Researches on Time Series Prediction with Echo State Networks

FONT face; Verdana; PENG Yu; WANG Jian-min; PENG Xi-yuan; FONT

您当前的位置：

首页 >

文章列表页 >

Researches on Time Series Prediction with Echo State Networks

更新时间：2025-07-16

- Researches on Time Series Prediction with Echo State Networks
- Acta Electronica Sinica Vol. 38, Issue 2A, Pages: 148-154(2010)
- 作者机构：
  
  1. 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. 哈尔滨理工大学电子科学与技术系,黑龙江,哈尔滨,150080
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP183
- Published：2010
- 稿件说明：
移动端阅览
FONT face, Verdana, PENG Yu, et al. Researches on Time Series Prediction with Echo State Networks[J]. Acta Electronica Sinica, 2010, 38(2A): 148-154.
DOI：

FONT face, Verdana, PENG Yu, et al. Researches on Time Series Prediction with Echo State Networks[J]. Acta Electronica Sinica, 2010, 38(2A): 148-154. DOI：

摘要

<FONT face=Verdana>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.

Abstract

<FONT face=Verdana>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 not only the accuracy and efficiency but also the good generalities.

关键词

Keywords

references

Views

4627

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Review of Visibility Graph Methods Research in Time Series Complex Network Analysis

Chaos Identification and Prediction for Rain Attenuation Time Series

A Data Analysis Method for RFID Supply Chain Based on Time Series

An Piecewise Linear Fitting Algorithm for Infinite Time Series

Echo State Networks for Static Classification with Corresponding Clusters

Related Author

LIN Wei-bin

CAI Yu

ZHOU Wen-hao

WANG Jie

LI Hai-lin

TAO Hai-hong

ZHAI Sheng-hua

ZHANG Yi

Related Institution

College of Business， Quanzhou Normal University

College of Business Administration， Huaqiao University

National Laboratory of Radar Signal Processing,Xidian University

China Academy of Space Technology

[JZ]3.北京大学信息科学技术学院软件研究所高可信软件技术教育部重点实验室

⁰