...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Geophysical Research, A. Space Physics: JGR >A new multivariate time series data analysis technique: Automateddetection of flux transfer events using Cluster data
【24h】

A new multivariate time series data analysis technique: Automateddetection of flux transfer events using Cluster data

机译：一种新的多变量时间序列数据分析技术:Automateddetection通量传输使用集群数据事件

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

A new data mining technique called MineTool-TS is introduced which captures thetime-lapse information in multivariate time series data through extraction of globalfeatures and metafeatures. This technique is developed into a JAVA-based data miningsoftware which automates all the steps in the model building to make it more accessible tononexperts. As its first application in space sciences, MineTool-TS is used to develop a model for automated detection of flux transfer events (FTEs) at Earth's magnetopause inthe Cluster spacecraft time series data. The model classifies a given time series into one ofthree categories of non-FTE, magnetosheath FTE, or magnetospheric FTE. Oneimportant feature of MineTool-TS is the ability to explore the importance of each variableor combination of variables as indicators of FTEs. FTEs have traditionally been identifiedon the basis of their magnetic field signatures, but here we find that some plasmavariables can also be effective indicators of FTEs. For example, the perpendicular iontemperature yields a model accuracy of .-93%, while a model based solely on the normalmagnetic field BN yields an accuracy of -,95%. This opens up the possibility of searchingfor more unusual FTEs that may, for example, have no clear BN signature and createa more comprehensive and less biased list of FTEs for statistical studies. We also find thatmodels using GSM coordinates yield comparable accuracy to those using boundarynormal coordinates. This is useful since there are regions where magnetopause models arenot accurate. Another surprising result is the finding that the algorithm can largely detectFTEs, and even distinguish between magnetosheath and magnetospheric FTEs, solelyon the basis of models built from single parameters, something that experts may not do sostraightforwardly on the basis of short time series intervals. The most accurate models usea combination of plasma and magnetic field variables and achieve a very high accuracyof prediction of —99%. We explain the high detection accuracies both in terms of theexistence of clear physical signatures of FTEs (for the majority of cases) and in terms ofthe capability of the data mining technique to explore the data set in a much morethorough fashion than expert human eyes. A list of 1222 FTEs from Cluster data duringyears 2001-2003 is provided as auxiliary material.
机译：一个叫做MineTool-TS新的数据挖掘技术它捕获thetime-lapse介绍多元时间序列数据的信息通过提取globalfeatures和metafeatures。基于java的数据miningsoftware自动化在模型构建的所有步骤更容易tononexperts。在空间科学应用,MineTool-TS用于开发一个模型进行自动检测通量传输事件(fte)在地球磁层在集群航天器时间序列数据。成一个non-FTE三个类别,磁鞘FTE或磁性层的FTE。MineTool-TS是中重要的特征之一探索能力的重要性variableor变量指标的结合有限责任。identifiedon磁场的基础签名,但这里我们发现一些plasmavariables也可以有效的指标有限责任。iontemperature收益率模型的准确性。- 93%,而模型完全基于normalmagnetic场BN收益率的准确性,95%。searchingfor更不寻常的可能性例如,招聘,可能没有明确的BN签名和创建更全面、更少有偏见的招聘列表统计研究。还发现thatmodels使用GSM坐标产量使用boundarynormal可比的准确性坐标。地区磁模型并不等同准确的。发现该算法可以在很大程度上detectFTEs,甚至区分磁鞘和磁性层的招聘,solelyon由单参数模型的基础上,专家可能不做的东西sostraightforwardly短时间的基础上系列的间隔。结合等离子体和磁场变量和实现accuracyof很高预测的-99%。精度方面明显的发现有限责任(对于大多数物理签名例)和数据的能力挖掘技术探索的数据集比专家人眼morethorough时尚。一个集群数据duringyears 1222招聘列表2001 - 2003是作为辅助材料提供。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号