Application Research on Optimization Algorithm of sEMG Gesture Recognition Based on Light CNN+LSTM Model

The deep learning gesture recognition based on surface electromyography plays an increasingly important role in human-computer interaction. In order to ensure the high accuracy of deep learning in multistate muscle action recognition and ensure that the training model can be applied in the embedded chip with small storage space, this paper presents a feature model construction and optimization method based on multichannel sEMG amplification unit. The feature model is established by using multidimensional sequential sEMG images by combining convolutional neural network and long-term memory network to solve the problem of multistate sEMG signal recognition. The experimental results show that under the same network structure, the sEMG signal with fast Fourier transform and root mean square as feature data processing has a good recognition rate, and the recognition accuracy of complex gestures is 91.40%, with the size of 1 MB. The model can still control the artificial hand accurately when the model is small and the precision is high.

Influence of Visual Stimulation-Induced Passive Reproduction of Motor Images in the Brain on Motor Paralysis After Stroke

Finger flexor spasticity, which is commonly observed among patients with stroke, disrupts finger extension movement, consequently influencing not only upper limb function in daily life but also the outcomes of upper limb therapeutic exercise. Kinesthetic illusion induced by visual stimulation (KINVIS) has been proposed as a potential treatment for spasticity in patients with stroke. However, it remains unclear whether KINVIS intervention alone could improve finger flexor spasticity and finger extension movements without other intervention modalities. Therefore, the current study investigated the effects of a single KINVIS session on finger flexor spasticity, including its underlying neurophysiological mechanisms, and finger extension movements. To this end, 14 patients who experienced their first episode of stroke participated in this study. A computer screen placed over the patient’s forearm displayed a pre-recorded mirror image video of the patient’s non-paretic hand performing flexion–extension movements during KINVIS. The position and size of the artificial hand were adjusted appropriately to create a perception that the artificial hand was the patient’s own. Before and after the 20-min intervention, Modified Ashworth Scale (MAS) scores and active range of finger extension movements of the paretic hand were determined. Accordingly, MAS scores and active metacarpophalangeal joint extension range of motion improved significantly after the intervention. Moreover, additional experimentation was performed using F-waves on eight patients whose spasticity was reduced by KINVIS to determine whether the same intervention also decreased spinal excitability. Our results showed no change in F-wave amplitude and persistence after the intervention. These results demonstrate the potential clinical significance of KINVIS as a novel intervention for improving finger flexor spasticity and extension movements, one of the most significant impairments among patients with stroke. The decrease in finger flexor spasticity following KINVIS may be attributed to neurophysiological changes not detectable by the F-wave, such as changes in presynaptic inhibition of Ia afferents. Further studies are certainly needed to determine the long-term effects of KINVIS on finger spasticity, as well as the neurophysiological mechanisms explaining the reduction in spasticity.

Recent Advances in Myoelectric Control for Finger Prostheses for Multiple Finger Loss

The loss of one or multiple fingers can lead to psychological problems as well as functional impairment. Various options exist for replacement and restoration after hand or finger loss. Prosthetic hand or finger prostheses improve esthetic outcomes and the quality of life for patients. Myoelectrically controlled hand prostheses have been used to attempt to produce different movements. The available articles (original research articles and review articles) on myoelectrically controlled finger/hand prostheses from January 1922 to February 2021 in English were reviewed using MEDLINE/PubMed, Web of Science, and ScienceDirect resources. The articles were searched using the keywords “finger/hand loss”, “finger prosthesis”, “myoelectric control”, and “prostheses” and relevant articles were selected. Myoelectric or electromyography (EMG) signals are read by myoelectrodes and the signals are amplified, from which the muscle’s naturally generated electricity can be measured. The control of the myoelectric (prosthetic) hands or fingers is important for artificial hand or finger movement; however, the precise control of prosthetic hands or fingers remains a problem. Rehabilitation after multiple finger loss is challenging. Implants in finger prostheses after multiple finger loss offer better finger prosthesis retention. This article presents an overview of myoelectric control regarding finger prosthesis for patients with finger implants following multiple finger loss.

Absence of reliable physiological signature of illusory body ownership revealed by fine-grained autonomic measurement during the rubber hand illusion

The neural representation of a ‘biological self’ is linked theoretically to the control of bodily physiology. In an influential model, selfhood relates to internal agency and higher-order interoceptive representation, inferred from the predicted impact of efferent autonomic nervous activity on afferent viscerosensory feedback. Here we tested if an altered representation of physical self (illusory embodiment of an artificial hand) is accompanied by sustained shifts in autonomic activity. Participants (N = 37) underwent procedures for induction of the rubber hand illusion (synchronous stroking of own unseen hand and observed stroking of artificial hand) and a control condition (asychronous stroking). We recorded electrocardiography, electrodermal activity, and a non-invasive measure of multiunit skin sympathetic nerve activity (SKNA) from the chest. We compared these autonomic indices between task conditions, and between individuals who did and did not experience the illusion. Bayes factors quantified the strength of evidence for and against null hypotheses. Observed proprioceptive drift and subjective reports confirmed the efficacy of the synchronous (vs asynchronous) condition in inducing illusory hand ownership. Stringent discriminant analysis classified 24/37 individuals as experiencing the rubber hand illusion. Surprisingly, heart rate, heart rate variability, electrodermal activity, and SKNA measures revealed no autonomic differences between synchronous vs asynchronous conditions, nor between individuals who did or did not experience the rubber hand illusion. Bayes factors indicated substantial evidence for no physiological differences. In contrast to earlier reports, our autonomic data show the absence of a reliable change in physiological state during the rubber hand illusion. More encompassing perturbations of self-experience, for example in full body illusions, may nevertheless be coupled to, or facilitated by, changes in efferent autonomic activity and afferent viscerosensory feedback. Our findings suggest that such changes in bodily physiology are not sustained as an obligatory component of the rubber hand illusion.

A Soft 3D-Printed Robotic Hand Actuated by Coiled SMA

Robotic hands with unique designs, capabilities and applications have been presented in the literature focusing on sensing, actuation, control, powering and manufacturing, most of which are created by manual assembly process. However, due to advancements in additive manufacturing, new capabilities have replaced traditional methods of manufacturing. In this paper, we present a soft 3D-printed robotic hand actuated by custom-made coiled shape memory alloy (SMA) actuators. The hand uses additive manufacturing of flexible thermoplastic polyurethane (TPU) material, which allows flexing at the joint and hence eliminates the need for additional assembly. Here, we present the full characteristics of the robotic hand such as object grasping categorized by size and weight from the ARAT kit and others. The robotic hand is 425 mm in length, weighs 235 g and is able to operate at a frequency of 0.125 Hz without active cooling. It can grasp an object of 55–81 mm widths, weighing up to 133 g, while consuming an average power of 7.82 W. We also show the time domain response of our custom-made coiled SMA to different current inputs, and its corresponding force and displacement. The current design yields a lightweight and low cost artificial hand with significantly simplified manufacturing for applications in robotics and prosthetics.

Design and Evaluation of Anthropomorphic Robotic Hand for Object Grasping and Shape Recognition

We developed an anthropomorphic multi-finger artificial hand for a fine-scale object grasping task, sensing the grasped object’s shape. The robotic hand was created using the 3D printer and has the servo bed for stand-alone finger movement. The data containing the robotic fingers’ angular position are acquired using the Leap Motion device, and a hybrid Support Vector Machine (SVM) classifier is used for object shape identification. We trained the designed robotic hand on a few monotonous convex-shaped items similar to everyday objects (ball, cylinder, and rectangular box) using supervised learning techniques. We achieve the mean accuracy of object shape recognition of 94.4%.

Low-Cost Prosthesis for People with Transradial Amputations

Prosthetic is an artificial tool that replaces part of the human frame absent because of ailment, damage, or distortion. The current activities in Iraq draw interest to the upper limb discipline because of the growth in variety of amputees and. It is necessary to do extensive researches in this subject to help lessen the struggling of patients. This paper describes the design and development of low-cost prosthesis for people with transradial amputations. The presented design involves a hand with five fingers moving by means of a gear box mechanism. The design of this artificial hand allows five degrees of freedom(5DOF), one degree of freedom for each finger. The artificial hand works by an actuation system (6V) Polou motor with gear ratio equal to 50:1 due to its compactness and cheapness. The designed hand was manufactured by a 3D printing process using polylacticacid material (PLA). Some experimental were accomplished using the designed hand for gripping objects. Initially the EMG signal was recorded when the muscle contracted in one second, two seconds, three seconds. The synthetic hand was able to produce range of gesture and grasping moves separately just like the actual hand by using KNN classification which are complete hand Pinch, fist, and jack chuck. The simulation of the fingers movements was achieved using ANSYS software to analysis the movement (pinch, fist, and jack chuck), obtain bested of stress influencer at each finger, and maximum deformation at each movement.