EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

From IMU Streams to Real-Time Decisions: Past-Only Next-Window Badminton Action Prediction

Qinglin Zhu, Jiao Wang, Bin Guo iD

Sensors · 08.06.2026 · 26 (12) · 3651

DOI: 10.3390/s26123651 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 08.06.2026. Verfasst von Qinglin Zhu und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Electrical Engineering, Sichuan University, Chengdu 610065, China. Hauptthemen laut MEDLINE: Racquet Sports. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We study real-time next-window badminton action prediction from wearable IMU streams where the system must predict the action label of the upcoming 100 ms window using past-only (causal) information. To handle severe class imbalance in continuous streams, we employ window-level downsampling of the dominant background class and compress multi-sensor time/frequency features using PCA before temporal modeling. We evaluate the full pipeline under a hop-based streaming protocol and show that our BiLSTM + MHSA model achieves high recognition performance (test accuracy 96.36%, Macro-F1 95.82%) while remaining deployable in real time, reaching 58.20 windows/s end to end (including preprocessing), i.e., 5.82× the real-time requirement (10 windows/s under a 100 ms output interval), on a Windows PC with an NVIDIA RTX 3080 GPU. These results support low-latency applications such as live coaching feedback and tactical analytics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Racquet SportsHumansAlgorithmsPrediction AlgorithmsWearable Electronic DevicesPrincipal Component Analysis

Stichwörter der Autor:innen

BiLSTMaction predictionbadmintoninertial measurement unit (IMU)principal component analysis (PCA)real-time inferenceself-attentiontime-series classificationwearable sensing

Autor:innen und Institutionen

  • College of Electrical Engineering, Sichuan University, Chengdu 610065, China.
  • College of Mechanical Engineering, Sichuan University, Chengdu 610065, China.

ORCID-Profile: Bin Guo

Zitieren

APA

Zhu, Q., Wang, J., & Guo, B. (2026). From IMU Streams to Real-Time Decisions: Past-Only Next-Window Badminton Action Prediction. Sensors, 26(12), 3651. https://doi.org/10.3390/s26123651

Vancouver

Zhu Q, Wang J, Guo B. From IMU Streams to Real-Time Decisions: Past-Only Next-Window Badminton Action Prediction. Sensors. 2026;26(12):3651. doi:10.3390/s26123651

BibTeX
@article{Zhu2026,
  author = {Zhu, Qinglin and Wang, Jiao and Guo, Bin},
  title = {From IMU Streams to Real-Time Decisions: Past-Only Next-Window Badminton Action Prediction},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {12},
  pages = {3651},
  doi = {10.3390/s26123651}
}
Kostenlos starten →