Design of an auditory P300 BCI speller for the Japanese Hiragana syllabary
-
1
Research Institute of National Rehabilitation Center for Persons with Disabilities, Department of Rehabilitation for Brain Function, Japan
-
2
The University of Electro-Communications, Brain Science Inspired Life Support Research Center, Japan
Persons with disabilities that affect communication may benefit from using a brain-computer interface (BCI) for communication. In some cases, the ability to attend to visual stimulation may also be affected. These persons then require a BCI that does not depend on visual stimuli (Käthner et al., 2013). In this abstract we propose using auditory stimulation to enable the selection of syllables from the Japanese Hiragana syllabary. Previous designs have also used the Hiragana syllabary as stimuli (Madarame et al., 2008, Chang et al., 2014). In this study we attempted to show the possibility of selecting from the 46 characters of the modern Japanese Hiragana syllabary using auditory stimuli with spatial cues, delivered over conventional stereo headphones and integrated into an online capable BCI framework. To our advantage, the Hiragana syllabary is constructed around a 5 × 10 matrix called the “fifty sounds” which can be used to implement an intuitive hierarchical selection approach for an auditory P300 speller. In this matrix the syllables are grouped according to the consonant they begin with and the vowel at the end. In the approach we propose the user will select the vowel first (a choice of one out of five) and then the consonant. Spatial cues were added to the stimuli according to the methods described in Käthner et al. (2013).
We investigated the feasibility of the design with a single healthy participant over three sessions on separate days. In the first session the participant selected ten Hiragana syllables, in sessions two and three twenty syllables. Offline classification of the data was performed separately for vowels, consonants and finally syllables. Vowel selection was between 66% (2.6 bits/min; session two) and 83% (3.7 bits/min; session three). The highest information transfer rate (ITR) with a simultaneous accuracy above 70% was in session two after five stimulus repetitions (4.9 bits/min). The consonant selection accuracy was between 60% (2.1 bits/min; session three) and 73% (2.7 bits/min; session one). The latter was also the highest ITR with an accuracy above 70%. Consequently, Hiragana selection accuracy was also the highest for session one (63%; 2.5 bits/min) but did not surpass 70% accuracy. Nonetheless, this is above the chance level of 2.2%. The participant achieved high accuracies during vowel selection, but this decreased considerably for con- sonant selection. Despite the need to further improve the speed and usability of the system and increase the validity of the results by collecting further data, the ITRs achieved during vowel selection are already comparable to what is achieved with other state-of-the-art auditory BCI systems.
References
Chang, M., Mori, K., Makino, S., and Rutkowski, T. M. (2014). Spatial auditory two-step input japanese syllabary brain-computer interface speller. Procedia Technology, 18:25–31.
Käthner, I., Ruf, C., Pasqualotto, E., Braun, C., Birbaumer, N., and Halder, S. (2013). A portable auditory P300 brain-computer interface with directional cues. Clin Neurophysiol, 124(2):327–38.
Madarame, T., Tanaka, H., Inoue, T., Kamata, M., and Shino, M. (2008). The development of a brain computer interface device for amyotrophic lateral sclerosis patients. In Systems, Man and Cybernetics, 2008. SMC 2008. IEEE International Conference on, pages 2401–2406. IEEE.
Keywords:
brain-computer interface (BCI),
visual stimulation,
auditory stimulation,
Hiragana,
spatial cues
Conference:
2015 International Workshop on Clinical Brain-Machine Interfaces (CBMI2015), Tokyo, Japan, 13 Mar - 15 Mar, 2015.
Presentation Type:
Poster 2-3
Topic:
Clinical Brain-Machine Interfaces
Citation:
Halder
S,
Ora
H and
Kansaku
K
(2015). Design of an auditory P300 BCI speller for the Japanese Hiragana syllabary.
Conference Abstract:
2015 International Workshop on Clinical Brain-Machine Interfaces (CBMI2015).
doi: 10.3389/conf.fnhum.2015.218.00022
Copyright:
The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers.
They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.
The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.
Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.
For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.
Received:
23 Apr 2015;
Published Online:
29 Apr 2015.
*
Correspondence:
Dr. Kenji Kansaku, Research Institute of National Rehabilitation Center for Persons with Disabilities, Department of Rehabilitation for Brain Function, Tokorozawa, Saitama, Japan, kansakuk@dokkyomed.ac.jp