Skip to content
Conference

DTFNet: Dual-stage LSTM-Transformer fusion architecture for time series prediction

Aug 2026 · 2026 IEEE International Conference on Mechatronics and Automation (ICMA) · pp. 1436-1441 · 0 citations · 8 references

Abstract

Time series prediction plays a vital role across numerous real-world domains. However, existing methods struggle to simultaneously capture short-term temporal dynamics and long-term dependencies. To overcome this limitation, this paper proposes a Dual-stage Temporal Fusion Network, termed DTFNet, which realizes multi-scale timing modeling by integrating the architectural advantages of LSTM and Transformer. The model first employs LSTM with its inherent gating mechanism to extract local dynamic features from the sequence. Then, a lightweight cross-stage feature calibration module (CFC) is introduced to adaptively refine and recalibrate the feature distribution, making it more suitable for the input requirements of the Transformer. Finally, the hierarchical multi-headed self-attention module (HMSA) is used to efficiently capture the global contextual dependencies of the sequence in a windowed manner. Experimental results on the four benchmark datasets (ETTh1, ETTm1, Weather and ECL) show that DTFNet reduces the mean square error (MSE) by 2.2% to 3.7% compared with the state-of-the-art methods. Especially in the short sequence prediction task, compared to TimeMixer, the MSE is reduced by 3.8%, which demonstrates the effectiveness of the proposed dual-stage architecture in balancing short-term and long-term forecasting capabilities.

View source

Similar papers

Conference Aug 2026

A transformer encoder architecture for node-level time series forecasting

Experimental results show that the proposed model outperforms traditional RNN and LSTM models across various tasks, indicating promising potential for practical applications.

Ze Zhao, Ming-Yan Jiang, Feng Wang · 0 citations
Open access Sep 2026

FCA-Transformer: A Feature Pyramid Time Series Forecasting Model Driven by Cross-Attention Mechanism

The findings indicate that the proposed architecture successfully reconciles multi-scale feature extraction with lightweight dependency modeling, enhancing structural generalization and providing a scalable framework for real-time temporal analysis in complex industrial environments.

Lin-Li Wu, Ji-Yong Zhang, Zhi-Ming Zhang et al. · 0 citations
Open access 2026

CSSFormer-VaR: A Cross-Scale State-Space Deep Learning Framework for Robust Financial Value-at-Risk Forecasting

The model introduces a Mamba-Enhanced Multi-Scale Bidirectional Fusion module (MEMBA-F) and a Cross-Scale Contextual Attention Gating module (CSCAG) to jointly model global temporal dependencies and local fluctuation features, thereby enhancing the identification capability for extreme risk events.

Wei-Yan Tan · 0 citations
Open access Sep 2026

DST-SGR: a Mamba-inspired dual-stream spectro-temporal network for remaining useful life prediction of rotating machinery

Introduction Predicting the Remaining Useful Life (RUL) of rolling bearings is essential in predictive maintenance. High-frequency vibration signals present a dual-domain challenge, since impulses are most visible in the time domain while harmonics are most visible in time-frequency analysis. Existing approaches are li...

A. S. Gaurish Kumar, S. Madhavan, R. Dhanalakshmi · 0 citations
#artificial intelligence Preprint Sep 2026

SMart: A Multi-source Multi-phase Time Series Representation Transfer Framework

This work proposes a new TSRL framework, namely multi-source multi-phase time series representation transfer (SMart), which has two novel mechanisms to address the aforementioned deficiencies, and shows that SMart outperforms several state-of-the-art models for time series representation learning, classification and re...

Fang-Yue He, Wang-Chien Lee · 0 citations
Conference Aug 2026

Frequency-domain temporal transformer networks for state-of-charge estimation of Li-ion batteries

Accurate estimation of the state of charge (SOC) in lithium-ion batteries is crucial for ensuring the safe operation of new energy systems. Existing deep learning methods typically employ recurrent neural networks (RNNs) or Transformer-based architectures to encode temporal dependencies for SOC prediction. However, mos...

Xu-Tong Wan · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.