The objective of this work is to describe and test a hand rehabilitation device with particular attention to the key ingredients for a successful neuro-motor rehabilitation training identified in literature, and in particular: i) adjunctive high duration and intensity therapy sessions; ii) functional orientation of the training; and iii) patient active involvement. The developed system is composed by a PC, the Gloreha hand rehabilitation glove along with its dedicated screen for visual feedback during movements execution, and the MYO armband for EMG signals recording. Multiple degrees-of-freedom hand grasp movements (i.e., grasping, grasp an object, pinching, wave) were predicted by means of surface EMG signals. Two cascaded artificial neural networks were exploited to detect the patient’s motion intention from the EMG signal window starting from the electrical activity onset up to the movement onset. The proposed approach was tested on nine healthy control subjects (7 females; age range 16-93 years) and it demonstrated an overall mean ± SD testing performance of 80% ± 13% for correctly predicting healthy users’ motion intention. A pilot post-stroke patient obtained a percentage of correctly classified tasks of 67% ± 16%. The classifier performance was negatively correlated with age, with the pilot patient behaving similarly to more aged participants.
EMG-Controlled Hand Rehabilitation Device for Clinical and Domestic Use: Intensive and Repetitive Training with Patient Active Participation
GANDOLLA, MARTA;FERRANTE, SIMONA;PEDROCCHI, ALESSANDRA LAURA GIULIA
2016-01-01
Abstract
The objective of this work is to describe and test a hand rehabilitation device with particular attention to the key ingredients for a successful neuro-motor rehabilitation training identified in literature, and in particular: i) adjunctive high duration and intensity therapy sessions; ii) functional orientation of the training; and iii) patient active involvement. The developed system is composed by a PC, the Gloreha hand rehabilitation glove along with its dedicated screen for visual feedback during movements execution, and the MYO armband for EMG signals recording. Multiple degrees-of-freedom hand grasp movements (i.e., grasping, grasp an object, pinching, wave) were predicted by means of surface EMG signals. Two cascaded artificial neural networks were exploited to detect the patient’s motion intention from the EMG signal window starting from the electrical activity onset up to the movement onset. The proposed approach was tested on nine healthy control subjects (7 females; age range 16-93 years) and it demonstrated an overall mean ± SD testing performance of 80% ± 13% for correctly predicting healthy users’ motion intention. A pilot post-stroke patient obtained a percentage of correctly classified tasks of 67% ± 16%. The classifier performance was negatively correlated with age, with the pilot patient behaving similarly to more aged participants.File | Dimensione | Formato | |
---|---|---|---|
_DEF_pubblicato.pdf
Accesso riservato
Descrizione: Articolo principale
:
Publisher’s version
Dimensione
401.5 kB
Formato
Adobe PDF
|
401.5 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.