Application of Multi-step Iterative ESN Method in Data Forecasting

DOI

10.2991/wartia-18.2018.77How to use a DOI?

Keywords

Single-step prediction, multi-step direct prediction, multi-step iterative prediction, data prediction

Abstract

Aiming at the application of echo state network in the field of data prediction, the hierarchical structure and parameter configuration of echo state network are analyzed in detail. On this basis, the three processes of ESN single-step prediction, ESN multi-step direct prediction and ESN multi - step iterative prediction are constructed and compared with the experimental results of three different sequence data. Experimental results show that compared with ESN single-step prediction and ESN multi-step direct prediction, ESN multi-step prediction has higher prediction accuracy and more practical in the field of data prediction.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Shuang Liu
AU  - Jianming Sun
PY  - 2018/09
DA  - 2018/09
TI  - Application of Multi-step Iterative ESN Method in Data Forecasting
BT  - Proceedings of the 4th Workshop on Advanced Research and Technology in Industry (WARTIA 2018)
PB  - Atlantis Press
SP  - 419
EP  - 423
SN  - 2352-5401
UR  - https://doi.org/10.2991/wartia-18.2018.77
DO  - 10.2991/wartia-18.2018.77
ID  - Liu2018/09
ER  -