收稿日期: 2014-11-04
修回日期: 2015-03-12
网络出版日期: 2015-09-15
基金资助
中国科学院西部之光联合学者项目(201491)资助
Prediction of length-of-day variation using grey relational analysis and extreme learning machine
Received date: 2014-11-04
Revised date: 2015-03-12
Online published: 2015-09-15
针对日长变化难以用精确模型进行预报的问题,将一种新型人工神经网络——极限学习机(extreme learning machine, ELM)用于日长变化预报中.首先针对时间序列预测问题中存在的嵌入维数选取和网络结构设计问题,提出一种基于灰色关联分析(grey relational analysis, GRA)的ELM算法(GRA-ELM),该算法将灰色关联分析输入节点选取嵌入到ELM网络的训练过程中,同时完成嵌入维数和隐层节点规模的确定.然后根据日长变化数据的特点对其进行预处理,建立一种能够高精度、近实时预报日长变化的GRA-ELM预报模型.最后将GRA-ELM模型的预报结果同标准ELM、反向传播神经网络、广义回归神经网络和地球定向参数预报比较竞赛的结果进行比较.结果表明,通过本方法得到的日长变化较其他方法在精度上有较大改善.
雷雨 , 蔡宏兵 , 赵丹宁 . 利用灰色关联极限学习机预报日长变化[J]. 中国科学院大学学报, 2015 , 32(5) : 588 -593 . DOI: 10.7523/j.issn.2095-6134.2015.05.003
Due to the time-varying characteristics of length-of-day (LOD), it is difficult to model LOD variations with a deterministic model. We employ a new type of artificial neural networks (ANN)-extreme learning machine (ELM) to predict LOD variations. In order to solve the problems of embedding dimension selection and network topology design, a training algorithm for ELM based on grey relational analysis (GRA) is first proposed. It optimizes the input and hidden layers simultaneously. Secondly, the values of LOD variation are preprocessed and a GRA-ELM model is then set up to accurately forecast LOD variation in near real-time. Finally, the prediction results are analyzed and compared with those obtained by the back propagation neural networks, generalization regression neural networks and Earth orientation parameters prediction comparison campaign. The results show that the prediction accuracy of our method is equal to or even better than those of the other prediction methods. The developed method is easy to use.
[1] Gambis D, Luzum B. Earth rotation monitoring, UT1 determination and prediction [J]. Metrologia, 2011, 48(4): 165-170.
[2] Tomasz N, Kosek W. Prediction of UT1-UTC, LOD and AAM χ3 by combination of least-squares and multivariate stochastic methods [J]. Journal of Geodesy, 2008, 82(2): 83-92.
[3] Kosek W, McCarthy D D, Luzum B J. Possible improvement of Earth orientation forecast using autocovariance prediction procedures[J]. Journal of Geodesy, 1998, 72(4):189-199.
[4] Gross R S, Eubanks T M, Steppe J A, et al. A Kalman filter-based approach to combining independent Earth-orientation series[J]. Journal of Geodesy, 1998, 72(4):215-235.
[5] Schuh H, Ulrich M, Egger D, et al. Prediction of Earth orientation parameters by artificial neural networks[J]. Journal of Geodesy, 2002, 76(5):247-258.
[6] 张晓红, 王琪洁, 朱建军, 等. 广义回归神经网络在日长变化预报中的应用[J]. 天文学报,2011, 52(4):322-331.
[7] Wang Q J, Du Y N, Liu J. Introducing atmospheric angular momentum into prediction of length of day change by generalized regression neural network model[J]. Journal of Central South University, 2014, 21:1396-1401.
[8] Akyilmaz O, Kutterer H. Prediction of Earth rotation parameters by fuzzy inference systems[J]. Journal of Geodesy, 2004, 78(1/2):82-93.
[9] Huang G B, Zhu Q Y, Siew C K. Extreme learning machine:theory and applications[J]. Neurocomputing, 2006, 70(1-3):489-501.
[10] Huang G B, Zhu H M, Ding X J, et al. Extreme learning machine for regression and multiclass classification[J]. Iee Transactions on Systems, Man, and Cybernetics-Part B:Cybernetics, 2012, 42(2):513-529.
[11] Sun Z L, Choi T M. Sales forecasting using extreme learning machine with applications in fashion retailing[J]. Decision Support Systems, 2008, 46(1):411-419.
[12] Gerard P, Brain L. IERS Conventions (2010)[S]. Germany:Verlag des Bundesamts für Kartographie und Geodasie, 2011:123-131.
[13] 崔杰. 一种新的灰色相似关联度及其应用[J]. 统计与决策, 2008, 20:14-16.
[14] Kalarus M, Schuh H, Kosek W, et al. Achievements of the Earth orientation parameters prediction comparison campaign[J]. Journal of Geodesy, 2010, 84(10):587-596.
/
| 〈 |
|
〉 |
