TY - JOUR
T1 - Online classification algorithm for eye-movement-based communication systems using two temporal EEG sensors
AU - Belkacem, Abdelkader Nasreddine
AU - Shin, Duk
AU - Kambara, Hiroyuki
AU - Yoshimura, Natsue
AU - Koike, Yasuharu
N1 - Funding Information:
This work was supported by the Japan Intentional Cooperation Agency (JICA) and the Strategic Research Program for Brain Sciences by the Ministry of Education, Culture, Sports, Science and Technology of Japan . We would like to thank the experimental participants for their time and patience.
Publisher Copyright:
© 2014 Elsevier Ltd. All rights reserved.
PY - 2015/2
Y1 - 2015/2
N2 - Real-time classification of eye movements offers an effective mode for human-machine interaction, and many eye-based interfaces have been presented in the literature. However, such systems often require that sensors be attached around the eyes, which can be obtrusive and cause discomfort. Here, we used two electroencephalography sensors positioned over the temporal areas to perform real-time classification of eye-blink and five classes of eye movement direction. We applied a continuous wavelet transform for online detection then extracted some discriminable time-series features. Using linear classification, we obtain an average accuracy of 85.2% and sensitivity of 77.6% over all classes. The results showed that the proposed algorithm was efficient in the detection and classification of eye movements, providing high accuracy and low-latency for single trials. This work demonstrates the promise of portable eye-movement-based communication systems and the sensor positions, features extraction, and classification methods used.
AB - Real-time classification of eye movements offers an effective mode for human-machine interaction, and many eye-based interfaces have been presented in the literature. However, such systems often require that sensors be attached around the eyes, which can be obtrusive and cause discomfort. Here, we used two electroencephalography sensors positioned over the temporal areas to perform real-time classification of eye-blink and five classes of eye movement direction. We applied a continuous wavelet transform for online detection then extracted some discriminable time-series features. Using linear classification, we obtain an average accuracy of 85.2% and sensitivity of 77.6% over all classes. The results showed that the proposed algorithm was efficient in the detection and classification of eye movements, providing high accuracy and low-latency for single trials. This work demonstrates the promise of portable eye-movement-based communication systems and the sensor positions, features extraction, and classification methods used.
KW - Brain-computer interface (BCI)
KW - EOG-related applications
KW - Electrooculography (EOG)
KW - Eye movements Electroencephalogram (EEG)
KW - Online classification
KW - Wearable sensors
UR - http://www.scopus.com/inward/record.url?scp=84978025365&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84978025365&partnerID=8YFLogxK
U2 - 10.1016/j.bspc.2014.10.005
DO - 10.1016/j.bspc.2014.10.005
M3 - Article
AN - SCOPUS:84978025365
SN - 1746-8094
VL - 16
SP - 40
EP - 47
JO - Biomedical Signal Processing and Control
JF - Biomedical Signal Processing and Control
ER -