Factor Echo State Network for Multivariate Chaotic Time Series Prediction
-
摘要: 针对采用回声状态网络预测多元混沌时间序列时存在的病态解问题, 本文建立了因子回声状态网络模型, 通过因子分析(Factor analysis, FA)方法提取高维储备池状态矩阵的公因子, 去除冗余和噪声成分. 利用降维后的因子变量与期望输出之间的线性回归关系, 求解网络未知参数. 基于Lorenz序列和大连月平均气温--降雨量的仿真实验验证了本文所提模型的有效性.Abstract: When an echo state network is used to predict multivariate time series, there may exist ill-posed problem. This paper proposes a novel prediction model, named factor echo state network, to solve the problem. It uses a factor analysis (FA) algorithm to extract the common factors of the reservoir matrix, and to remove the redundancies and noises. Then the unknown output weights are calculated by linear regression of the output and common factors. The model is used to predict Lorenz series and monthly average temperature-rainfall time series in Dalian, and simulation results substantiate its effectiveness.
-
Key words:
- Multivariate chaotic time series /
- prediction /
- echo state network /
- factor analysis (FA)
-
[1] Rong T Z, Xiao Z. Nonparametric interval prediction of chaotic time series and its application to climatic system. International Journal of Systems Science, 2013, 44(9): 1726-1732 [2] Han Min, Xu Mei-Ling, Ren Wei-Jie. Research on multivariate chaotic time series prediction using mRSM model. Acta Automatica Sinica, 2014, 40(5): 822-829(韩敏, 许美玲, 任伟杰. 多元混沌时间序列的相关状态机预测模型研究. 自动化学报, 2014, 40(5): 822-829) [3] [3] Inoussa G, Peng H, Wu J. Nonlinear time series modeling and prediction using functional weights wavelet neural network-based state-dependent AR model. Neurocomputing, 2012, 86(1): 59-74 [4] [4] Li P H, Li Y G, Xiong Q Y, Chai Y, Zhang Y. Application of a hybrid quantized Elman neural network in short-term load forecasting. International Journal of Electrical Power Energy Systems, 2014, 55: 749-759 [5] [5] Yeh W C. New parameter-free simplified swarm optimization for artificial neural network training and its application in the prediction of time series. IEEE Transactions on Neural Networks and Learning Systems, 2013, 24(4): 661-665 [6] Xuan Zhao-Yan, Yang Gong-Xun. Application of EMD in the atmoshere time series prediction. Acta Automatica Sinica, 2008, 34(1): 97-101(玄兆燕, 杨公训. 经验模态分解法在大气时间序列预测中的应用. 自动化学报, 2008, 34(1): 97-101) [7] [7] Zeng Z G, Wang J. Improved conditions for global exponential stability of recurrent neural networks with time-varying delays. IEEE Transactions on Neural Networks, 2006, 17(3): 623-635 [8] [8] Zhang H G, Liu J H, Ma D Z, Wang Z S. Data-core-based fuzzy min-max neural network for pattern classification. IEEE Transactions on Neural Networks, 2011, 22(12): 2339-2352 [9] [9] Zhang H G, Liu D R, Luo Y H, Wang D. Adaptive Dynamic Programming for Control: Algorithms and Stability. London: Springer, 2013. 1-19 [10] Jaeger H. The Echo State Approach to Analysing and Training Recurrent Neural Networks with An Erratum Note, GMD Report 148, German National Research Center for Information Technology, Germany, 2001. [11] Jaeger H, Haas H. Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science, 2004, 304(5667): 78-80 [12] Massar M, Massar S. Mean-field theory of echo state networks. Physical Review E, 2013, 87(4): 042809 [13] Lukosevičius M, Jaeger H, Schrauwen B. Reservoir computing trends. Kl-Knstliche Intelligenz, 2012, 26(4): 365-371 [14] Qiao Jun-Fei, Bo Ying-Chun, Han Guang. Application of ESN-based multi indices dual heuristic dynamic programming on wastewater treatment process. Acta Automatica Sinica, 2013, 39(7): 1146-1151(乔俊飞, 薄迎春, 韩广. 基于 ESN 的多指标 DHP 控制策略在污水处理过程中的应用. 自动化学报, 2013, 39(7): 1146-1151) [15] Shi Z W, Han M. Support vector echo-state machine for chaotic time-series prediction. IEEE Transactions on Neural Networks, 2007, 18(2): 359-372 [16] Chatzis S P, Demiris Y. Echo state Gaussian process. IEEE Transactions on Neural Networks, 2011, 22(9): 1435-1445 [17] Han Min, Wang Ya-Nan. Prediction of multivariate time series based on reservoir principal component analysis. Control and Decision, 2009, 24(10): 1526-1530(韩敏, 王亚楠. 基于储备池主成分分析的多元时间序列预测研究. 控制与决策, 2009, 24(10): 1526-1530) [18] Ghahramani Z, Hinton G E. The EM Algorithm for Mixtures of Factor Analyzers, Technical Report CRG-TR-96-1, University of Toronto, Canada, 1996. [19] He Liang, Shi Yong-Zhe, Liu Jia. Eigenchannel space combination method of joint factor analysis. Acta Automatica Sinica, 2011, 37(7): 849-856(何亮, 史永哲, 刘加. 联合因子分析中的本征信道空间拼接方法. 自动化学报, 2011, 37(7): 849-856) [20] Meng Qing-Fang, Peng Yu-Hua, Qu Huai-Jing, Han Min. The neighbor point selection method for local prediction based on information criterion. Acta Physica Sinica, 2008, 57(3): 1423-1430(孟庆芳, 彭玉华, 曲怀敬, 韩民. 基于信息准则的局域预测法邻近点的选取方法. 物理学报, 2008, 57(3): 1423-1430) [21] Yang Xu-Kui, Qu Dan, Zhang Wen-Lin. An orthogonal Laplacian language recognition approach. Acta Automatica Sinica, 2014, 40(8): 1812-1818(杨绪魁, 屈丹, 张文林. 正交拉普拉斯语种识别方法. 自动化学报, 2014, 40(8): 1812-1818) [22] Varadhan R, Roland C. Simple and globally convergent methods for accelerating the convergence of any EM algorithm. Scandinavian Journal of Statistics, 2008, 35(2): 335-353 [23] Mirmomeni M, Lucas C, Araabi B N, Moshiri B, Bidar M R. Recursive spectral analysis of natural time series based on eigenvector matrix perturbation for online applications. IET Signal Processing, 2011, 5(6): 515-526 [24] van der Maaten L J P, Postm E O, van den Herik H J. Dimensionality Reduction: a Comparative Review. Technical Report TiCC-TR 2009-005, Tilburg University, Tilburg, The Netherlands, 2009.
点击查看大图
计量
- 文章访问数: 2137
- HTML全文浏览量: 89
- PDF下载量: 1168
- 被引次数: 0