Within the sports domain, the athlete needs to prioritize and maximize performance while minimizing injuries and incidents. With this aim, in recent years, the research community has started to investigate how innovative solutions like the Internet of Things (IoT), Artificial Intelligence (AI), and Digital Twins could be utilized to monitor and improve the level of customization in athletes' training. This paper presents a Digital Twin architecture that combines IoT and AI techniques to create a dynamic digital copy of the athlete. By using physiological data captured by the wearable sensors, the proposed system can implement a Machine Learning(ML) layer of classification aiding in the detection of fatigue levels, one of the most important parameters that influence athletes' performances. The collected data can be used to enrich the dynamic digital copies of the athletes in order to create more realistic simulations and help the interested stakeholders in their mission of enabling athletes to reach their best performance without sacrificing their overall health. The system we propose enhances fatigue management research by utilizing non-intrusive digital scenarios.
A Digital Twin Architecture for Minimizing Injuries Risks with Personalized Regimens via IoT and Machine Learning
Mamen, Abdelkarim;Kovaci, Sara;Montanaro, Teodoro;Sergi, Ilaria;Patrono, Luigi
2024-01-01
Abstract
Within the sports domain, the athlete needs to prioritize and maximize performance while minimizing injuries and incidents. With this aim, in recent years, the research community has started to investigate how innovative solutions like the Internet of Things (IoT), Artificial Intelligence (AI), and Digital Twins could be utilized to monitor and improve the level of customization in athletes' training. This paper presents a Digital Twin architecture that combines IoT and AI techniques to create a dynamic digital copy of the athlete. By using physiological data captured by the wearable sensors, the proposed system can implement a Machine Learning(ML) layer of classification aiding in the detection of fatigue levels, one of the most important parameters that influence athletes' performances. The collected data can be used to enrich the dynamic digital copies of the athletes in order to create more realistic simulations and help the interested stakeholders in their mission of enabling athletes to reach their best performance without sacrificing their overall health. The system we propose enhances fatigue management research by utilizing non-intrusive digital scenarios.File | Dimensione | Formato | |
---|---|---|---|
DaIeeeXplore_A_Digital_Twin_Architecture_for_Minimizing_Injuries_Risks_with_Personalized_Regimens_via_IoT_and_Machine_Learning.pdf
solo utenti autorizzati
Tipologia:
Post-print referato (Refereed author’s manuscript)
Licenza:
NON PUBBLICO - Accesso privato/ristretto
Dimensione
292.27 kB
Formato
Adobe PDF
|
292.27 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.