TFMSNet: A time series forecasting framework with time–frequency analysis and multi-scale processing

被引：0

作者：

Song, Xin ^{[1
,2
]}

Zhang, Xianglong ^{[1
]}

Tian, Wang ^{[1
]}

Zhu, Qiqi ^{[1
]}

机构：

[1] School of Computer Science and Engineering, Northeastern University, No.11, Lane 3, Wenhua Road, Heping District, Liaoning, Shenyang

[2] Hebei Key Laboratory of Marine Perception Network and Data Processing, Northeastern University at Qinhuangdao, No.143, Taishan Road, Hebei, Qinhuangdao

来源：

Computers and Electrical Engineering | 2025年 / 123卷

关键词：

Discrete wavelet transform; Multi-scale analysis; Time series forecasting; Time–frequency analysis;

D O I：

10.1016/j.compeleceng.2025.110260

中图分类号：

学科分类号：

摘要：

Time series forecasting is crucial in various fields. When dealing with complex time series data, existing methods often focus on a single scale or overlook frequency domain information, leading to the loss of critical information. To address this, this paper proposes TFMSNet, a novel time series forecasting framework combining time–frequency analysis with multi-scale processing. The framework decomposes the data into seasonal and trend components. For the seasonal component, TFMSNet utilizes Discrete Wavelet Transform (DWT) to decompose the data into subsequences of different frequencies, combining this with patch-based encoding layers and Inverse DWT to finely capture and reconstruct time–frequency features. It then performs multi-scale analysis and forecasting. For the trend component, the framework achieves multi-resolution representations through downsampling and uses Multilayer Perceptrons (MLPs) for prediction. By integrating both frequency and time domain information and leveraging the multi-scale characteristics of the data, TFMSNet significantly enhances prediction accuracy and robustness. Across 70 results from seven datasets, TFMSNet achieves 48 best and 20 second-best results, demonstrating the best overall performance. © 2025 Elsevier Ltd

引用

共 39 条

[1] Fister D., Perez-Aracil J., Pelaez-Rodriguez C., Del Ser J., Salcedo-Sanz S., Accurate long-term air temperature prediction with machine learning models and data reduction techniques, Appl Soft Comput, 136, (2023)
[2] He Y., Zhu J., Wang S., A novel neural network-based multiobjective evolution lower upper bound estimation method for electricity load interval forecast, IEEE Trans Syst Man Cybern Syst, 54, pp. 3069-3083, (2024)
[3] Fang Z., Ma X., Pan H., Yang G., Arce G.R., Movement forecasting of financial time series based on adaptive LSTM-BN network, Expert Syst Appl, 213, (2023)
[4] Cheng Y., Xing W., Pedrycz W., Xian S., Liu W., NFIG-X: Nonlinear fuzzy information granule series for long-term traffic flow time-series forecasting, IEEE Trans Fuzzy Syst, 31, 10, pp. 3582-3597, (2023)
[5] Zhou Y., Zhao J., Song Y., Sun J., Fu H., Chu M., A seasonal–trend-decomposition-based voltage-source-inverter open-circuit fault diagnosis method, IEEE Trans Power Electr, 37, 12, pp. 15517-15527, (2022)
[6] Dudek G., STD: A seasonal-trend-dispersion decomposition of time series, IEEE Trans Knowl Data Eng, 35, 10, pp. 10339-10350, (2023)
[7] Zhang X., Jin X., Gopalswamy K., Gupta G., Park Y., Shi X., Et al., First de-trend then attend: Rethinking attention for time-series forecasting, arxiv, (2022)
[8] He R., Zhang L., Chew A.W.Z., Modeling and predicting rainfall time series using seasonal-trend decomposition and machine learning, Knowl-Based Syst, 251, (2022)
[9] Wu H., Hu T., Liu Y., Zhou H., Wang J., Long M., TimesNet: Temporal 2D-variation modeling for general time series analysis, International conference on learning representations, (2023)
[10] Barjasteh A., Ghafouri S.H., Hashemi M., A hybrid model based on discrete wavelet transform (DWT) and bidirectional recurrent neural networks for wind speed prediction, Eng Appl Artif Intell, 127, (2024)

← 1 2 3 4 →