Self-organizing deep belief modular echo state network for time series prediction

作者：

Highlights：

• The proposed model can automatically determine its structure.

• The proposed model is suitable for data containing noise and outliers.

• The proposed model achieves better prediction performance than other variant models.

摘要

•The proposed model can automatically determine its structure.•The proposed model is suitable for data containing noise and outliers.•The proposed model achieves better prediction performance than other variant models.

论文关键词：Time series prediction,Self-organizing mechanism,Deep belief network,Echo state network,Mutual information,Algal bloom

论文评审过程：Received 10 October 2020, Revised 4 January 2021, Accepted 29 March 2021, Available online 1 April 2021, Version of Record 12 April 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.107007