• Default Ordering • Sorted by Date • Classified by Publication Type • Classified by Research Category •
Jan Hendrik Metzen, Su-Kyoung Kim, and Elsa Andrea Kirchner. Minimizing Calibration Time for Brain Reading. In Pattern Recognition, pp. 366–375, Lecture Notes in Computer Science 6835, Springer, August 2011. The original publication is available at www.springerlink.com under http://www.springerlink.com/content/731775n33wg062w2/fulltext.pdf
Machine learning is increasingly used to autonomously adapt brain-machineinterfaces to user-specific brain patterns. In order tominimize thepreparation time of the system, it is highly desirable to reduce the length ofthe calibration procedure, during which training data is acquired from the user,to a minimum. One recently proposed approach is to reuse models that have beentrained in historic usage sessions of the same or other users by utilizing anensemble-based approach. In this work, we propose two extensions of thisapproach which are based on the idea to combine predictions made bythe historic ensemble with session-specific predictions that become availableonce a small amount of training data has been collected. These extensions areparticularly useful for Brain Reading Interfaces (BRIs), a specific kindof brain-machine interfaces. BRIs do not require that userfeedback is given and thus, additional training data may be acquiredconcurrently to the usage session. Accordingly, BRIs should initiallyperform well when only a small amount of training data acquired in ashort calibration procedure is available and allow an increased performancewhen more training data becomes available during the usage session. Anempirical offline-study in a testbed for the use of BRIs to support robotictelemanipulation shows that the proposed extensions allow to achieve thiskind of behavior.
@inproceedings{Metzen:DAGM:2011,
author = {Jan Hendrik Metzen and {Su-Kyoung} Kim and Elsa Andrea Kirchner},
title = {Minimizing Calibration Time for Brain Reading},
booktitle = {Pattern Recognition},
series = {Lecture Notes in Computer Science},
publisher = {Springer Berlin / Heidelberg},
isbn = {978-3-642-23122-3},
pages = {366--375},
volume = {6835},
month = aug,
year = {2011},
publisher = {Springer},
location = {Heidelberg, Germany},
note={The original publication is available at www.springerlink.com under http://www.springerlink.com/content/731775n33wg062w2/fulltext.pdf},
abstract = {Machine learning is increasingly used to autonomously adapt brain-machine
interfaces to user-specific brain patterns. In order to
minimize the
preparation time of the system, it is highly desirable to reduce the length of
the calibration procedure, during which training data is acquired from the user,
to a minimum. One recently proposed approach is to reuse models that have been
trained in historic usage sessions of the same or other users by utilizing an
ensemble-based approach. In this work, we propose two extensions of this
approach which are based on the idea to combine predictions made by
the historic ensemble with session-specific predictions that become available
once a small amount of training data has been collected. These extensions are
particularly useful for Brain Reading Interfaces (BRIs), a specific kind
of brain-machine interfaces. BRIs do not require that user
feedback is given and thus, additional training data may be acquired
concurrently to the usage session. Accordingly, BRIs should initially
perform well when only a small amount of training data acquired in a
short calibration procedure is available and allow an increased performance
when more training data becomes available during the usage session. An
empirical offline-study in a testbed for the use of BRIs to support robotic
telemanipulation shows that the proposed extensions allow to achieve this
kind of behavior.},
Local-Url = "../files/DAGM_2011.pdf"
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