期刊文献+

基于广义回归神经网络的电离层VTEC建模 被引量:26

Modeling of Ionosphere VTEC Using Generalized Regression Neural Network
下载PDF
导出
摘要 提出一种基于广义回归神经网络的电离层电子总含量建模的新方法。依据电子总含量的时空变化特性建立基于广义回归神经网络的区域电子总含量模型。结合实例,详细讨论训练样本的采样策略对网络模型性能的影响,并确定较优的模型光滑参数和采样策略。分别从理论和实例上与常用的多项式模型进行对比分析。结果表明在数据样本密集区域两者的精度相当,而在外推的空白区域内网络模型的精度优于多项式模型,验证网络模型的可行性和有效性。 A new idea is for model ionosphere vertical total electron content based on generalized regression neural network. Firstly, this new model is established according to time and space characteristics of vertical total electron content. Then, we have discussed how sampling strategy influences network model performance. An excellent sampling strategy and smooth coefficients were determined according to investigation scenario. Finally, the feasibility and availability of network model are proved based on the comparing analysis between network model and polynomial model. Results show that the accuracy of network model in ample data region is similar with polynomial model, and which is better than polynomial model in the extrapolated blank data region.
出处 《测绘学报》 EI CSCD 北大核心 2010年第1期16-21,共6页 Acta Geodaetica et Cartographica Sinica
基金 国家863计划(2007AA12Z307)
关键词 电子总含量 广义回归神经网络 采样 模型精度 total electron content generalized regression neural network sampling model accuracy
  • 相关文献

参考文献10

  • 1范国清,王威,郗晓宁,魏立栋.高精度的连续电离层延迟建模研究[J].空间科学学报,2009,29(2):188-194. 被引量:1
  • 2HABARULEMA J B, MCKINNELL L A, CILLIERS P J. Prediction of Global Positioning System Total Electron Content Using Neural Networks over South Africa [ J]. Journal of Atmospheric and Solar-Terrestrial Physics. 2007, 69: 1842-1850.
  • 3MCKINNELL L A, FRIEDRICH M. A Neural Networkbased Ionospheric Model for the Auroral Zone[J]. Journal of Atmospheric and Solar-Terrestrial Physics. 2007, 69:1203-1210.
  • 4FRIEDRICH M, EGGER G, MCKINNELL L A, et al. Perturbations in EISCAT Electron Densities Visualised by Normalisation[J]. Advances in Space Research. 2006, 38: 2413-2417.
  • 5Simon Haykin. Neural Network: A Comprehensive Foundation[M]. USA: Person Education. 1999,8: 183-201.
  • 6WANG Wei, FAN Guoqing, XI Xiaoning. Composite Data Weight Analysis of Ionosphere Model Determination[C]// The 2007 International Symposium on GNSS/GPS. Sydney:[s.n.], 2007: 16.
  • 7谷志红,牛东晓,王会青.广义回归神经网络模型在短期电力负荷预测中的应用研究[J].中国电力,2006,39(4):11-14. 被引量:32
  • 8PARZEN E. On Estimation of a Probability Density Function and Mode[J]. Annals of Mathematical Statistics, 1962, 33: 1065-1076.
  • 9ROSENBLATT M. Density Estimates and Markov Sequences Nonparametric Techniques in Statistical Inference [M]. Cambridge: Cambridge Univ. Press, 1970, 41 :199- 213.
  • 10ROSENBLATT M. Remarks on Some Nonparametric Estimates of a Density Function[J]. Annals of Mathematical Statistics, 1956, 27, 832-837.

二级参考文献11

  • 1张雪莹,管霖,谢锦标.采用谱分析建模和基于人工神经网络的短期负荷预测方案[J].电网技术,2004,28(11):49-52. 被引量:8
  • 2章红平,平劲松,朱文耀,黄珹.电离层延迟改正模型综述[J].天文学进展,2006,24(1):16-26. 被引量:85
  • 3胡上序.观测数据的分析与处理[M].杭州:浙江大学出版社,2002..
  • 4Klobuchar J A. Ionosphere time delay algorithm for single-frequency GPS user. IEEE, 1987, AES23:325-331
  • 5RUTKOWSKI L. Generalized regression neural network in time-varyingenvironment [J ], IEEE Transaction on Neural Network, 2004,15 (3):576-596.
  • 6TOMANDL D, SCHOBER A. A modified general regression neural network with new, efficient training algorithms as a robust ‘black box'tool for data analysis [ J ]. Neural Networks, 2001,14 (8): 1023-1034.
  • 7CHENG Shih-lian, HWANG Chyi. Optimal approximation of linear systems by a differential evolution algorithm [ J ]. IEEE Transaction on Systems, Man and Cybernetics, 2001, 31 (6):698-707.
  • 8WATERS C R, SOMMESE T, HIBBELN B. Background clutter rejection using generalized regression neural networks [A ]. 2000 IEEE Aerospace Conference Proceedings [ C ] ,2000, 3 (3) :271-279
  • 9JIA Lei, PEI Ren-qing, YANG Shu-zhen. Using general regression neural network to determine profile of roller [A]. Proceedings of 2003 International Conference on Neural Networks and Signal Processing[ C ]. 2003,4 ( 11 ) : 365-368,
  • 10郑启富,陈德钊.优进遗传算法及其在化工数据处理中的应用[J].浙江大学学报(工学版),2003,37(3):303-306. 被引量:11

共引文献31

同被引文献251

引证文献26

二级引证文献237

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部