Transient EMG 신호를 이용한 손가락의 움직임 추정

다국어 초록 (Multilingual Abstract)

In this paper, we propose a deep learning model for estimating finger movements based on EMG signals. We have also evaluated and analyzed the accuracy of the model. We have applied the U-Net structure, which is widely used in medical image analysis, to our model. In general, U-Net is mainly used for processing of two-dimensional images. However, in this paper, 8-channel one-dimensional time series EMG data is used as inputs, and information about finger movement is obtained as results. We have acquired the data set consisting of 8,000 motions, which is divided into the training and evaluation data sets. The accuracy of the prediction of our model is about 89.32%.

참고문헌 (Reference)

1 임상헌 ; 김영재 ; 김광기, "딥 러닝 기반의 영상분할 알고리즘을 이용한 의료영상 3차원 시각화에 관한 연구" 한국멀티미디어학회 23 (23): 468-475, 2020

2 김성중 ; 이한수 ; 김종만 ; 안순재 ; 김영호, "근전도와 관성센서가 내장된 암밴드를 이용한 실시간 수화 인식" 한국재활복지공학회 10 (10): 329-336, 2016

3 O. Ronneberger, "UNet : Convolutional Networks for Biomedical Image Segmentation" 9351 : 234-241, 2015

4 H. S. Chun, "The Technology and Development Trends of Brain Computer Interface" 26 (26): 123-133, 2011

5 I. J. R. Martínez, "Online Grasp Force Estimation from the Transient EMG" 28 (28): 2333-2341, 2020

6 신재영 ; 김성욱 ; 이윤성 ; 이형탁 ; 황한정, "LSTM을 이용한 표면 근전도 분석을 통한 서로 다른 손가락 움직임 분류 정확도 향상" 대한의용생체공학회 40 (40): 242-249, 2019