AMSFormer: A transformer with adaptive multi-scale partitioning and multi-level spectral filtering for time-series forecasting
Authors:
- Honghao LiuHLHonghao Liu
- Yining DiaoYDYining Diao
- Ke SunKSKe Sun
- Zhaolin WanZWZhaolin Wan
- Zhiyang LiZLZhiyang Li
- 24 March 2025
- journal article
- Published by Elsevier in Neurocomputing
- Vol. 637
Abstract
No abstract availableFunding Information
- Natural Science Foundation of Heilongjiang Province (LH2024F018, 2023M740939)
- China Postdoctoral Science Foundation (GZB20230969)
- National Natural Science Foundation of China (62102059)
This publication has 18 references indexed in Scilit:
- TCM: An efficient lightweight MLP-based network with affine transformation for long-term time series forecastingNeurocomputing, 2024
- TF4TF: Multi-semantic modeling within the time–frequency domain for long-term time-series forecastingNeurocomputing, 2024
- FTMLP: MLP with Feature-Temporal Block for multivariate time series forecastingNeurocomputing, 2024
- GRAformer: A gated residual attention transformer for multivariate time series forecastingNeurocomputing, 2024
- Interpretable weather forecasting for worldwide stations with a unified deep modelNature Machine Intelligence, 2023
- Multi-scale receptive fields: Graph attention neural network for hyperspectral image classificationExpert Systems with Applications, 2023
- DeepAR: Probabilistic forecasting with autoregressive recurrent networksInternational Journal of Forecasting, 2020
- Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather stationSoft Computing, 2020
- A review and discussion of decomposition-based hybrid models for wind energy forecasting applicationsApplied Energy, 2019
- Prediction of global solar irradiance based on time series analysis: Application to solar thermal power plants energy production planningSolar Energy, 2010