Effects of Training Patterns on Predictions of Variations of Length Of Day Using an Extreme Learning Machine Neural Network

Lei Yu; Cai Hongbing; Zhao Danning

Astronomical Research and Technology > 2015 > 12(3): 299-305.

Lei Yu, Cai Hongbing, Zhao Danning. Effects of Training Patterns on Predictions of Variations of Length Of Day Using an Extreme Learning Machine Neural Network[J]. Astronomical Research and Technology, 2015, 12(3): 299-305.

Citation:

PDF (1375 KB)

Effects of Training Patterns on Predictions of Variations of Length Of Day Using an Extreme Learning Machine Neural Network

Lei Yu^1,2,3,
Cai Hongbing^1,2,
Zhao Danning^1,3

1.
National Time Service Center, Chinese Academy of Sceinces, Xi'an 710600, China
2.
Key Laboratory of Primary Time and Frequency Standards, Chinese Academy of Sciences, Xi'an 710600, China
3.
University of Chinese Academy of Sciences, Beijing 100049, China

More Information

Received Date: October 09, 2014
Revised Date: October 27, 2014
Published Date: July 14, 2015

Graphical Abstract

Abstract

Abstract

In this paper we investigate effects of training patterns on predictions of varations of Lenth Of Day (LOD) by an Extreme Learning Machine (ELM) neural network. We first discuss three types of training patterns, which are named as interval patterns, continuous patterns, and iterative patterns, respectively. We then present comparisons of the accuracies of the predictions using training patterns of the three types.We have found that results of using interval patterns are the worst; using iterative patterns can yield more accurate short-term predictions (of 1 day to 30 days away) as compared to using continuous patterns, but the situation is reversed in medium-term predictions (of 30 days to 360 days away). As for compution efficiencies, using iterative patterns is noticeably faster than using either of the other two patterns. Iterative patterns are thus suitable for real-time predictions of varations of LOD, while continuous patterns are suitable for medium-term predictions of varations of LOD. Efficiencies and accuracies are the primary concerns in these two types of predictions, respectively.

FullText(HTML)

References (14)

References

[1]	Gambis D, Luzum B. Earth rotation monitoring, UT1 determination and prediction[J]. Metrologia, 2011, 48(4): 165-170.
[2]	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. Zhang Xiaohong, Wang Qijie, Zhu Jianjun, et al. An application to the prediction of LOD change based on general regression neural network[J]. Acta Astronomica Sinica, 2011, 52(4): 322-331.
[3]	Zhang Xiaohong, Wang Qijie, Zhu Jianjun, et al. Application of general regression neural network to the prediction of LOD change[J]. Chinese Astronomy and Astrophysics, 2012, 36(1): 86-96.
[4]	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.
[5]	王琪洁, 廖得春, 周永宏. 地球自转速率变化的实时快速预报[J]. 科学通报, 2007, 52(15): 1728-1731.
[6]	Wang Qijie, Liao Dechun, Zhou Yonghong. Real-time rapid prediction of variations of Earth's rotation[J]. Chinese Science Bulletin, 2008, 53(7): 969-973.
[7]	王琪洁, 廖得春, 周永宏, 等. 日长变化预报中BP神经网络拓扑结构的选择[J]. 中国科学院上海天文台年刊, 2007(28): 23-29. Wang Qijie, Liao Dechun, Zhou Yonghong, et al. Determination of the topology of the neural networks in the prediction of LOD[J]. Annals of Shanghai Astronomical Observatory Chinese Academy of Scinices, 2007(28): 23-29.
[8]	王宇谱, 吕志平. 小波神经网络日长预报算法研究[J]. 大地测量与地球动力学, 2012, 32(1): 127-131. Wang Yupu, Lü Zhiping. Research on algorithm of wavelet neural network for forecasting length of day[J]. Journal of Geodesy and Geodynamics, 2012, 32(1): 127-131.
[9]	许雪晴, 周永宏. 地球定向参数高精度预报方法研究[J]. 飞行器测控学报, 2010, 29(2): 70-76. Xu Xueqing, Zhou Yonghong. High precision prediction method of Earth orientation parameters[J]. Journal of Spacecraft TT & C Technology, 2010, 29(2): 70-76.
[10]	Liao D C, Wang Q J, Zhou Y H, et al. Long-term prediction of the Earth orientation parameters by the artificial neural network technique[J]. Journal of Geodynamics, 2012, 62: 87-92.
[11]	Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: a new learning scheme of feedforward neural networks[C]//Proceedings of 2004 IEEE International Joint Conference on Neural Networks. 2004: 985-990.
[12]	Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1-3): 489-501.
[13]	Akyilmaz O, Kutterer H. Prediction of Earth rotation parameters by fuzzy inference systems[J]. Journal of Geodesy, 2004, 78(1-2): 82-93.
[14]	Gérard P, Brain L. IERS conventions (2010) [R]. Germany: Verlag des Bundesamts für Kartographie und Geodasie, 2011: 123-131.