Use of a Bayesian maximum-likelihood classifier to generate training data for brain–machine interfaces
dc.contributor.author | Ludwig, Kip Allan | en_US |
dc.contributor.author | Miriani, Rachel M | en_US |
dc.contributor.author | Langhals, Nicholas Brandon | en_US |
dc.contributor.author | Marzullo, Timothy C. | en_US |
dc.contributor.author | Kipke, Daryl R. | en_US |
dc.date.accessioned | 2012-04-06T20:59:09Z | |
dc.date.available | 2012-04-06T20:59:09Z | |
dc.date.issued | 2011 | en_US |
dc.identifier.citation | Ludwig, Kip A; Miriani, Rachel M; Langhals, Nicholas B; Marzullo, Timothy C; Kipke, Daryl R (2011). "Use of a Bayesian maximum-likelihood classifier to generate training data for brain–machine interfaces." Journal of Neural Engineering, vol. 8, 4, 046009. <http://hdl.handle.net/2027.42/90824> | en_US |
dc.identifier.uri | http://stacks.iop.org/1741-2552/8/i=4/a=046009 | en_US |
dc.identifier.uri | https://hdl.handle.net/2027.42/90824 | |
dc.description.abstract | Brain–machine interface decoding algorithms need to be predicated on assumptions that are easily met outside of an experimental setting to enable a practical clinical device. Given present technological limitations, there is a need for decoding algorithms which (a) are not dependent upon a large number of neurons for control, (b) are adaptable to alternative sources of neuronal input such as local field potentials (LFPs), and (c) require only marginal training data for daily calibrations. Moreover, practical algorithms must recognize when the user is not intending to generate a control output and eliminate poor training data. In this paper, we introduce and evaluate a Bayesian maximum-likelihood estimation strategy to address the issues of isolating quality training data and self-paced control. Six animal subjects demonstrate that a multiple state classification task, loosely based on the standard center-out task, can be accomplished with fewer than five engaged neurons while requiring less than ten trials for algorithm training. In addition, untrained animals quickly obtained accurate device control, utilizing LFPs as well as neurons in cingulate cortex, two non-traditional neural inputs. | en_US |
dc.publisher | IOP Publishing | en_US |
dc.title | Use of a Bayesian maximum-likelihood classifier to generate training data for brain–machine interfaces | en_US |
dc.type | Article | en_US |
dc.subject.hlbsecondlevel | Physics | en_US |
dc.subject.hlbtoplevel | Science | en_US |
dc.description.peerreviewed | Peer Reviewed | en_US |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/90824/1/1741-2552_8_4_046009.pdf | |
dc.identifier.doi | 10.1088/1741-2552-8-4-046009 | en_US |
dc.identifier.source | Journal of Neural Engineering | en_US |
dc.owningcollname | Physics, Department of |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.