A Versatile Embedded Platform for EMG Acquisition and Gesture Recognition

Abstract

Wearable devices offer interesting features, such as low cost and user friendliness, but their use for medical applications is an open research topic, given the limited hardware resources they provide. In this paper, we present an embedded solution for real-time EMG-based hand gesture recognition. The work focuses on the multi-level design of the system, integrating the hardware and software components 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 end with the flexibility of a low power and high performance microcontroller for on-board processing. Our system achieves the same accuracy of high-end and more expensive active EMG sensors used in applications with strict requirements on signal quality. At the same time, due to its flexible configuration, it can be compared to the few wearable platforms designed for EMG gesture recognition available on market. We demonstrate that we reach similar or better performance while embedding the gesture recognition on board, with the benefit of cost reduction. To validate this approach, we collected a dataset of 7 gestures from 4 users, which were used to evaluate the impact of the number of EMG channels, the number of recognized gestures and the data rate on the recognition accuracy and on the computational demand of the classifier. As a result, we implemented a SVM recognition algorithm capable of real-time performance on the proposed wearable platform, achieving a classification rate of 90%, which is aligned with the state-of-the-art off-line results and a 29.7 mW power consumption, guaranteeing 44 hours of continuous operation with a 400 mAh battery.

An Embedded, Eight Channel, Noise Canceling, Wireless, Wearable sEMG Data Acquisition System With Adaptive Muscle Contraction Detection

“…EMG technology is used in a wide range of applications such as medical diagnosis and rehabilitation [12]- [15], sports science research, athlete monitoring [16], human machine interaction and gesture recognition [17]- [20]. Specifically, non-invasive EMG technology, i.e., surface electromyography (sEMG), has been recently used in research with these wearable systems [21].…”

Classification complexity in myoelectric pattern recognition

“…Research on MPR has focused on classifiers [4], pre-processing algorithms [5], and electromyography (EMG) acquisition [6], among other factors that influence the classification outcome. Reaz et al studied different attributes of EMG signals, such as signal-to-noise ratio, that decrease the complexity of MPR [7].…”

A Prosthetic Hand Body Area Controller Based on Efficient Pattern Recognition Control Strategies

“…The presence of two independent 16-bit SAR ADCs ( ADC0 and ADC1 ) and of a dedicated PWM output peripheral allow the control of the proposed prosthetic hand minimizing the need for external components and hence the board complexity. Data are acquired at a frequency 500 Hz, which has been shown to be sufficient for gesture recognition applications [49]. On each channel, an RC low pass filters minimizes the high frequency electrical noise.…”

“…We focus on the use of the SVM algorithm, which provides an optimal accuracy Vs complexity trade-off and it is suitable for real-time embedded implementation and tight integration with the hand control. Moreover, in our previous work we demonstrated the robustness of the SVM approach against variation of arm postures and electrodes number and positioning [17,49]. …”