Prediction for Chaotic Time Series-Based AE-CNN and Transfer Learning

It has been a hot and challenging topic to predict the chaotic time series in the medium-to-long term. We combine autoencoders and convolutional neural networks (AE-CNN) to capture the intrinsic certainty of chaotic time series. We utilize the transfer learning (TL) theory to improve the prediction...

Full description

Saved in:
Bibliographic Details
Main Authors: Baogui Xin, Wei Peng
Format: Article
Language:English
Published: Wiley 2020-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2020/2680480
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849683603756154880
author Baogui Xin
Wei Peng
author_facet Baogui Xin
Wei Peng
author_sort Baogui Xin
collection DOAJ
description It has been a hot and challenging topic to predict the chaotic time series in the medium-to-long term. We combine autoencoders and convolutional neural networks (AE-CNN) to capture the intrinsic certainty of chaotic time series. We utilize the transfer learning (TL) theory to improve the prediction performance in medium-to-long term. Thus, we develop a prediction scheme for chaotic time series-based AE-CNN and TL named AE-CNN-TL. Our experimental results show that the proposed AE-CNN-TL has much better prediction performance than any one of the following: AE-CNN, ARMA, and LSTM.
format Article
id doaj-art-d422c9c8d7094a8ca9ea2e1beedaf3e8
institution DOAJ
issn 1076-2787
1099-0526
language English
publishDate 2020-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-d422c9c8d7094a8ca9ea2e1beedaf3e82025-08-20T03:23:47ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/26804802680480Prediction for Chaotic Time Series-Based AE-CNN and Transfer LearningBaogui Xin0Wei Peng1College of Economics and Management, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Economics and Management, Shandong University of Science and Technology, Qingdao 266590, ChinaIt has been a hot and challenging topic to predict the chaotic time series in the medium-to-long term. We combine autoencoders and convolutional neural networks (AE-CNN) to capture the intrinsic certainty of chaotic time series. We utilize the transfer learning (TL) theory to improve the prediction performance in medium-to-long term. Thus, we develop a prediction scheme for chaotic time series-based AE-CNN and TL named AE-CNN-TL. Our experimental results show that the proposed AE-CNN-TL has much better prediction performance than any one of the following: AE-CNN, ARMA, and LSTM.http://dx.doi.org/10.1155/2020/2680480
spellingShingle Baogui Xin
Wei Peng
Prediction for Chaotic Time Series-Based AE-CNN and Transfer Learning
Complexity
title Prediction for Chaotic Time Series-Based AE-CNN and Transfer Learning
title_full Prediction for Chaotic Time Series-Based AE-CNN and Transfer Learning
title_fullStr Prediction for Chaotic Time Series-Based AE-CNN and Transfer Learning
title_full_unstemmed Prediction for Chaotic Time Series-Based AE-CNN and Transfer Learning
title_short Prediction for Chaotic Time Series-Based AE-CNN and Transfer Learning
title_sort prediction for chaotic time series based ae cnn and transfer learning
url http://dx.doi.org/10.1155/2020/2680480
work_keys_str_mv AT baoguixin predictionforchaotictimeseriesbasedaecnnandtransferlearning
AT weipeng predictionforchaotictimeseriesbasedaecnnandtransferlearning