TY - GEN
T1 - Initial assessment of artifact filtering for rsvp keyboard™
AU - Haghighi, Marzieh
AU - Akcakaya, Murat
AU - Orhan, Umut
AU - Erdogmus, Deniz
AU - Okeny, Barry
AU - Fried-Okeny, Melanie
PY - 2013
Y1 - 2013
N2 - RSVP KeyboardTM is an electroencephalography (EEG)-based spelling interface that uses evoked response potential classification with the help of language models. As in any brain computer interface, severe physiological and environmental signal artifacts that affect signal quality in EEG are a detriment to performance. To alleviate the negative effects of such artifacts on RSVP KeyboardTM, we implemented a filter that is based on an existing methodology from the literature. Using statistical modeling of pre-recorded EEG that includes three types of artifacts intentionally generated by operators, we perform Monte Carlo simulations of copy-phrase tasks and analyze the effect of artifact filtering on estimated typing performance. The presented results demonstrate an evidence against the usability of the tested method for online artifact reduction applications.
AB - RSVP KeyboardTM is an electroencephalography (EEG)-based spelling interface that uses evoked response potential classification with the help of language models. As in any brain computer interface, severe physiological and environmental signal artifacts that affect signal quality in EEG are a detriment to performance. To alleviate the negative effects of such artifacts on RSVP KeyboardTM, we implemented a filter that is based on an existing methodology from the literature. Using statistical modeling of pre-recorded EEG that includes three types of artifacts intentionally generated by operators, we perform Monte Carlo simulations of copy-phrase tasks and analyze the effect of artifact filtering on estimated typing performance. The presented results demonstrate an evidence against the usability of the tested method for online artifact reduction applications.
KW - Artifact Filtering
KW - EEG
KW - ERP. Language Model
KW - Independent Component Analysis
KW - Kernel Density Estimate
UR - https://www.scopus.com/pages/publications/84897680661
UR - https://www.scopus.com/pages/publications/84897680661#tab=citedBy
U2 - 10.1109/SPMB.2013.6736777
DO - 10.1109/SPMB.2013.6736777
M3 - Conference contribution
AN - SCOPUS:84897680661
SN - 9781479930074
T3 - 2013 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2013
BT - 2013 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2013
PB - IEEE Computer Society
T2 - 2013 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2013
Y2 - 7 December 2013 through 7 December 2013
ER -