EUVIMEDEUVIMED entdecken
Crossref

MSDIPN: Multi-Scale Deep Interval Prediction Network for Multivariate Time Series

Feng Jiang, Bo Wu, Shiping Wen, Tianhai Tian

IEEE Transactions on Knowledge and Data Engineering · 2025-09 · 37 (9) · 5452-5466

DOI: 10.1109/tkde.2025.3579406 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2025-09. Verfasst von Feng Jiang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Humanities and Social Science Research Foundation of the Ministry of Education of China, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Interval prediction is crucial in decision-making processes across many domains. Although significant progress has been made in existing interval prediction methods, they still face several challenges, such as assumptions about data distribution, fixed interval widths, limitations of gradient-based optimization algorithm, crossing of upper and lower bounds, and insufficient consideration of multi-scale spatial-temporal patterns. To address these issues, we propose a Multi-Scale Deep Interval Prediction Network (MSDIPN). Specifically, a Multi-Scale Spatio-Temporal Self-Attention Mechanism is introduced to capture spatio-temporal dependencies across different spatial scales. Additionally, a Temporal Self-Attention Mechanism module is constructed to extract temporal dependencies of historical variables across varying lag phases. Then a Global Self-Attention Mechanism module is designed to address representation degradation using residual connections and self-attention mechanisms. To overcome limitations related to distributional assumptions, fixed interval widths, and crossing problems, an Improved LUBE module is developed as the output module for generating prediction intervals (PIs) of time series data. Furthermore, a gradient-based PIs loss function is designed to address the optimization issue of MSDIPN by integrating a smooth approximation function with a pinball loss function. We validate the effectiveness of the proposed algorithm using five real-world datasets, demonstrating its superiority over traditional models.

Förderung

  • Humanities and Social Science Research Foundation of the Ministry of Education of China
  • National Natural Science Foundation of China

Zitieren

APA

Jiang, F., Wu, B., Wen, S., & Tian, T. (2025). MSDIPN: Multi-Scale Deep Interval Prediction Network for Multivariate Time Series. IEEE Transactions on Knowledge and Data Engineering, 37(9), 5452-5466. https://doi.org/10.1109/tkde.2025.3579406

Vancouver

Jiang F, Wu B, Wen S, Tian T. MSDIPN: Multi-Scale Deep Interval Prediction Network for Multivariate Time Series. IEEE Transactions on Knowledge and Data Engineering. 2025;37(9):5452-5466. doi:10.1109/tkde.2025.3579406

BibTeX
@article{Jiang2025,
  author = {Jiang, Feng and Wu, Bo and Wen, Shiping and Tian, Tianhai},
  title = {MSDIPN: Multi-Scale Deep Interval Prediction Network for Multivariate Time Series},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = {2025},
  volume = {37},
  number = {9},
  pages = {5452--5466},
  doi = {10.1109/tkde.2025.3579406}
}
Kostenlos starten →