• Default Ordering • Sorted by Date • Classified by Publication Type • Classified by Research Category •
Jan Hendrik Metzen, Su Kyoung Kim, Timo Duchrow, Elsa Andrea Kirchner, and Frank Kirchner. On Transferring Spatial Filters in a Brain Reading Scenario. In Statistical Signal Processing Workshop (SSP), 2011 IEEE, pp. 797–800, June 2011.
(unavailable)
Machine learning approaches are increasingly used in brain-machine-interfaces toallow automatic adaptation to user-specific brainpatterns. One of the most crucial factors for the practical success of thesesystems is that this adaptation can be achieved with a minimum amount oftraining data since training data needs to be recorded during acalibration procedure prior to the actual usage session. To this end, onepromising approach is to reuse models based on data recorded in precedingsessions of the same or of other users. In this paper, we investigateunder which conditions it is favorable to reuse models (more specificallyspatial filters) trained on data from historic sessions compared to learning newspatial filters on the current session's calibration data. We present anempirical study in a scenario in which Brain Reading, a particular kind ofbrain-machine-interface, is used to support robotic telemanipulation.
@inproceedings{Metzen:SSP:2011,
title = {On Transferring Spatial Filters in a Brain Reading Scenario},
booktitle={Statistical Signal Processing Workshop (SSP), 2011 IEEE},
author = {Jan Hendrik Metzen and Su Kyoung Kim and Timo Duchrow and Elsa Andrea Kirchner and Frank Kirchner},
isbn = {978-1-4577-0569-4},
pages = {797--800},
month=jun,
year = {2011},
abstract = {Machine learning approaches are increasingly used in brain-machine-interfaces to
allow automatic adaptation to user-specific brain
patterns. One of the most crucial factors for the practical success of these
systems is that this adaptation can be achieved with a minimum amount of
training data since training data needs to be recorded during a
calibration procedure prior to the actual usage session. To this end, one
promising approach is to reuse models based on data recorded in preceding
sessions of the same or of other users. In this paper, we investigate
under which conditions it is favorable to reuse models (more specifically
spatial filters) trained on data from historic sessions compared to learning new
spatial filters on the current session's calibration data. We present an
empirical study in a scenario in which Brain Reading, a particular kind of
brain-machine-interface, is used to support robotic telemanipulation.},
bib2html_pubtype = {Refereed Conference},
bib2html_rescat = {Brain Computer Interface}
}
Generated by bib2html.pl (written by Patrick Riley ) on Thu May 23, 2013 11:36:00