卫星遥测数据相关性知识发现方法 | |
Alternative Title | Correlation knowledge discovery method for satellite telemetry data |
杨甲森; 孟新; 王春梅 | |
Department | 空间技术部 |
Source Publication | 国防科技大学学报
![]() |
Volume | 41Issue:5Pages:71-78 |
DOI | 10.11887/j.cn.201905011 |
ISSN | 1001-2486 |
Language | 中文 |
Keyword | 信息熵 最大信息系数 遥测数据 相关性 量子卫星 |
Abstract | 为快速发现海量遥测数据中的相关关系,提出一种基于改进最大信息系数(Maximal Information Coefficient, MIC)的遥测数据相关性知识发现方法。以Mini Batch K-Means聚类算法为前驱过程对数据进行网格划分;计算该网格划分下的互信息,并以信息熵代替原有最大熵对互信息进行归一化矫正得到信息系数;选择不同网格划分下MIC作为变量相关性的测度。采用量子卫星遥测数据进行试验,结果表明:与基于动态规划算法的MIC方法相比,所提方法可有效解决MIC测度偏向多值变量的问题,时间复杂度从O(n~(2.4))下降为O(n~(1.6)),是一种适用于大规模遥测数据相关性分析的有效方法。 |
Other Abstract | To discover correlations in massive telemetry data efficiently, a novel correlation knowledge discovery method based on the improved MIC (maximal information coefficient) was proposed. The Mini Batch K-Means clustering algorithm was used to discretize data in the precursor process; the mutual information between two variables under this partition was calculated and normalized by information entropy instead of maximal entropy to obtain the information coefficient; the MIC was selected as the measure of variable correlation. Aflerwards, the method was applied to the correlation analysis of the quantum satellite telemetry data, and the results show that the proposed method can effectively solve the problem of MIC measure bias to multi-valued variables compared with the method based on dynamic programming algorithm, the time complexity dropped from O(n~(2.4)) to O(n~(1.6)), and it is an effective method for large-scale telemetry data correlation analysis. |
Indexed By | EI ; CSCD |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.nssc.ac.cn/handle/122/7260 |
Collection | 空间技术部 |
Recommended Citation GB/T 7714 | 杨甲森,孟新,王春梅. 卫星遥测数据相关性知识发现方法[J]. 国防科技大学学报,41(5):71-78. |
APA | 杨甲森,孟新,&王春梅. |
MLA | 杨甲森,et al."卫星遥测数据相关性知识发现方法".国防科技大学学报 41.5 |
Files in This Item: | Download All | |||||
File Name/Size | DocType | Version | Access | License | ||
201941571-78.pdf(848KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | View Download |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment