EEG classifier cross-task transfer to avoid training sessions in robot-assisted rehabilitation
Niklas Küper, Su-Kyoung Kim, Elsa Andrea Kirchner
In ArXiv e-prints, ArXiv, volume 11, pages 1-11, Feb/2024.

Zusammenfassung (Abstract) :

For an individualized support of patients during rehabilitation, learning of individual machine learning models from the human electroencephalogram (EEG) is required. Our approach allows labeled training data to be recorded without the need for a specific training session, which is important for the feasibility of using EEG to support exoskeleton-assisted therapy. For this, the planned exoskeleton-assisted rehabilitation enables bilateral mirror therapy, in which movement intentions can be inferred from the activity of the unaffected arm. During this therapy, labeled EEG data can be collected to enable movement predictions of only the affected arm of a patient based on the EEG and a proposed transfer learning approach in the second step.

Stichworte :

EEG; movement prediction; rehabilitation; classifier transfer; robot assisted therapy; lateralized readiness potential (LRP); event related potential (ERP); BCI; transfer learning

Files:

20241121_Kueper2024_EEG_classifier_cross_task.pdf


© DFKI GmbH
zuletzt geändert am 27.02.2023