This paper presents the integration of extended reality (XR) with brain-computer interfaces (BCI) to open up new possibilities in the health 4.0 framework. Such integrated systems are here investigated with respect to an active and a passive BCI paradigm. Regarding the active BCI, the XR part consists of providing visual and vibrotactile feedbacks to help the user during motor imagery tasks. Therefore, XR aims to enhance the neurofeedback by enhancing the user engagement. Meanwhile, in the passive BCI, user engagement monitoring allows the adaptivity of a XR-based rehabilitation game for children. Preliminary results suggest that the XR neurofeedback helps the BCI users to carry on motor imagery tasks with up to 84% classification accuracy, and that the level of emotional and cognitive engagement can be detected with an accuracy greater than 75%.
Active and Passive Brain-Computer Interfaces Integrated with Extended Reality for Applications in Health 4.0 / Arpaia, Pasquale; Esposito, Antonio; Mancino, Francesca; Moccaldi, Nicola; Natalizio, Angela. - 12980:(2021), pp. 392-405. (Intervento presentato al convegno International Conference on Augmented Reality, Virtual Reality and Computer Graphics tenutosi a Lecce, Italy nel September 7–10, 2021) [10.1007/978-3-030-87595-4_29].
Active and Passive Brain-Computer Interfaces Integrated with Extended Reality for Applications in Health 4.0
Esposito, Antonio;Natalizio, Angela
2021
Abstract
This paper presents the integration of extended reality (XR) with brain-computer interfaces (BCI) to open up new possibilities in the health 4.0 framework. Such integrated systems are here investigated with respect to an active and a passive BCI paradigm. Regarding the active BCI, the XR part consists of providing visual and vibrotactile feedbacks to help the user during motor imagery tasks. Therefore, XR aims to enhance the neurofeedback by enhancing the user engagement. Meanwhile, in the passive BCI, user engagement monitoring allows the adaptivity of a XR-based rehabilitation game for children. Preliminary results suggest that the XR neurofeedback helps the BCI users to carry on motor imagery tasks with up to 84% classification accuracy, and that the level of emotional and cognitive engagement can be detected with an accuracy greater than 75%.File | Dimensione | Formato | |
---|---|---|---|
SalentoAVR_2021__active_and_passive_XR_BCI (versione editoriale).pdf
non disponibili
Licenza:
Non specificato
Dimensione
1.05 MB
Formato
Adobe PDF
|
1.05 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.