Real-Time Recognition of Feedback Error-Related Potentials during a Time-Estimation Task

Feedback error-related potentials are a promising brain process in the field of rehabilitation since they are related to human learning. Due to the fact that many therapeutic strategies rely on the presentation of feedback stimuli, potentials generated by these stimuli could be used to ameliorate the patient's progress. In this paper we propose a method that can identify, in real-time, feedback evoked potentials in a time-estimation task. We have tested our system with five participants in two different days with a separation of three weeks between them, achieving a mean single-trial detection performance of 71.62% for real-time recognition, and 78.08% in offline classification. Additionally, an analysis of the stability of the signal between the two days is performed, suggesting that the feedback responses are stable enough to be used without the needing of training again the user.

Published in:
Proceedings of the IEEE Engineering in Medicine and Biology Society (EMBC), 2670-3
Presented at:
IEEE Engineering in Medicine and Biology Society (EMBC), Buenos Aires, Argentina, 2010

 Record created 2015-02-18, last modified 2019-04-16

Download fulltext

Rate this document:

Rate this document:
(Not yet reviewed)