Waveel: a wavelet-based ensemble learning framework for time series forecasting

Abstract With the booming development of the Internet of Things, billions of smart devices and sensors have generated massive amounts of time series data. Accurate time series forecasting (TSF) can help to uncover deep underlying patterns in the data. However, most existing TSF models focus on tempo...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaohou Shi, Tianxin Hu, Yuan Chang, Yaqi Song, Aobo Liang, Yan Sun
Format: Article
Language:English
Published: SpringerOpen 2025-07-01
Series:EURASIP Journal on Wireless Communications and Networking
Subjects:
Online Access:https://doi.org/10.1186/s13638-025-02479-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333969603002368
author Xiaohou Shi
Tianxin Hu
Yuan Chang
Yaqi Song
Aobo Liang
Yan Sun
author_facet Xiaohou Shi
Tianxin Hu
Yuan Chang
Yaqi Song
Aobo Liang
Yan Sun
author_sort Xiaohou Shi
collection DOAJ
description Abstract With the booming development of the Internet of Things, billions of smart devices and sensors have generated massive amounts of time series data. Accurate time series forecasting (TSF) can help to uncover deep underlying patterns in the data. However, most existing TSF models focus on temporal features and ignore the rich frequency information in time series data. Additionally, due to the non-stationarity of real-world data, previous works face challenges of adapting to diverse data distributions across domains, leading to difficulties in ensuring consistent performance and generalizability in varying scenarios. To address these issues, we propose a wavelet-based ensemble learning framework WaveEL for TSF. WaveEL converts time series data into wavelet domain coefficients while capturing both temporal and frequency domain features. We further integrate multiple TSF models and propose a weight decision maker for determining the weight of model combinations in TSF tasks. We conduct extensive experiments on seven real-world datasets and the results show that our model exhibits superior prediction performance.
format Article
id doaj-art-e4a5f09cb17640c8879ee0dc421e251f
institution Kabale University
issn 1687-1499
language English
publishDate 2025-07-01
publisher SpringerOpen
record_format Article
series EURASIP Journal on Wireless Communications and Networking
spelling doaj-art-e4a5f09cb17640c8879ee0dc421e251f2025-08-20T03:45:43ZengSpringerOpenEURASIP Journal on Wireless Communications and Networking1687-14992025-07-012025112010.1186/s13638-025-02479-4Waveel: a wavelet-based ensemble learning framework for time series forecastingXiaohou Shi0Tianxin Hu1Yuan Chang2Yaqi Song3Aobo Liang4Yan Sun5China Telecom Research InstituteComputer Science (National Pilot Software Engineering School), Beijing University of Posts and TelecommunicationsChina Telecom Research InstituteChina Telecom Research InstituteComputer Science (National Pilot Software Engineering School), Beijing University of Posts and TelecommunicationsComputer Science (National Pilot Software Engineering School), Beijing University of Posts and TelecommunicationsAbstract With the booming development of the Internet of Things, billions of smart devices and sensors have generated massive amounts of time series data. Accurate time series forecasting (TSF) can help to uncover deep underlying patterns in the data. However, most existing TSF models focus on temporal features and ignore the rich frequency information in time series data. Additionally, due to the non-stationarity of real-world data, previous works face challenges of adapting to diverse data distributions across domains, leading to difficulties in ensuring consistent performance and generalizability in varying scenarios. To address these issues, we propose a wavelet-based ensemble learning framework WaveEL for TSF. WaveEL converts time series data into wavelet domain coefficients while capturing both temporal and frequency domain features. We further integrate multiple TSF models and propose a weight decision maker for determining the weight of model combinations in TSF tasks. We conduct extensive experiments on seven real-world datasets and the results show that our model exhibits superior prediction performance.https://doi.org/10.1186/s13638-025-02479-4Time series forecastingDiscrete wavelet transformEnsemble learning
spellingShingle Xiaohou Shi
Tianxin Hu
Yuan Chang
Yaqi Song
Aobo Liang
Yan Sun
Waveel: a wavelet-based ensemble learning framework for time series forecasting
EURASIP Journal on Wireless Communications and Networking
Time series forecasting
Discrete wavelet transform
Ensemble learning
title Waveel: a wavelet-based ensemble learning framework for time series forecasting
title_full Waveel: a wavelet-based ensemble learning framework for time series forecasting
title_fullStr Waveel: a wavelet-based ensemble learning framework for time series forecasting
title_full_unstemmed Waveel: a wavelet-based ensemble learning framework for time series forecasting
title_short Waveel: a wavelet-based ensemble learning framework for time series forecasting
title_sort waveel a wavelet based ensemble learning framework for time series forecasting
topic Time series forecasting
Discrete wavelet transform
Ensemble learning
url https://doi.org/10.1186/s13638-025-02479-4
work_keys_str_mv AT xiaohoushi waveelawaveletbasedensemblelearningframeworkfortimeseriesforecasting
AT tianxinhu waveelawaveletbasedensemblelearningframeworkfortimeseriesforecasting
AT yuanchang waveelawaveletbasedensemblelearningframeworkfortimeseriesforecasting
AT yaqisong waveelawaveletbasedensemblelearningframeworkfortimeseriesforecasting
AT aoboliang waveelawaveletbasedensemblelearningframeworkfortimeseriesforecasting
AT yansun waveelawaveletbasedensemblelearningframeworkfortimeseriesforecasting