EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Smart Wearable Analytics for Cycling: AI-Based Physical Exertion Prediction

Aref Smiley, Joseph Finkelstein

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti250714 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Aref Smiley und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, The University of Utah, SLC, UT, USA. Hauptthemen laut MEDLINE: Physical Exertion, Bicycling, Wearable Electronic Devices, Deep Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We evaluated deep learning approaches for classification and regression prediction, focusing on an LSTM with Multi-Head Attention model. Data from 27 healthy participants performing cycling exercises were segmented into eight two-minute intervals. Heart rate, oxygen saturation, pedal speed (RPM), and HRV features (extracted from ECG in both frequency and time domains) served as predictive inputs. Rating of Perceived Exertion (RPE) was collected every minute and used as the predictive response, categorized into high and low exertion for classification. Physiological features and RPM from each segment were used to predict the next two-minute RPE. Feature selection via Minimum Redundancy Maximum Relevance (MRMR) and Univariate Feature Ranking (UFR) identified key predictors. The LSTM with Multi-Head Attention model achieved an MSE of 1.4 and R2 of 0.54 for regression and 82.9% accuracy with an F1 score of 86.3% for classification, demonstrating its effectiveness in exertion prediction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Physical ExertionBicyclingWearable Electronic DevicesDeep LearningHumansMaleHeart RateFemaleAdult

Stichwörter der Autor:innen

Heart rate variability (HRV)deep learningphysical exertion predictionwearable sensors

Autor:innen und Institutionen

  • Department of Biomedical Informatics, The University of Utah, SLC, UT, USA.

Zitieren

APA

Smiley, A., & Finkelstein, J. (2025). Smart Wearable Analytics for Cycling: AI-Based Physical Exertion Prediction. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250714

Vancouver

Smiley A, Finkelstein J. Smart Wearable Analytics for Cycling: AI-Based Physical Exertion Prediction. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250714

BibTeX
@article{Smiley2025,
  author = {Smiley, Aref and Finkelstein, Joseph},
  title = {Smart Wearable Analytics for Cycling: AI-Based Physical Exertion Prediction},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti250714}
}
Kostenlos starten →