EUVIMEDEUVIMED entdecken
BeobachtungsstudieOpen Access · CC BY 4.0

Artificial neural network predictive models for optimizing the training process in race walking: a longitudinal observational study

Dariusz Skalski, Magdalena Prończuk, Kinga Łosińska, Petr Stastny, Adam Maszczyk, Adam Zajac

PeerJ · 22.05.2026 · 14 · e21224

DOI: 10.7717/peerj.21224 ↗

Kurz gefasst

Beobachtungsstudie in der Zeitschrift PeerJ, online erschienen am 22.05.2026. Verfasst von Dariusz Skalski und 5 weiteren Autor:innen. Beteiligte Einrichtung: Gdańsk University of Physical Education and Sport, Gdansk, Poland. Hauptthemen laut MEDLINE: Neural Networks, Computer, Walking. Die Arbeit nennt 77 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study identified key physiological, biomechanical, and strength-related predictors of competitive performance in elite female race walkers and evaluated the effectiveness of classical and machine-learning models for individualized training optimization. Thirty nationally ranked female race walkers (25 ± 3 years) were assessed over four seasons (2021–2024). Laboratory and field tests included ergospirometry (VO 2 max, VCO2, VE (minute ventilation), respiratory exchange ratio (RER)), blood lactate (LA), heart rate (HR), gait kinematics (step length, speed), and lower-limb strength (1RM, maximal power). Temporal and seasonal dynamics were evaluated using Kruskal–Wallis and g-Fisher tests. Predictive models included multiple regression, polynomial regression, multilayer perceptron (MLP), and radial basis function (RBF) networks, developed with correlation-vector analysis (R0, R1), collinearity diagnostics, and interaction terms. The most influential predictors were HR, step length, VO 2 max, and 1RM (R0 > 0.70). RBF achieved the best predictive accuracy ( R 2 = 0.89; RMSE = 0.28), outperforming MLP ( R 2 = 0.87) and regression baselines ( R 2 = 0.61–0.81). Significant seasonal variation ( p < 0.001) underscored the value of time-dependent modeling. Conclusion: RBF neural networks offer superior performance for predicting race-walking outcomes; HR and step length are key real-time indicators, whereas VO 2 max and 1RM inform longer-term adaptation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerWalkingHumansFemaleLongitudinal StudiesPredictive Learning ModelsAdultPrediction AlgorithmsMultilayer PerceptronsHeart RateBiomechanical PhenomenaGaitRadial Basis Function Networks

Stichwörter der Autor:innen

Machine learningPhysiological monitoringRace walking performanceTraining adaptation

Autor:innen und Institutionen

  • Gdańsk University of Physical Education and Sport, Gdansk, Poland.
  • Department of Sport Games, Faculty of Physical Education and Sport, Charles University in Prague, Prague, Czech Republic.
  • Institute of Sport Science, The Jerzy Kukuczka Academy of Physical Education, Katowice, Poland.

Zitieren

APA

Skalski, D., Prończuk, M., Łosińska, K., Stastny, P., Maszczyk, A., & Zajac, A. (2026). Artificial neural network predictive models for optimizing the training process in race walking: a longitudinal observational study. PeerJ, 14, e21224. https://doi.org/10.7717/peerj.21224

Vancouver

Skalski D, Prończuk M, Łosińska K, Stastny P, Maszczyk A, Zajac A. Artificial neural network predictive models for optimizing the training process in race walking: a longitudinal observational study. PeerJ. 2026;14:e21224. doi:10.7717/peerj.21224

BibTeX
@article{Skalski2026,
  author = {Skalski, Dariusz and Prończuk, Magdalena and Łosińska, Kinga and Stastny, Petr and Maszczyk, Adam and Zajac, Adam},
  title = {Artificial neural network predictive models for optimizing the training process in race walking: a longitudinal observational study},
  journal = {PeerJ},
  year = {2026},
  volume = {14},
  pages = {e21224},
  doi = {10.7717/peerj.21224}
}
Kostenlos starten →