http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Emotiv EPOC측정 DWT기반 EEG신호 분석을 통한 동작 이분 분류
선지영(Ji-Young Sun),한효정(Hyo-Jeung Han) 대한전자공학회 2015 대한전자공학회 학술대회 Vol.2015 No.11
By using Emotiv EPOC as EEG measurement tool , an improved classification algorithm for binary human motion recognition is implemented in this paper. EEG signals were collected using 14 channels from 44 trials for 8 seconds each. The raw EEG signals are preprocessed using Butterworth low pass filtering method and decomposed into three selected frequency band(alpha, beta, gamma, delta, theta) using Discrete Wavelet Transformation. Linear Discriminant Analysis with different number of component values are used to reduce dimensions, and Linear/RBF support vector machine are used as final classification method. We proposed three feature extraction method(ALREE and standard deviation for each frequency band, average of power). The experimental results indicate that butterworth-filtered Gamma signal processed by standard deviation feature with linear SVM gives maximum classification rate of 75%.