Loading [MathJax]/extensions/MathMenu.js
Error-Driven Chained Multiple-Subnetwork Echo State Network for Time-Series Prediction | IEEE Journals & Magazine | IEEE Xplore

Error-Driven Chained Multiple-Subnetwork Echo State Network for Time-Series Prediction


Abstract:

Hybrid echo state networks (ESNs), a type of modified ESN, have been developed to improve the prediction accuracy of ESNs. However, they have been criticized for their co...Show More

Abstract:

Hybrid echo state networks (ESNs), a type of modified ESN, have been developed to improve the prediction accuracy of ESNs. However, they have been criticized for their computational complexity, which makes it difficult to use them directly in industrial applications. In this article, an error-driven chained multiple-subnetwork ESN (CESN) is proposed to build a simple structured hybrid network and improve its prediction accuracy. For this reason, a chain topology is generated to gradually reduce the residual error, while each subnetwork is trained separately. The weight matrix for each subnetwork does not need to be optimized, which reduces the computational cost. Meanwhile, the optimal number of subnetworks is determined on the basis of a given application. The efficiency of the proposed CESN is tested on a Santa Fe Laser and a public building dataset. Compared with ESN, 70% of the test data have been optimized by CESN for the public building dataset.
Published in: IEEE Sensors Journal ( Volume: 22, Issue: 20, 15 October 2022)
Page(s): 19533 - 19542
Date of Publication: 25 August 2022

ISSN Information:

Funding Agency:


References

References is not available for this document.