myo-electric hand prosthesis / multi-articulated / adult
The surface EMG(sEMG) is collected using 8 channel bi-polar electrodes, and is then sampled with a high sampling rate after pre-processing techniques such as filtering and amplification. During training phase, users are asked to record sEMG for different gestures using the training interactive app. Collected sEMG will be uploaded to cloud and used to train a deep neural network model. After training process, the model will be sent back to the prosthetic hand. During usage, sensors will collect user real-time sEMG and model will provide control information to motor driver component based on collected data to perform corresponding gesture.