首页 | 本学科首页   官方微博 | 高级检索  
     检索      

时间序列异常值探测的Bayes方法及其在电离层VTEC数据处理中的应用
引用本文:归庆明,李涛,衡广辉.时间序列异常值探测的Bayes方法及其在电离层VTEC数据处理中的应用[J].武汉大学学报(信息科学版),2011(7):802-806.
作者姓名:归庆明  李涛  衡广辉
作者单位:信息工程大学理学院;
基金项目:国家自然科学基金资助项目(40974009,40474007); 郑州市科技攻关计划资助项目(0910SGYG21198)
摘    要:基于Bayes统计推断理论,提出了自回归模型中异常值定位的Bayes方法;在正态-Gamma先验分布下,分别基于均值漂移模型和方差膨胀模型,提出了后验概率的计算方法,并运用Bayes方法估计了异常扰动;最后将该方法应用到电离层VTEC数据处理的建模中,比较模型修正前后预报的结果,验证了新方法的有效性。

关 键 词:时间序列  异常值探测  Bayes方法  后验概率  电离层

Bayesian Methods for Time Series Outliers Detection and Applications in Ionospheric VTEC Data Processing
GUI Qingming LI Tao HENG Guanghui.Bayesian Methods for Time Series Outliers Detection and Applications in Ionospheric VTEC Data Processing[J].Geomatics and Information Science of Wuhan University,2011(7):802-806.
Authors:GUI Qingming LI Tao HENG Guanghui
Institution:GUI Qingming1 LI Tao1 HENG Guanghui1(1 Institute of Science,Information Engineering University,62 Kexue Road,Zhengzhou 450001,China)
Abstract:The observation of time series may be influenced by outliers.If we forecasts directly,neglecting the influence,will lead to false result.So,it is important to find proper outliers detection method.Based on the theory of Bayesian statistical inference,in this paper we put forward Bayesian method of positioning outliers in autoregressive model firstly;and then,under the condition of normal-gamma prior information,we put forward computation method of posterior probability based on mean shift model and variance...
Keywords:time series  outliers detection  Bayesian method  posterior probability  ionospheric  
本文献已被 CNKI 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号