EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Enhanced Transformer Encoder Using Inverted Stationarization Decomposition for Long-Term Multivariate Time Series Forecasting

Nasra Pratama Putra, Suprapto, Agus Sihabuddin

Engineering, Technology & Applied Science Research · 04.04.2026 · 16 (2) · 33179-33186

DOI: 10.48084/etasr.16535 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 04.04.2026. Verfasst von Nasra Pratama Putra und 2 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Autoformer is the first Transformer-based model employing auto-correlation and moving average decomposition to extract trend and seasonal patterns from time series data. Although effective in modeling complex temporal dependencies, these mechanisms show limited accuracy when applied to real-world multivariate time series that are highly non-stationary and lack clear periodicity. This limitation arises from the sensitivity of moving average-based decomposition to fluctuations and distribution shifts, as well as the inability of auto-correlation to capture inter-variable dependencies. To overcome these challenges, this study proposes an Inverted Stationarization Decomposition approach integrated with a Transformer encoder for long-term multivariate time series forecasting. The stationarization process reduces non-stationarity in the input data and restores appropriate statistical properties at the output stage, whereas the inverted embedding mechanism enables effective modeling of correlations among variables. The proposed approach was evaluated using the ETT dataset (four subsets), and the Exchange, Weather, ECL, and Traffic datasets. Experimental results demonstrate that the proposed model consistently outperforms Autoformer, achieving an average Mean Squared Error (MSE) reduction of 29.15% and an average Mean Absolute Error (MAE) reduction of 23.82% across all evaluated datasets.

Zitieren

APA

Putra, N. P., Suprapto, & Sihabuddin, A. (2026). An Enhanced Transformer Encoder Using Inverted Stationarization Decomposition for Long-Term Multivariate Time Series Forecasting. Engineering, Technology & Applied Science Research, 16(2), 33179-33186. https://doi.org/10.48084/etasr.16535

Vancouver

Putra NP, Suprapto, Sihabuddin A. An Enhanced Transformer Encoder Using Inverted Stationarization Decomposition for Long-Term Multivariate Time Series Forecasting. Engineering, Technology & Applied Science Research. 2026;16(2):33179-33186. doi:10.48084/etasr.16535

BibTeX
@article{Putra2026,
  author = {Putra, Nasra Pratama and Suprapto and Sihabuddin, Agus},
  title = {An Enhanced Transformer Encoder Using Inverted Stationarization Decomposition for Long-Term Multivariate Time Series Forecasting},
  journal = {Engineering, Technology & Applied Science Research},
  year = {2026},
  volume = {16},
  number = {2},
  pages = {33179--33186},
  doi = {10.48084/etasr.16535}
}
Kostenlos starten →