|

AUCD Community Inclusion

AUCD’s Community Inclusion Team supports the University Centers for Excellence in Developmental Disabilities (UCEDD) Network in partnership with the Administration for Community Living.

Learn More
|

AUCD Maternal and Child Health Engagement

AUCD’s Maternal and Child Health Engagement supports the Autism CARES Programs, including LEND and DBP Programs.

Learn More
|

AUCD Public Health

AUCD’s Public Health Team works to create health promotion and public health efforts that include people with disabilities.

Learn More
|

AUCD Emerging Leaders Community

AUCD Emerging Leaders are a part of a community that includes trainees, early career professionals, self-advocates, and family members from AUCD member Centers and Programs.

Learn More

Donate

Product

Fusion with language models improves spelling accuracy for ERP-based brain computer interface spellers

Center:

OR-Oregon Institute on Development & Disability, UCEDD/LEND

Fiscal Year:

2012

Contact Information:

Melanie Fried-Oken
[email protected]
503-494-7587

Product Description:

In this paper, we study the effects of Bayesian fusion of an n-gram language model with a regularized discriminant analysis ERP detector for EEG-based BCIs. The letter classification accuracies are rigorously evaluated for varying language model orders as well as number of ERP-inducing trials. The results demonstrate that the language models contribute significantly to letter classification accuracy. Specifically, we find that a BCI-speller supported by a 4-gram language model may achieve the same performance using 3-trial ERP classification for the initial letters of the words and using single trial ERP classification for the subsequent ones. Overall, fusion of evidence from EEG and language models yields a significant opportunity to increase the word rate of a BCI based typing system.

Keyword(s):

electroencephalography, brain computer interface , Bayesian fusion, language model

Product/Publication Type(s):

Peer-reviewed publications in scholarly journals Published/In Press

Target Audience:

Professionals

Alternative Format:

To Obtain Copies (URL or Email):

http://www.ncbi.nlm.nih.gov/pubmed/22255652

COVID-19 Related Data:

N/A

1100 Wayne Avenue, Suite 1000 Silver Spring, MD 20910