Designing a Cost Effective Dry Contact sEMG Sensor System for Controlling a Bionic Hand
Our Final Year Project at the University of Moratuwa.
Surface Electromyogram (sEMG) signals from the forearm is widely used as a source for gesture controlled applications and prosthesis control.This project involves development of a real-time gesture recognition algorithm using forearm sEMG signals and development of a cost effective electrode system to acquire forearm signals, with the aim of controlling a bionic arm. Most commonly used approach in hand gesture recognition tasks is to extract a set of temporal and frequency domain features from acquired sEMG recordings and then classify them using different learning algorithms such as SVM and LDA. In these studies the sEMG recordings from electrodes placed on the forearm are treated as individual and uncorrelated entities. However we observed a correlated nature between the signal channels whenever a gesture is elicited. Hence we came up with a novel idea of Temporal Muscle Activation Maps that can represent the individual and mutual activation patterns of forearm muscles which was then used in real-time gesture recognition. The code and the demo of this work can be found here. In order to acquire sEMG signals from the forearm we developed a active, dry-contact electrode sensors to acquire high quality sEMG signals, and a final device to interface our novel finger gesture recognition algorithm with the sensors. The electrode design was fabricated and assembled on a double-sided flex printed circuit, with a small form-factor and these electrodes were interfaced with an ADS1299 Performance Demonstration Kit with STM32 F411RE Nucleo board to obtain the sEMG signals required for the gesture classification. The electrode sensors were evaluated with a finger gesture classification experiment, and the CMRR of the sensor was experimentally characterized as well.
On the left, a diagram that outlines the method of computing TMA maps. Right, the sEMG sensors and circuitry used.
Publications
2020
Low-cost Active Dry-Contact Surface EMG Sensor for Bionic Arms
Asma M. Naim, Kithmin Wickramasinghe, Ashwin De Silva, and 3 more authors
IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2020
Surface electromyography (sEMG) is a popular bio-signal used for controlling prostheses and finger gesture recognition mechanisms. Myoelectric prostheses are costly, and most commercially available sEMG acquisition systems are not suitable for real-time gesture recognition. In this paper, a method of acquiring sEMG signals using novel low-cost, active, dry-contact, flexible sensors has been proposed. Since the active sEMG sensor was developed to be used along with a bionic arm, the sensor was tested for its ability to acquire sEMG signals that could be used for real-time classification of five selected gestures. In a study of 4 subjects, the average classification accuracy for real-time gesture classification using the active sEMG sensor system was 85%. The common-mode rejection ratio of the sensor was measured to 59 dB, and thus the sensor’s performance was not substantially limited by its active circuitry. The proposed sensors can be interfaced with a variety of amplifiers to perform fully wearable sEMG acquisition. This satisfies the need for a low-cost sEMG acquisition system for prostheses.
Real-Time Hand Gesture Recognition Using Temporal Muscle Activation Maps of Multi-Channel sEMG Signals
Ashwin De Silva, Malsha V. Perera, Kithmin Wickramasinghe, and 3 more authors
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020
Accurate and real-time hand gesture recognition is essential for controlling advanced hand prostheses. Surface Electromyography (sEMG) signals obtained from the forearm are widely used for this purpose. Here, we introduce a novel hand gesture representation called Temporal Muscle Activation (TMA) maps which captures information about the activation patterns of muscles in the forearm. Based on these maps, we propose an algorithm that can recognize hand gestures in real-time using a Convolution Neural Network. The algorithm was tested on 8 healthy subjects with sEMG signals acquired from 8 electrodes placed along the circumference of the forearm. The average classification accuracy of the proposed method was 94%, which is comparable to state-of-the-art methods. The average computation time of a prediction was 5.5ms, making the algorithm ideal for the real-time gesture recognition applications.
