Project Submission

[renatofnc]

Author

• Name: Renato Fonseca Nóbrega

• Affiliation: FH Kufstein

Keywords

• Heart rate variability
• overtraining
• machine learning

Abstract The strive to achieve new best performances is an intrinsic characteristic of humans. While training hard to succeed in sport can be seen as an admirable trait, too much sport without adequate recovery can be detrimental to the desired progress and lead potentially to fatigue and injury. The body embarks into a state of overtraining, where it has no chance of convalesce from intense and repetitive training. With the advent and propagation of wearables the collection of physiological data turned into a large-scale process. In almost every device heart rate variability (HRV) is gathered along other metrics. Changes at HRV may indicate an overtraining state. HRV combined with other parameters can be utilized as a basis for the use of machine learning techniques in order to detect patterns and predict training readiness.

.. Abstract_Renato_Fonseca.pdf

Full PDF: DOI, [Zenodo], Github Repo. Github Release Zenodo WholeTale Zenodo Github ..

[MHeini]

The article provides a thorough and well-informed discussion on the topic of heart rate variability (HRV) as a tool for assessing training readiness. The introduction effectively sets the stage for the importance of this issue in the athletic community and the potential consequences of overtraining. The use of wearables to collect physiological data, including HRV, is explained clearly and the idea of using HRV in conjunction with machine learning techniques to detect patterns and predict training readiness is intriguing and innovative. The article presents a strong case for the effectiveness of HRV in detecting overtraining and predicting training readiness, supported by relevant research studies and examples. The potential of machine learning techniques to improve the prediction of training readiness is particularly noteworthy. Overall, the article is well-written, informative, and presents a valuable contribution to the field. It is an excellent resource for anyone interested in the use of HRV as a tool for assessing training readiness.

[miticdalibor]

The present article "Heart rate variability for training readiness assessment" shows very deep insights about the prediction of heart variability rate using real-time data from smart devices and machine learning. By addressing the problem shows the importance of prediction of HRV in the medical research but also for athletes to improve their training more data-centered. Comparing different machine learning models, starting from ensemble models like Random Forest to more complex neural networks (CNN) gives valuable insights for data scientist, which are aiming to further research in this area. Furthermore, the article shows a lot of benefits using HRV detection and prediction. It would be interesting to show the social impact of continuous detection of HRV in the presentation, as people might get too "worried" about their data and get more stressed, if their training application shows out of limits. However, the very advanced article shows that the author has a lot of background knowledge in this research area. In general, this article gives fundamental insights for data scientists, which aim to further research the HRV prediction, as it shows the baseline of state-of-the-art models and architectures and therefore shows a valuable contribution in this research field.