| 基于回声状态网络的时间序列预测方法研究 |
| |
| 引用本文： | 彭宇,王建民,彭喜元.基于回声状态网络的时间序列预测方法研究[J].电子学报,2010,38(Z1). |
| |
| 作者姓名： | 彭宇 王建民 彭喜元 |
| |
| 作者单位： | 1. 哈尔滨工业大学自动化测试与控制研究所,黑龙江哈尔滨,150001
2. 哈尔滨工业大学自动化测试与控制研究所,黑龙江哈尔滨,150001;哈尔滨理工大学电子科学与技术系,黑龙江哈尔滨,150080 |
| |
| 基金项目： | 装备预研重点基金，教育部高等学校博士学科点专项科研基金 |
| |
| 摘 要： | 针对回声状态网络(Echo State Networks,ESNs)输入序列延迟时间(和嵌入维数D的选择以及储备池的适应性问题,利用自相关性分析法从被预测样本序列构建ESNs网络输入,并通过移动通信话务量的预测问题,采用实验分析的方法讨论了储备池参数选择对于时间序列预测性能的影响.与采用ARMA和BP神经网络的预测方法相比,新方法在保证预测精度和效率的情况下,具有更好的泛化能力.
|
| 关 键 词： | 回声状态网络 自相关系数 时间序列 移动通信话务量 |
Researches on Time Series Prediction with Echo State Networks |
| |
| PENG Yu,WANG Jian-min,PENG Xi-yuan.Researches on Time Series Prediction with Echo State Networks[J].Acta Electronica Sinica,2010,38(Z1). |
| |
| Authors: | PENG Yu WANG Jian-min PENG Xi-yuan |
| |
| Affiliation: | PENG Yu1,WANG Jian-min1,2,PENG Xi-yuan1(1.Automatic Test and Control Institute,Harbin Institute of Technology,Harbin,Heilongjiang 150001,China,2.Department of Electronics Science and Technology,Harbin University of Science and Technology,Heilongjiang 150080,China) |
| |
| Abstract: | The choice of delay time and embedded dimension in time series modeling and prediction and the problem of reservoir adaption are challenges for Echo State Networks(ESNs).Correlation analysis is introduced to construct the inputs vector from the time series in ESNs networks.Moreover,the effects of different parameters settings on prediction performances in reservoir is analyzed by experiments of mobile communication traffic prediction.Compared with ARMA and BP neural networks,the proposed method can ensure n... |
| |
| Keywords: | echo state networks self-correlation coefficient time series mobile communications traffic |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
