DocumentCode :
3684325
Title :
Event-related modulation of steady-state visual evoked potentials for eyes-closed brain computer interface
Author :
Seiji Nishifuji;Yuya Sugita;Hitoshi Hirano
Author_Institution :
Department of Electrical and Electronic Engineering, Yamaguchi University, Ube, 755-8611 JAPAN
fYear :
2015
Firstpage :
1918
Lastpage :
1921
Abstract :
Brain computer interfaces (BCIs), also be referred to be as brain machine interfaces, transform modulations of electroencephalogram (EEG) into user´s intents to communicate with others without voice and physical movement. BCIs have been studied and developed as one of the important means for communication-aid between disabled with severe motor disabilities such as amyotrophic lateral sclerosis and muscular dystrophy patients and their caregivers. State-of-art BCIs have achieved the outstanding performance in information transfer rate and classification accuracy. However, most of conventional BCIs are still unavailable for patients with impaired oculomotor control due to requirement of visual modality. The present study aimed at developing a novel 2-class BCI which was independent of oculomotor control including eye-opening using event-related modulation of steady state visual evoked potential (SSVEP) associated with mental tasks under eyes-closed condition. Eleven healthy subjects aged 21-24 years old were recruited and directed to perform each of two mental tasks under an eyes-closed condition; mental focus on flicker stimuli and image recall of their favorite animals, respectively. The magnitudes of SSVEP in the posterior regions of almost all the subjects were seen to be modulated by performing the mental tasks under the conditions of the flickering frequency of 10 Hz and stimulus intensity of 3-5 lx, which was used to express a user´s binary intent, namely, performing one of the mental tasks or not (rest). The classification performance on the mental focus, 80 %, was larger than that on the image recall, 75 %, in average across all the subjects. Shortening of the data length used for classification would improve the information transfer rate of the proposed BCI.
Keywords :
"Modulation","Electroencephalography","Brain-computer interfaces","Electrodes","Visualization","Steady-state","Accuracy"
Publisher :
ieee
Conference_Titel :
Engineering in Medicine and Biology Society (EMBC), 2015 37th Annual International Conference of the IEEE
ISSN :
1094-687X
Electronic_ISBN :
1558-4615
Type :
conf
DOI :
10.1109/EMBC.2015.7318758
Filename :
7318758
Link To Document :
بازگشت