一种前兆观测时序特征量的数据检测方法
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
借鉴数据挖掘思想,设计了一种利用特征量检测地震前兆观测数据的方法,可快速定位异常数据。该方法对于前兆台网中心大量数据处理及大数据应用中的前期资料处理工作具有重要意义。
Borrowing ideas from data mining techniques,a method of picking up characteristic values from time series is designed to detect earthquake precursor observation data.Significant deviations from normal observation data could be identified rapidly using this method.It makes significant sense to adopt this method for the task of large data preprocessing of earthquake precursor observation data.
引文
[1]周克昌,赵刚,王晨,等.中国地震前兆台网观测技术系统整合[J].中国地震,2013,29(2):270-275(Zhou Kechang,Zhao Gang,Wang Chen,et al.Upgrade and Integration of the Precursor Observation Network of China[J].Earthquake Research in China,2013,29(2):270-275)
    [2]Shannon C E.A Mathematical Theory of Communication[J].The Bell System Technical Journal,1948,27(7):379-423
    [3]王栋,朱远甡.信息熵在水系统中的应用研究综述[J].水文,2001,21(2):9-14(Wang Dong,Zhu Yuanshen.Informational Entropy and the State-of-the-Art of Its Application in Hydrology,Water Resources and Water Environment[J].Hydrology,2001,21(2):9-14)
    [4]李海林,杨丽彬.时间序列数据降维和特征表示方法[J].控制与决策,2013,28(11):1 718-1 722(Li Hailin,Yang Libin.Method of Dimensionality Reduction and Feature Representation for Time Series[J].Control and Decision,2013,28(11):1 718-1 722)
    [5]任江涛,何武,印鉴,等.一种时间序列快速分段及符号化方法[J].计算机科学,2005,32(9):166-169(Ren Jiangtao,He Wu,Yin Jian,et al.A Fast Time Series Segmentation and Symbolization Method[J].Computer Science,2005,32(9):166-169)
    [6]钟清流,蔡自兴.基于统计特征的时序数据符号化算法[J].计算机学报,2008,31(10):1 857-1 864(Zhong Qingliu,Cai Zixing.The Symbolic Algorithm for Time Series Data Based on Statistic Feature[J].Chinese Journal of Computers,2008,31(10):1 857-1 864)

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