TY - GEN
T1 - Analyzing power spectral of electroencephalogram (EEG) signal to identify motoric arm movement using EMOTIV EPOC+
AU - Bustomi, A.
AU - Wijaya, Sastra Kusuma
AU - Prawito, null
N1 - Publisher Copyright:
© 2017 Author(s).
PY - 2017/7/10
Y1 - 2017/7/10
N2 - Rehabilitation of motoric dysfunction from the body becomes the main objective of developing Brain Computer Interface (BCI) technique, especially in the field of medical rehabilitation technology. BCI technology based on electrical activity of the brain, allow patient to be able to restore motoric disfunction of the body and help them to overcome the shortcomings mobility. In this study, EEG signal phenomenon was obtained from EMOTIV EPOC+, the signals were generated from the imagery of lifting arm, and look for any correlation between the imagery of motoric muscle movement against the recorded signals. The signals processing were done in the time-frequency domain, using Wavelet relative power (WRP) as feature extraction, and Support vector machine (SVM) as the classifier. In this study, it was obtained the result of maximum accuracy of 81.3 % using 8 channel (AF3, F7, F3, FC5, FC6, F4, F8, and AF4), 6 channel remaining on EMOTIV EPOC + does not contribute to the improvement of the accuracy of the classification system.
AB - Rehabilitation of motoric dysfunction from the body becomes the main objective of developing Brain Computer Interface (BCI) technique, especially in the field of medical rehabilitation technology. BCI technology based on electrical activity of the brain, allow patient to be able to restore motoric disfunction of the body and help them to overcome the shortcomings mobility. In this study, EEG signal phenomenon was obtained from EMOTIV EPOC+, the signals were generated from the imagery of lifting arm, and look for any correlation between the imagery of motoric muscle movement against the recorded signals. The signals processing were done in the time-frequency domain, using Wavelet relative power (WRP) as feature extraction, and Support vector machine (SVM) as the classifier. In this study, it was obtained the result of maximum accuracy of 81.3 % using 8 channel (AF3, F7, F3, FC5, FC6, F4, F8, and AF4), 6 channel remaining on EMOTIV EPOC + does not contribute to the improvement of the accuracy of the classification system.
UR - http://www.scopus.com/inward/record.url?scp=85026251825&partnerID=8YFLogxK
U2 - 10.1063/1.4991175
DO - 10.1063/1.4991175
M3 - Conference contribution
AN - SCOPUS:85026251825
T3 - AIP Conference Proceedings
BT - International Symposium on Current Progress in Mathematics and Sciences 2016, ISCPMS 2016
A2 - Sugeng, Kiki Ariyanti
A2 - Triyono, Djoko
A2 - Mart, Terry
PB - American Institute of Physics Inc.
T2 - 2nd International Symposium on Current Progress in Mathematics and Sciences 2016, ISCPMS 2016
Y2 - 1 November 2016 through 2 November 2016
ER -