PROJECT TITLE :
A Versatile Embedded Platform for EMG Acquisition and Gesture Recognition
Wearable devices provide attention-grabbing features, such as low cost and user friendliness, however their use for medical applications is an open research topic, given the limited hardware resources they provide. In this paper, we tend to gift an embedded resolution for real-time EMG-based hand gesture recognition. The work focuses on the multi-level style of the system, integrating the hardware and software elements to develop a wearable device capable of acquiring and processing EMG signals for real-time gesture recognition. The system combines the accuracy of a custom analog front finish with the flexibility of a low power and high performance microcontroller for on-board processing. Our system achieves the identical accuracy of high-end and more expensive active EMG sensors utilized in applications with strict requirements on signal quality. At the same time, due to its versatile configuration, it will be compared to the few wearable platforms designed for EMG gesture recognition offered on market. We have a tendency to demonstrate that we have a tendency to reach similar or higher performance whereas embedding the gesture recognition on board, with the advantage of price reduction. To validate this approach, we collected a dataset of 7 gestures from 4 users, that were used to guage the impact of the number of EMG channels, the quantity of recognized gestures and the info rate on the popularity accuracy and on the computational demand of the classifier. Thus, we implemented a SVM recognition algorithm capable of real-time performance on the proposed wearable platform, achieving a classification rate of ninety%, which is aligned with the state-of-the-art off-line results and a 29.seven mW power consumption, guaranteeing forty four hours of continuous operation with a 400 mAh battery.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here