TY - GEN
T1 - Two frequencies sequential coding for the assr-based brain-computer interface application
AU - Cao, Guozhi
AU - Xie, Jun
AU - Xu, Guanghua
AU - Fang, Peng
AU - Du, Guangjing
AU - Li, Min
AU - Zhang, Qing
AU - Li, Guanglin
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2019/8
Y1 - 2019/8
N2 - Auditory steady state response (ASSR) based brain-computer interface (BCI) shows unique advantages compared with other BCIs such as steady-state visual evoked potentials (SSVEP) based BCI paradigm due to its visual-independent characteristic, and has attracted much attention from researchers. In this paper, a novel ASSR-based BCI using multiple frequencies sequential coding was proposed with the aim of improving the performance of conventional ASSR BCI. Each audio stimulus stream was modulated by two sequential frequencies, i.e., 4Hz and 13Hz for left ear stimulation and 5Hz and 9Hz for right ear stimulation. An experiment consisting of 200-trial offline task and 50-trial online task was performed for each subject and four subjects were recruited to participate in this study. Canonical correlation analysis (CCA) method was used in offline task to extract the ASSR response features, with which LDA model was trained. By applying the trained model to online task, we found that the accuracy of the proposed multiple frequencies sequential coding method is higher than that using the single frequency. And we also draw such a conclusion that the low frequency range can be used in ASSR-based BCIs. All of the results proved the feasibility of the proposed method to provide a new possible paradigm for practical ASSR BCI applications.
AB - Auditory steady state response (ASSR) based brain-computer interface (BCI) shows unique advantages compared with other BCIs such as steady-state visual evoked potentials (SSVEP) based BCI paradigm due to its visual-independent characteristic, and has attracted much attention from researchers. In this paper, a novel ASSR-based BCI using multiple frequencies sequential coding was proposed with the aim of improving the performance of conventional ASSR BCI. Each audio stimulus stream was modulated by two sequential frequencies, i.e., 4Hz and 13Hz for left ear stimulation and 5Hz and 9Hz for right ear stimulation. An experiment consisting of 200-trial offline task and 50-trial online task was performed for each subject and four subjects were recruited to participate in this study. Canonical correlation analysis (CCA) method was used in offline task to extract the ASSR response features, with which LDA model was trained. By applying the trained model to online task, we found that the accuracy of the proposed multiple frequencies sequential coding method is higher than that using the single frequency. And we also draw such a conclusion that the low frequency range can be used in ASSR-based BCIs. All of the results proved the feasibility of the proposed method to provide a new possible paradigm for practical ASSR BCI applications.
UR - https://www.scopus.com/pages/publications/85089143238
U2 - 10.1109/RCAR47638.2019.9044004
DO - 10.1109/RCAR47638.2019.9044004
M3 - 会议稿件
AN - SCOPUS:85089143238
T3 - 2019 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2019
SP - 170
EP - 174
BT - 2019 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2019
Y2 - 4 August 2019 through 9 August 2019
ER -