康状况。该模型是在决策DEX专家系统外壳中开发的(M.Bohanec,V.Rajkovic:决策专家系统,Sistemica 1(1),第145-157页,1990年)。

    The hierarchical model ranks nursery-school applications according to the following concept structure:

    NURSERY            evaluation of applications for nursery schools
    . EMPLOY           Employment of parents and child's nursery
    . . parents        Parents' occupation
    . . has_nurs       Child's nursery
    . STRUCT_FINAN     Family structure and financial standings
    . . STRUCTURE      Family structure
    . . . form         Form of the family
    . . . children     Number of children
    . . housing        Housing conditions
    . . finance        Financial standing of the family
    . SOC_HEALTH       Social and health picture of the family
    . . social         Social conditions
    . . health         Health conditions

    Input attributes are printed in lowercase. Besides the target concept (NURSERY) the model includes four intermediate concepts: EMPLOY, STRUCT_FINAN, STRUCTURE, SOC_HEALTH. Every concept is in the original model related to its lower level descendants by a set of examples (for these examples sets see [Web link]).

    The Nursery Database contains examples with the structural information removed, i.e., directly relates NURSERY to the eight input attributes: parents, has_nurs, form, children, housing, finance, social, health.

    Because of known underlying concept structure, this database may be particularly useful for testing constructive induction and structure discovery methods.

    Attribute Information:

    parents:        usual, pretentious, great_pret
      has_nurs:       proper, less_proper, improper, critical, very_crit
      form:           complete, completed, incomplete, foster
      children:       1, 2, 3, more
      housing:        convenient, less_conv, critical
      finance:        convenient, inconv
      social:         non-prob, slightly_prob, problematic
      health:         recommended, priority, not_recom

    Relevant Papers:

    M. Olave, V. Rajkovic, M. Bohanec: An application for admission in public school systems. In (I. Th. M. Snellen and W. B. H. J. van de Donk and J.-P. Baquiast, editors) Expert Systems in Public Administration, pages 145-160. Elsevier Science Publishers (North Holland), 1989.
    [Web link]

    B. Zupan, M. Bohanec, I. Bratko, J. Demsar: Machine learning by function decomposition. ICML-97, Nashville, TN. 1997
    [Web link]


    Vladislav Rajkovic et al. (13 experts)


    Marko Bohanec   (marko.bohanec '@'
    Blaz Zupan      (blaz.zupan '@'