http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
근전도 신호 기반 사용자 맞춤 분류기와 선형보간법을 이용한 보행단계 예측기법
류재환(Jaehwan. Ryu),김상호(Sang-Ho Kim),이미란(Mi-Ran Lee),김덕환(Deok-Hwan Kim) 한국재활복지공학회 2014 한국재활복지공학회 학술대회논문집 Vol.2014 No.11
Recently, there have been many studies to bionic leg using physical sensor. But existing bionic leg have to move the same speed as training stage regardless of person’s intention. To solve this problem, a few sEMG signal based gait phase recognition studies are presented. However they didn’t supply real-time recognition for gait phase. In this paper, we propose a gait phase prediction using linear interpolation and user adaptive classification based on sEMG signal. Experimental results show that the average accuracy of user adaptive classification is about 81.4% whereas that of existing method is about 71.22%.
안면근육 표면근전도 신호기반 특징 및 근육 선별을 통한 단모음인식
이병현(Byeong-Hyeon Lee),류재환(Jaehwan Ryu),이미란(Miran Lee),김상호(Sangho Kim),Md Zia Uddin,김덕환(Deok-Hwan Kim) 대한전자공학회 2015 대한전자공학회 학술대회 Vol.2015 No.6
In this paper, we propose monophthong recognition method using feature and muscle selection based on facial surface EMG signals. We observed that EMG signal patterns may vary according to Korean monophthong pronunciation. The proposed method can recognize Korean monophthong and improve recognition accuracy by selecting muscle and feature rather than by using all of them. Experimental results show that the recognition accuracy of the proposed method using best muscle and best, second features set is better than that using all of muscles and features. The improved average accuracies are 29.13% in kNN, 34.52% in LDA.