TY - GEN
T1 - Fusion with language models improves spelling accuracy for ERP-based brain computer interface spellers
AU - Orhan, Umut
AU - Erdogmus, Deniz
AU - Roark, Brian
AU - Purwar, Shalini
AU - Hild, Kenneth E.
AU - Oken, Barry
AU - Nezamfar, Hooman
AU - Fried-Oken, Melanie
PY - 2011
Y1 - 2011
N2 - Event related potentials (ERP) corresponding to a stimulus in electroencephalography (EEG) can be used to detect the intent of a person for brain computer interfaces (BCI). This paradigm is widely utilized to build letter-by-letter text input systems using BCI. Nevertheless using a BCI-typewriter depending only on EEG responses will not be sufficiently accurate for single-trial operation in general, and existing systems utilize many-trial schemes to achieve accuracy at the cost of speed. Hence incorporation of a language model based prior or additional evidence is vital to improve accuracy and speed. 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.
AB - Event related potentials (ERP) corresponding to a stimulus in electroencephalography (EEG) can be used to detect the intent of a person for brain computer interfaces (BCI). This paradigm is widely utilized to build letter-by-letter text input systems using BCI. Nevertheless using a BCI-typewriter depending only on EEG responses will not be sufficiently accurate for single-trial operation in general, and existing systems utilize many-trial schemes to achieve accuracy at the cost of speed. Hence incorporation of a language model based prior or additional evidence is vital to improve accuracy and speed. 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.
KW - Bayesian fusion
KW - Brain computer interfaces
KW - Event related potential
KW - Language model
UR - http://www.scopus.com/inward/record.url?scp=84862299633&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84862299633&partnerID=8YFLogxK
U2 - 10.1109/IEMBS.2011.6091429
DO - 10.1109/IEMBS.2011.6091429
M3 - Conference contribution
C2 - 22255652
AN - SCOPUS:84862299633
SN - 9781424441211
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 5774
EP - 5777
BT - 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
T2 - 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
Y2 - 30 August 2011 through 3 September 2011
ER -