A wireless and wearable device with a low number of channels and dry electrodes is proposed for EEG-based attention assessment during motor-rehabilitation tasks. The system is a part of an instrument for real-time engagement assessment in rehabilitation 4.0. An experimental campaign on nine volunteers was realized for metrologically characterizing the system. Common Spatial Pattern (CSP) algorithm was used for features selection from the brain signal. The performance of three different supervised classifiers for distracted and non-distracted conditions were compared. The higher accuracy, 71.63±3.43 %, was obtained by the k-Nearest Neighbors classifier.
EEG-based attention assessment in motor-rehabilitation / Apicella, A.; Arpaia, P.; Frosolone, M.; Improta, G.; Isgro, F.; Moccaldi, N.; Natalizio, A.. - (2020), pp. 17-22. (Intervento presentato al convegno 24th IMEKO TC4 International Symposium and 22nd International Workshop on ADC and DAC Modelling and Testing, IWADC 2020 tenutosi a ita nel 2020).
EEG-based attention assessment in motor-rehabilitation
Apicella A.;Arpaia P.;Frosolone M.;Improta G.;Isgro F.;Moccaldi N.;
2020
Abstract
A wireless and wearable device with a low number of channels and dry electrodes is proposed for EEG-based attention assessment during motor-rehabilitation tasks. The system is a part of an instrument for real-time engagement assessment in rehabilitation 4.0. An experimental campaign on nine volunteers was realized for metrologically characterizing the system. Common Spatial Pattern (CSP) algorithm was used for features selection from the brain signal. The performance of three different supervised classifiers for distracted and non-distracted conditions were compared. The higher accuracy, 71.63±3.43 %, was obtained by the k-Nearest Neighbors classifier.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
