Wearable EMG Bridge—A Multiple-Gesture Reconstruction System Using Electrical Stimulation Controlled by the Volitional Surface Electromyogram of a Healthy Forearm

Abstract

In this study, a wearable prototype system was developed for multiple-gesture rehabilitation using electrical stimulation controlled by a volitional surface electromyography (sEMG) scan of a healthy forearm. The purpose of the prototype system is to reconstruct multiple gestures of a paralysed limb and to simplify the positioning of sEMG detection sites on a healthy forearm. A self-designed eight-channel sEMG detection armband was used to detect the sEMG signal distributions of the muscle groups in healthy forearms. Linear discriminant analysis (LDA) was used to classify the sEMG signal distributions corresponding to different gestures, and then the classification results were mapped to corresponding stimulation channels. The sEMG signal with the maximum root mean square (RMS) was used as the source of stimulus coding for each gesture. Our proposed mean absolute value (MAV)/number of slope sign changes (NSS) dual-coding (MNDC) algorithm was used to encode the sEMG signal into an electrical stimulus with a dynamic pulse width and frequency. The constant-current stimulation armband electrically stimulated multiple muscles in the affected forearm by means of a circuit designed with a time-division multiplexed stimulation channel. An experiment involving 6 able-bodied volunteers showed that when the detection armband was located near the middle of the forearm, the gesture classification accuracy was greater than 90%, and each active sEMG signal was high. Gesture bridge experiments, including grasping, wrist flexion, wrist extension and finger extension, were carried out among six hemiplegic subjects and between one able-bodied volunteer acting as a controller and each of six stroke patients as the controllee. Both sets of results show that the proposed system can reconstruct these four gestures in the controlled subject with a delay of at most 360 ms and with a correlation coefficient of > 0.72.

A Co-driven Functional Electrical Stimulation Control Strategy by Dynamic Surface Electromyography and Joint Angle

“… Rossi et al (2020) proposed an average threshold crossing (ATC) FES control strategy, and the correlation coefficient of joint angle during elbow flexion was 0.87 ± 0.07. Bi et al (2020) designed a multiple-gesture FES system, and the correlation coefficient of joint angle during wrist extension was 0.89 ± 0.04. The accuracy of FES-induced joint angle for this study was much better than previous studies.…”

Hand Gestures Recognition for Human-Machine Interfaces: A Low-Power Bio-Inspired Armband

“…All the reported works developed their wearable device, but only [7], [16], [29], [40] managed to fit their learner into an embedded prototype. The armband developed in [9], for example, is reported to be designed to support the embedding of ML algorithms, but all the predictions are still evaluated 1 Current Absorption, 2 Battery Capacity, 3 Operating Time, 4 Discrete Wavelet Transform, 5 Linear Discriminant Analysis Acquisition window 6 Gated Recurrent Unit, 7 Considering the most comfortable use-case with idle norm equal to 5 Prediction on a computer.…”

“…Many research groups exploit the capability of the CNN paradigm, even with some enhanced features added, while only [3] maintains the simpler ANN structure. On the other hand, all the embedded solutions fell back on more compact classifiers, like smaller ANNs [40], SVM [7] or even the Linear Discriminant Analysis (LDA) [29]. The only work that was able to perform a CNN computation on a microcomputer inside a prosthesis is [16], which, applying 32 High-Density (HD) sEMG electrodes on the skin covered by the prosthesis body, was able to recognize 8 gestures with 98.2 % accuracy.…”

“…Indeed, standard rehabilitative sessions can motivate the patients making them interact with the so-called serious games [23]- [25] or by giving them more simple feedback during movements execution [26]- [28]. On the other hand, for people which are not able to autonomously perform the rehabilitation routine, the therapist can, for example, apply the functional electrical stimulation on the injured muscle(s), both involving data compression [29] and maintaining the association of the gestures one by one [30], [31].…”

Sensors for Context-Aware Smart Healthcare: A Security Perspective

“…On the one hand, intramuscular EMG methods are invasive, potentially painful, and not well aligned with smart healthcare solutions. On the other hand, surface EMG methods are non-invasive procedures that only require placing some patch electrodes on the muscle’s skin, facilitating their integration in wearable devices, such as wristbands, armbands, caps or even textiles, to enable long-term monitoring in real-time [ 125 , 126 , 127 , 128 ], tracking tremor and dyskinesia symptoms [ 129 ], preventing falls [ 130 ], recognising gestures and activities [ 131 ], controlling robotic prosthetics [ 132 , 133 , 134 ] and rehabilitation [ 135 , 136 ]. Although more comfortable, the quality of these measurements is affected by the skin’s properties, tissue structure, the adherence of the electrodes to the skin and external electromagnetic interference and noise-filtering techniques are required [ 137 ].…”