累积量测序列的区间云变换及识别
CSTR:
作者:
作者单位:

海军航空工程学院电子信息工程系,山东烟台264001.

作者简介:

孙贵东

通讯作者:

中图分类号:

TN95

基金项目:

国家自然科学基金重点项目(61032001);教育部新世纪优秀人才支持计划项目(NCET-11-0872).


Interval cloud transform and recognition research of accumulative measurement sequence data
Author:
Affiliation:

(Department of Electronics and Information Engineering,Naval Aeronautical and Astronautical University,Yantai 264001,China.

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    目标多属性序列类数据不能直接与数据库中的区间类数据融合识别, 对此, 提出一种基于云变换的序列-区间异类数据识别算法. 对目标多属性序列数据进行频数计算形成频率分布函数, 并进行虚警检测, 实施云变换形成云簇, 提取云簇特征, 再根据3 En 准则形成云滴区间, 实现了序列型数据的区间化表示. 进一步, 利用一种区间多属性识别判定准则进行识别判定, 得到识别结果, 解决了序列-区间异类数据的识别问题. 仿真实验结果验证了该算法对序列-区间异类数据识别的有效性.

    Abstract:

    An asynchronous data recognition algorithm for sequence and interval number based on cloud transform is proposed to solve the problem that the multi-attribute sequence data of the target can not be recognized with the interval number in the database directly. This algorithm counts the possible values in the multi-attribute sequence data approximately and forms the frequency distribution function firstly and then detects the possible values with the threshold. Afterwards, cloud groups are formed with back cloud transform and their the characteristics are extracted, the cloud interval number is got to represent the sequence data according to the 3En rule. The transformed interval recognition is made by using the multi-attribute interval recognition rule and the satisfied result is obtained, which solves the asynchronous data recognition for the sequence and interval number. Simulation experiment results show that the proposed algorithm can recognize the sequence and interval asynchronous data effectively.

    参考文献
    相似文献
    引证文献
引用本文

关欣 孙贵东 衣晓 郭强.累积量测序列的区间云变换及识别[J].控制与决策,2015,30(8):1345-1355

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2014-05-14
  • 最后修改日期:2014-07-22
  • 录用日期:
  • 在线发布日期: 2015-08-20
  • 出版日期:
文章二维码