EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dairy Product Production Prediction Based on BiLSTM-Attention model

Xiangyuan Qi, Guanglei Qiang, Fujiang Yuan

Journal of Computer Science and Digital Technology · 2025

DOI: 10.71204/by8g5g40 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computer Science and Digital Technology, 2025. Verfasst von Xiangyuan Qi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid development of the dairy industry, accurate prediction of production is crucial to optimizing production plans. To this end, this paper proposes a prediction model that combines a bidirectional long short-term memory network (BiLSTM) with an attention mechanism (Attention). BiLSTM can effectively capture long-term and short-term dependencies in time series, while the attention mechanism can dynamically focus on the features of key time points, thereby improving prediction accuracy. Experiments show that the BiLSTM-Attention model improves the accuracy of dairy production prediction compared to traditional regression analysis and a single LSTM model, especially when processing long time series data. This study provides an effective solution for the accurate prediction of dairy production.

Zitieren

APA

Qi, X., Qiang, G., & Yuan, F. (2025). Dairy Product Production Prediction Based on BiLSTM-Attention model. Journal of Computer Science and Digital Technology. https://doi.org/10.71204/by8g5g40

Vancouver

Qi X, Qiang G, Yuan F. Dairy Product Production Prediction Based on BiLSTM-Attention model. Journal of Computer Science and Digital Technology. 2025. doi:10.71204/by8g5g40

BibTeX
@article{Qi2025,
  author = {Qi, Xiangyuan and Qiang, Guanglei and Yuan, Fujiang},
  title = {Dairy Product Production Prediction Based on BiLSTM-Attention model},
  journal = {Journal of Computer Science and Digital Technology},
  year = {2025},
  doi = {10.71204/by8g5g40}
}
Kostenlos starten →