Publikation

Movement identification based on exoskeleton sensor data for event marking of the electroencephalogram

Nils Eckardt, Marc Tabie, Anett Seeland, Elsa Andrea Kirchner, P. Rostalski

In: Student Conference Proceedings 2016: 5th Conference on Medical Engineering Science and 1st Conference on Medical Informatics. Student Conference on Medical Engineering Science 5th befindet sich and 1st Conference on Medical Informatics March 9-11 Lübeck Germany Seiten 151-154 ISBN 3945954185 Infinite Science Publishing 3/2016.

Abstrakt

In this paper, the development of an algorithm for movement identification based on exoskeleton sensor data is described. The exoskeleton is part of a project on post stroke rehabilitation. The algorithm shall be used to mark movement events in a simultaneously recorded electroencephalography stream as a replacement for external motion tracking. The angular values for each joint of the exoskeleton are utilized by the algorithm to calculate a threshold and decide, if a movement was done or not. The quality of the algorithm is evaluated with an experiment, where the subject has to do specific movements while wearing the exoskeleton. During the experiment, data from exoskeleton sensors, electroencephalography and motion tracking is recorded. The provisional results show, that the algorithm is able to detect the movements, but the threshold needs to be adapted to the status of the bearer. Subsequently, the algorithm gets embedded in a signal processing framework.

Projekte

20160906_Movement_identification_based_on_exoskeleton_sensor_data_for.pdf (pdf, 344 KB)

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence