航空学报 > 2015, Vol. 36 Issue (10): 3349-3358   doi: 10.7527/S1000-6893.2014.0365

基于云映射的多粒度语义决策属性识别

孙贵东, 关欣, 衣晓, 王虹   

  1. 海军航空工程学院 电子信息工程系, 烟台 264001
  • 收稿日期:2014-09-26 修回日期:2014-12-30 出版日期:2015-10-15 发布日期:2015-01-07
  • 通讯作者: 关欣, Tel.: 0535-6635676 E-mail: gxtongwin@163.com E-mail:gxtongwin@163.com
  • 作者简介:孙贵东 男, 博士研究生。主要研究方向: 信息融合理论, 智能数据挖掘。 Tel: 0535-6635676 E-mail: sdwhsgd@163.com;关欣 女, 博士, 教授, 硕士生导师。主要研究方向: 智能信息处理, 多源信息融合。 Tel: 0535-6635676 E-mail: gxtongwin@163.com;衣晓 男, 博士, 教授, 硕士生导师。主要研究方向: 无线传感器网络, 多源信息融合。 Tel: 0535-6635673 E-mail: yxgx_gxyx@163.com;王虹 女, 硕士研究生。主要研究方向: 多源信息融合, 目标识别。 Tel: 0535-6635676 E-mail: wang_hvirgo@sina.com
  • 基金资助:

    国家自然科学基金 (61032001); 新世纪优秀人才支持计划 (NCET-11-0872)

Recognition of multi-granularity linguistic and decision attribute based on cloud map

SUN Guidong, GUAN Xin, YI Xiao, WANG Hong   

  1. Department of Electronics and Information Engineering, Naval Aeronautical and Astronautical University, Yantai 264001, China
  • Received:2014-09-26 Revised:2014-12-30 Online:2015-10-15 Published:2015-01-07
  • Supported by:

    National Natural Science Foundation of China (61032001); Program for New Century Excellent Talents in University (NCET-11-0872)

摘要:

异类多传感器多属性目标识别中的描述性语义和决策属性信息无法直接进行识别判定,为此基于粒层转化的思想,提出了一种语义和决策属性识别方法。首先构造云映射函数,将语义和决策属性粒层统一到区间粒层,再根据灰色关联的思想计算区间化后的语义和决策属性信息与数据库之间的区间关联度,实现了不等粒层属性的粒度计算,最后采用证据推理进行了识别判定。结合语义和决策属性识别算例及对比分析,验证了所提出方法在异类数据模糊转化处理和识别上的有效性。

关键词: 目标识别, 云映射, 语义决策属性, 灰色关联, 证据理论

Abstract:

Descriptive linguistic and decision attribute of target cannot be recognized with database directly in multiple asynchronous sensors multi-attribute target recognition domain. So a linguistic and decision attribute recognition method based on granular level transform is proposed to solve this problem. Firstly, with this algorithm, cloud mapping function is introduced, which unifies the linguistic and decision granular level to the same interval granular level. Then the interval degree of incidence between the transformed linguistic, decision interval and the interval database is calculated based on grey incidence theory, which achieves the granular computation among the multi-granularity levels. Finally, combined with the evidence theory the recognition result is obtained. The simulation and compared analysis of linguistic and decision attribute show the effectiveness of the proposed method in precision and fuzzy transform processing.

Key words: target recognition, cloud map, linguistic and decision attribute, grey incidence, evidence theory

中图分类号: