基于优势关系粗糙集的地震数据约简和规则提取
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
针对现有的基于不可分辨关系的数据约简算法在地震数据处理中存在的缺点,提出一个新的优势区分矩阵的定义,并在此基础上给出相应的具有更好约简效率的数据约简算法和规则提取算法.在运用该算法对全国小震目录数据进行的实验中,从上海市地震局提供的44 381条样本数据中挖掘出272条确定性规则,取得了有实际意义的结果.
After discussing the classical rough set theory based on indiscemibility relation and its reduction algorithms on earthquake data,we present a new definition of dominance discemibility matrix by taking advantage of the unique characteristic of the extended model.The corresponding reduction and rule extraction algorithms are then given accordingly to enhance efficiency in seeking the reduction to some extent.We use the rough set theory based on dominance relation to get 272 rules with realistic meaning from 44 381 items in a small set of earthquake data of China.
引文
[1]敖雪明,王桂岭,黄克强,等.相关地震预报方法的研究[C]//地震预报方法实用化研究文集——地震学专辑.北京:学术出版社,1989:268-295.
    [2]PAWLAK Z.Rough sets:theoretical aspects of reasoningabout data[M].Dordrecht:Kluwer Academic Publishers,1991:341-356.
    [3]GAWRYS M,SIENKIEWICZ J.Rough set library user’smanual[M].Dordrecht:Kluwer Academic Publishers,1993.
    [4]OHRN A,KOMOROWSKI J.ROSETTA:a rough settoolkit for analysis of data[C]//Proc Third InternationalJoint Conference on Information Sciences,Fifth InternationalWorkshop on Rough Sets and Soft Computing(RSSC’97),Durham,NC,USA.1997:403-407.
    [5]常犁云,王国胤.一种基于Rough set理论的属性约简及规则提取方法[J].软件学报,1999,10(11):1206-1211.
    [6]潘丹,郑启伦.属性约简自寻优方法[J].计算机研究与发展,2001,36(6):904-910.
    [7]GRECO S,MATAATAZZO B,SLOWINSKI R.A newrough set approach to evaluation of bankruptcy risk[C]//ZOPOUNIDIS C.Operational Tools in the Management ofFinancial Risks.Dordrecht:Kluwer Academic Publishers,1998:121-136.
    [8]GRECO S,MATAARZZO B,SLOWINSKI R.Rough setsmethodology for sorting problems in presence of multipleattributes and criteria[J].European Journal of OperationalResearch,2002,138:247-259.

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心