http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Mustapha Deji Dere,Jo Ji-hun,Boreom Lee 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11
Deep learning resurgence ushered in the application of pattern recognition algorithms in high-impact research fields with impressive accuracy. In addition, deep neural networks (DNN) have recently been used to classify gestures for rehabilitation device control utilizing raw electromyography data. However, the computational resources required by a convolution neural network (CNN) are a constraint that often limits deployment to embedded devices for real-time inference. An optimized edge adaptive convolutional neural network using a short-time Fourier transform (STFT) spectrogram input was proposed in this study. The models classification accuracy was evaluated offline and on-device for inter-subject accuracy. Furthermore, an adaptive weight update approach was implemented to improve inference model accuracy due to degradation. The proposed model and optimization technique achieved offline accuracy of 92.19 % and 94.29 % for the raw and STFT input, respectively. However, the on-device accuracy for raw and STFT input to the model was 82.26 % and 85.19 %, respectively. On the other hand, the adaptive model update increased the respective accuracy by an average of 7% on-device. Finally, our study demonstrates the deployment of DNN on-device for real-time gesture classification inference.
Development of FPGA-based deep learning orthosis actuating system using bio signal data
Ji-Hun Jo,Dere Mustapha Deji,Hyeong-jun Park,Boreom Lee 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11
Recently, many health care applications for rehabilitation are used to developed with various technologies for treatment and assistance. And these technologies are mainly applied to purpose with improve the essential activities for human life. In this study, we develop the 3D-printed hand orthosis for patients who has low motor function from the spinal cord injury (SCI) or stroke, and build the hand motion actuating system with Field-Programmable Gate Array (FPGA) using Electroencephalogram (EEG) and Electromyogram (EMG). Our system applied the custom 2D-CNN deep learning algorithm for the higher motion accuracy, real-time motion actuating. And we conducted experiment to investigate the characteristics of each seven gesture in EEG and EMG with seven healthy subjects. In experiment, subject do the gesture as same as showing in screen, then the system acquired the bio signals and analysis in same time. In further, to evaluate the system, we’ll verifying the motor function improvement through experiment to actual patients with orthosis. And also compare the performance with other on-chip programmable device.