Electromyographic Control Research Articles

1070 Muscle Mechanomyography (MMG) for Peripheral Nerve Monitoring During Lateral Lumbar Fusion: The New Kid on the Block?

INTRODUCTION: The lateral transpsoas approach has become a valuable minimally invasive option in lumbar spine surgery to achieve fusion, decompression, and deformity correction. However, femoral nerve injury during psoas retraction remains a significant concern, especially in the lower spinal levels. A newer alternative to electromyography (EMG), muscle mechanomyography (MMG) measures muscle fiber oscillation during contraction, providing a more specific and quantifiable response with a high signal to noise ratio. These characteristics make MMG an attractive option for intraoperative neuromonitoring (ION) in minimally invasive spine surgery. METHODS: Patients who underwent LLIF between 2018-2021 with MMG ION were included and compared to a historical cohot of patients who underwent LLIF from 2016-2021 with EMG ION. The femoral nerve palsy rate defined by ipsilateral thigh numbness, hip flexor, or quadricep weakness immediately post operatively were collected for both groups. Patients were re-evaluated at 3 month and 1 year follow up intervals. RESULTS: The rate of ipsilateral thigh numbness, hip flexor, and quadricep weakness at hospital discharge were 14.6% (6/41), 9.8% (4/41), and 7.3% (3/41) respectively for the MMG group, comparable to 14.8% (9/61), 23% (14/61), and 14.8% (9/61) observed in the EMG control group. Improvement in thigh numbness and leg weakness was observed for both groups at 3 month and 1 year follow up. No patients with leg weakness had less than antigravity strength. There were no statistically significant difference amongst patient demographics for both cohorts. CONCLUSIONS: In conclusion, MMG appears to be clinically equivalent to EMG as an intraoperative modality for femoral nerve monitoring in LLIF procedures. Further research is needed to evaluate the additional clinical advantages proposed by mechanomyography, such as low signal interference and quantifiable nerve localization.

Methodology of botulinum therapy in the treatment of dystonic scoliosis in generalized dystonia (clinical case)

Dystonic scoliosis as one of the forms of generalized dystonia is a highly disabling form of dystonia, which can lead to damage to internal organs (lungs, heart) and the peripheral nervous system, including the spinal cord. Almost always, those muscles that are involved in the formation of a dystonic posture in generalized dystonia have not been studied in terms of the effectiveness of treatment with botulinum toxin type A and are not reflected in the instructions. As a result, there is no understanding of the general motor interaction with differentiation into targeted and non-targeted muscles, administration doses and control methods.The aim of the work was to evaluate the efficacy and tolerability of high doses of botulinum toxin type A in dystonic scoliosis, as well as to present the introduction of botulinum toxin type A using ultrasound and electromyographic control. We have described a clinical case of a 19-year-old patient suffering from generalized dystonia with S-shaped dystonic scoliosis of the III degree. Deep brain stimulation was recommended as a treatment for the patient. During the waiting period for the timing of the operation, we attempted symptomatic therapy using the drug incobotulotoxin A. Over the next year and a half, 700 units of botulinum toxin type A were administered under ultrasound and electromyographic control every 3–4 months. As a result, treatment of trunk dystonia in the patient during the observation period led to a clinically significant decrease in the degree of curvature (from 37° to 27°, from III to II degree of scoliosis) in the absence of undesirable effects of the drug, including generalized muscle weakness. According to the repeated conclusion of the council of neurosurgeons, surgical intervention is not indicated for the patient due to the positive effect of the introduction of botulinum toxin type A.

Neural prosthesis control restores near-normative neuromechanics in standing postural control.

Current lower-limb prostheses do not provide active assistance in postural control tasks to maintain the user's balance, particularly in situations of perturbation. In this study, we aimed to address this missing function by enabling neural control of robotic lower-limb prostheses. Specifically, electromyographic (EMG) signals (amplified neural control signals) recorded from antagonistic residual ankle muscles were used to drive a robotic prosthetic ankle directly and continuously. Participants with transtibial amputation were recruited and trained in using the EMG-driven robotic ankle. We studied how using the EMG-controlled ankle affected the participants' anticipatory and compensatory postural control strategies and stability under expected perturbations compared with using their daily passive devices. We investigated the similarity of neuromuscular coordination (by analyzing motor modules) of the participants, using either device in a postural sway task, to that of able-bodied controls. Results showed that, compared with their passive prosthesis, the EMG-controlled prosthesis enabled participants to use near-normative postural control strategies, as evidenced by improved between-limb symmetry in intact-prosthetic center-of-pressure and joint angle excursions. Participants substantially improved postural stability, as evidenced by a reduction in steps or falls using the EMG-controlled prosthetic ankle. Furthermore, after relearning to use residual ankle muscles to drive the robotic ankle in postural control, nearly all participants' motor module structure shifted toward that observed in individuals without limb amputations. Here, we have demonstrated the potential benefit of direct EMG control of robotic lower limb prostheses to restore normative postural control strategies (both neural and biomechanical) toward enhancing standing postural stability in amputee users.

Comprehensive diagnosis of cervical dystonia and the efficacy of long-term (three-year) botulinum therapy

Cervical dystonia (CD) is common in outpatient practice but in many cases is diagnosed at late stages. The efficacy of long-term botulinum therapy (BT) in CD has been poorly studied.Objective: to analyse the typical practice of treating patients with CD and the efficacy of long-term BT therapy (three years).Material and methods. Sixty-three patients (43 women and 20 men) diagnosed with CD (mean age 51 [42; 63] years) participated in the study. We performed an analysis of typical practice of managing patients with CD before starting BT. The mean duration of disease at the time of referral was 6 [4; 10] years. Patients received repeated injections of BT at 10–20 week intervals; BT was administered under electromyographic control and ultrasound navigation. The severity of CD was assessed using the Toronto Western Spasmodic Torticollis Rating Scale (TWRSTW), quality of life using the EuroQol-5D questionnaire (EQ-5D) questionnaire, and anxiety level using the Generalized Anxiety Disorder Questionnaire scale-7, GAD-7). Patients' condition was assessed at baseline, 1 month after BT, and after 3 years against the background of regular BT. The severity of the disease before BT was 36.71±3.6 points. The control group consisted of 46 healthy subjects (39 women and 7 men, mean age 53.8±12.3 years).Results. The diagnosis of CD was made on average 2.3±1.1 years after the onset of the first symptoms, BT was started on average 5±2.6 years after diagnosis. At the first visit to the physician, CD was detected in only 32% of cases. In the CD group there was an increase in the severity of anxiety up to 9.93±4.7 points (in the control group – 4.28±3.5 points; p≤0.05) and a decrease in quality of life down to 62.53±12.1 points (in the control group – 86.38±6.4 points; p≤0.05). One month after BT, a significant decrease in the severity of the disease was observed – from 36.7±13.6 to 13.3±10.8 points (p≤0.05). After three years of regular BT the severity of the disease decreased to 12.7±10.5 points (p≤0.05), the level of anxiety decreased to 5.2±3.7 points (p≤0.05), the patients' quality of life increased up to 77.93±8.4 points (p≤0.05).Conclusion. CD is still underdiagnosed in practice, and BT is not prescribed until several years after the onset of the disease. Regular and longterm use of BT not only reduces the severity of CD, but also reduces the severity of anxiety disorders and improves patients' quality of life.

Volitional EMG Control Enables Stair Climbing with a Robotic Powered Knee Prosthesis.

Existing controllers for robotic powered prostheses regulate the prosthesis speed, timing, and energy generation using predefined position or torque trajectories. This approach enables climbing stairs step-over-step. However, it does not provide amputees with direct volitional control of the robotic prosthesis, a functionality necessary to restore full mobility to the user. Here we show that proportional electromyographic (EMG) control of the prosthesis knee torque enables volitional control of a powered knee prosthesis during stair climbing. The proposed EMG controller continuously regulates knee torque based on activation of the residual hamstrings, measured using a single EMG electrode located within the socket. The EMG signal is mapped to a desired knee flexion/extension torque based on the prosthesis knee position, the residual limb position, and the interaction with the ground. As a result, the proposed EMG controller enabled an above-knee amputee to climb stairs at different speeds, while carrying additional loads, and even backwards. By enabling direct, volitional control of powered robotic knee prostheses, the proposed EMG controller has the potential to improve amputee mobility in the real world.

Surgical decompression by laparoscopic approach and intraoperative electromyographic control of pudendal nerve entrapment

Surgical decompression by laparoscopic approach and intraoperative electromyographic control of pudendal nerve entrapment

Ankle Torque Estimation With Motor Unit Discharges in Residual Muscles Following Lower-Limb Amputation.

There has been increased interest in using residual muscle activity for neural control of powered lower-limb prostheses. However, only surface electromyography (EMG)-based decoders have been investigated. This study aims to investigate the potential of using motor unit (MU)-based decoding methods as an alternative to EMG-based intent recognition for ankle torque estimation. Eight people without amputation (NON) and seven people with amputation (AMP) participated in the experiments. Subjects conducted isometric dorsi- and plantarflexion with their intact limb by tracing desired muscle activity of the tibialis anterior (TA) and gastrocnemius (GA) while ankle torque was recorded. To match phantom limb and intact limb activity, AMP mirrored muscle activation with their residual TA and GA. We compared neuromuscular decoders (linear regression) for ankle joint torque estimation based on 1) EMG amplitude (aEMG), 2) MU firing frequencies representing neural drive (ND), and 3) MU firings convolved with modeled twitch forces (MUDrive). In addition, sensitivity analysis and dimensionality reduction of optimization were performed on the MUDrive method to further improve its practical value. Our results suggest MUDrive significantly outperforms (lower root-mean-square error) EMG and ND methods in muscles of NON, as well as both intact and residual muscles of AMP. Reducing the number of optimized MUDrive parameters degraded performance. Even so, optimization computational time was reduced and MUDrive still outperformed aEMG. Our outcomes indicate integrating MU discharges with modeled biomechanical outputs may provide a more accurate torque control signal than direct EMG control of assistive, lower-limb devices, such as exoskeletons and powered prostheses.

A 3D-printed soft orthotic hand actuated with twisted and coiled polymer muscles triggered by electromyography signals

<p class="Abstract">Various wearable robotic hands, prosthetic hands, and orthotic exoskeletons developed in the last decade aim to rehabilitate patients whose daily quality of life is affected from hand impairments – however, a majority of these devices are controlled by bulky, expensive, noisy, and uncomfortable actuators. Twisted and coiled polymer (TCP) muscles are novel smart actuators that address these key drawbacks. They have been utilized in soft robotics, hand orthosis exoskeletons, and powered hand orthotic devices; they are also light- weight, high-performance, and inexpensive to manufacture. Previously, TCP muscles have been controlled via power supplies with mechanical switches that are not portable, hence making it unfeasible for long term applications. In this work, a portable control system for TCP muscles via electromyography (EMG) signals that are captured through electrodes placed on the arm of the user and processed through a channel of electrical components to actuate 4-ply TCP muscles, which is demonstrated on a 3D-Printed soft orthotic hand. With portable EMG control, orthotic devices can become more independently accessible to the user, making these devices novel instruments for measuring, aiding, and expediting the progress of hand impairment rehabilitation.</p>

Individuals with moderate to severe hand impairments may struggle to use EMG control for assistive devices.

Neurological trauma, such as stroke, traumatic brain injury (TBI), spinal cord injury, and cerebral palsy can cause mild to severe upper limb impairments. Hand impairment makes it difficult for individuals to complete activities of daily living, especially bimanual tasks. A robotic hand orthosis or hand exoskeleton can be used to restore partial function of an intact but impaired hand. It is common for upper extremity prostheses and orthoses to use electromyography (EMG) sensing as a method for the user to control their device. However some individuals with an intact but impaired hand may struggle to use a myoelectrically controlled device due to potentially confounding muscle activity. This study was conducted to evaluate the application of conventional EMG control techniques as a robotic orthosis/exoskeleton user input method for individuals with mild to severe hand impairments. Nine impaired subjects and ten healthy subjects were asked to perform repeated contractions of muscles in their forearm and then onset analysis and feature classification were used to determine the accuracy of the employed EMG techniques. The average accuracy for contraction identification across employed EMG techniques was 95.4% ± 4.9 for the healthy subjects and 73.9% ± 13.1 for the impaired subjects with a range of 47.0% ± 19.1 - 91.6% ± 8.5. These preliminary results suggest that the conventional EMG control technologies employed in this paper may be difficult for some impaired individuals to use due to their unreliable muscle control.

Power Assist Rehabilitation Robot and Motion Intention Estimation

This article attempts to review papers on power assist rehabilitation robots, human motion intention, control laws, and estimation of power assist rehabilitation robots based on human motion intention in recent years. This paper presents the various ways in which human motion intention in rehabilitation can be estimated. This paper also elaborates on the control laws for the estimation of motion intention of the power assist rehabilitation robot. From the review, it has been found that the motion intention estimation method includes: Artificial Intelligence-based motion intention and Model-based motion intention estimation. The controllers include hybrid force/position control, EMG control, and adaptive control. Furthermore, Artificial Intelligence based motion intention estimation can be subdivided into Electromyography (EMG), Surface Electromyography (SEMG), Extreme Learning Machine (ELM), and Electromyography-based Admittance Control (EAC). Also, Model-based motion intention estimation can be subdivided into Impedance and Admittance control interaction. Having reviewed several papers, EAC and ELM are proposed for efficient motion intention estimation under artificial-based motion intention. In future works, Impedance and Admittance control methods are suggested under model-based motion intention for efficient estimation of motion intention of power assist rehabilitation robot. In addition, hybrid force/position control and adaptive control are suggested for the selection of control laws. The findings of this review paper can be used for developing an efficient power assist rehabilitation robot with motion intention to aid people with lower or upper limb impairment.

Semi-autonomous control of prosthetic hands based on multimodal sensing, human grasp demonstration and user intention

Semi-autonomous control strategies for prosthetic hands provide a promising way to simplify and improve the grasping process for the user by adopting techniques usually applied in robotic grasping. Such strategies endow prosthetic hands with the ability to autonomously select and execute grasps while keeping the user in the loop to intervene at any time for triggering, accepting or rejecting decisions taken by the controller in an intuitive and easy way. In this paper, we present a semi-autonomous control strategy that allows the user to perform fluent grasping of everyday objects based on a single EMG channel and a multi-modal sensor system embedded in the hand for object perception and autonomous grasp execution. We conduct a user study with 20 subjects to assess the effectiveness and intuitiveness of our semi-autonomous control strategy and compare it to a conventional electromyography-based control strategy. The results show that the workload is reduced by 25.9% compared to conventional electromyographic control, the physical demand is reduced by 60% and the grasping process is accelerated by 19.4%.

Botulinum Toxin Injection in Horizontal Rectus Muscles Without Electromyography Using an Open Sky Versus a Closed Sky Technique.

To ascertain whether electromyographic control when injecting botulinum toxin in the horizontal rectus muscles is necessary, and to compare the open sky and closed sky injection techniques that are used without electromyographic control. The records of 135 patients with horizontal strabismus who received botulinum toxin injections were reviewed retrospectively. Sevoflurane or propofol anesthesia was used in children, and topical benoxinate hydrochloride was used in adults. Patients received a bilateral injection of 2.5 to 15 IU of botulinum toxin, without electromyographic control, into the medial or lateral rectus muscles to correct esotropia or exotropia, respectively. An open sky technique was used in 31 patients, and a closed sky technique was used in 104 patients. Postoperative alignment within 10 prism diopters (PD) of orthotropia was considered a successful outcome. A successful outcome at 6 months of follow-up was achieved in 47% of all patients: 59% of patients in the open sky group and 44% of patients in the closed sky group (P = .151). Botulinum toxin injection corrected a mean of 14 ± 9.705 PD in patients in the open sky group and 31 ± 20.589 PD in patients in the closed sky group to obtain mean residual angles of 21 ± 16.692 and 13 ± 11.901 PD, respectively. The results obtained without electromyographic assistance were not remarkably different from the studies using electromyographic control. Moreover, because the results of the open sky technique were not significantly superior to the closed sky technique, the latter was favored to shorten the operative time and postoperative convalescence, and to reduce the risk of postoperative adhesions and scarring, which made re-operations difficult. [J Pediatr Ophthalmol Strabismus. 2022;59(6):388-395.].

Toward Developing a Powered Ankle-Foot Prosthesis With Electromyographic Control to Enhance Functional Performance: A Case Study in a U.S. Service Member.

The only commercially available ankle-foot prosthesis with powered propulsion lacks ruggedization and other capabilities for service members seeking to return to duty and/or other physically demanding activities. Here, we evaluated a ruggedized powered ankle-foot prosthesis with electromyographic control ("Warrior Ankle"; WA) in an experienced male user of the predicate (Empower) prosthesis. The participant (age = 56 years, mass = 86.8 kg, stature = 173 cm) completed a 650 m simulated hike with varying terrain at a fixed, self-selected speed in the WA and predicate prosthesis, with and without a 22.8 kg weighted vest ("loaded" and "unloaded," respectively). Peak dorsiflexion and plantarflexion angles were extracted from each gait cycle throughout the simulated hike (∼500 prosthetic-side steps). The participant walked faster with the WA (1.15 m/s) compared to predicate (0.80 m/s) prosthesis. On the prosthetic side, peak dorsiflexion angles were larger for the WA (loaded: 27.9°; unloaded: 26.9°) compared to the predicate (loaded: 19.4°; unloaded: 21.3°); peak plantarflexion angles were similar between prostheses and loading conditions [WA (loaded: 15.5°; unloaded: 14.9°), predicate (loaded: 16.9°; unloaded: 14.8°). The WA better accommodated the varying terrain profile, evidenced by greater peak dorsiflexion angles, as well as dorsiflexion and plantarflexion angles that more closely matched or exceeded those of the innate ankle [dorsiflexion (WA: 31.6°, predicate: 27.5°); plantarflexion (WA: 20.7°, predicate: 20.5°)]. Furthermore, the WA facilitated a faster walking speed, suggesting a greater functional capacity with the WA prosthesis. Although further design enhancements are needed, this case study demonstrated feasibility of a proof-of-concept, ruggedized powered ankle-foot prosthesis with electromyographic control.

A New Labeling Approach for Proportional Electromyographic Control.

Different control strategies are available for human machine interfaces based on electromyography (EMG) to map voluntary muscle signals to control signals of a remote controlled device. Complex systems such as robots or multi-fingered hands require a natural commanding, which can be realized with proportional and simultaneous control schemes. Machine learning approaches and methods based on regression are often used to realize the desired functionality. Training procedures often include the tracking of visual stimuli on a screen or additional sensors, such as cameras or force sensors, to create labels for decoder calibration. In certain scenarios, where ground truth, such as additional sensor data, can not be measured, e.g., with people suffering from physical disabilities, these methods come with the challenge of generating appropriate labels. We introduce a new approach that uses the EMG-feature stream recorded during a simple training procedure to generate continuous labels. The method avoids synchronization mismatches in the labels and has no need for additional sensor data. Furthermore, we investigated the influence of the transient phase of the muscle contraction when using the new labeling approach. For this purpose, we performed a user study involving 10 subjects performing online 2D goal-reaching and tracking tasks on a screen. In total, five different labeling methods were tested, including three variations of the new approach as well as methods based on binary labels, which served as a baseline. Results of the evaluation showed that the introduced labeling approach in combination with the transient phase leads to a proportional command that is more accurate than using only binary labels. In summary, this work presents a new labeling approach for proportional EMG control without the need of a complex training procedure or additional sensors.

Bionic arm: Mapping of elbow and wrist flexion using neural network and fuzzy logic

Cases on limb amputation necessitate the use of Transhumeral bionic for artificial limb rehabilitation, which is controlled using Electromyographic (EMG) signals from the muscles. Before the implementation of EMG control, a mapping between the movements of an arm to the angle formed at the corresponding joints is essential to be made. Most of the works in the field of Bionics use Supervised Machine Learning models, chiefly Classification, to map muscle flexion signals to joint actuations in the bionic arm. Ample literature is also there, which uses fuzzy logic for mapping. However, there are very few literatures that compare these two methods of mapping. In this article, 2 models have been discussed regarding the mapping, and their effectiveness is compared. The first model captures elbow and wrist flexion and maps them to their respective angular displacements of joints using a fuzzy logic model. In the second model, a Pattern Recognition Artificial Neural Network (ANN) model under Supervised Machine Learning is incorporated to map elbow and wrist flexion to the corresponding joint angular displacement. The ANN is trained with elbow and wrist joint flexion values and its corresponding joint angles data, optimized, and tested in real-time. This model is verified by comparing the joint angles of a test person (measured using Goniometers) with the joint angles of Bionic models made (using a 360° protractor sheet). The second model gave the insight that supervised machine learning models provide an accurate mapping to the joint flexion in the field of bionics.

Robust Torque Predictions From Electromyography Across Multiple Levels of Active Exoskeleton Assistance Despite Non-linear Reorganization of Locomotor Output.

Robotic exoskeletons can assist humans with walking by providing supplemental torque in proportion to the user's joint torque. Electromyographic (EMG) control algorithms can estimate a user's joint torque directly using real-time EMG recordings from the muscles that generate the torque. However, EMG signals change as a result of supplemental torque from an exoskeleton, resulting in unreliable estimates of the user's joint torque during active exoskeleton assistance. Here, we present an EMG control framework for robotic exoskeletons that provides consistent joint torque predictions across varying levels of assistance. Experiments with three healthy human participants showed that using diverse training data (from different levels of assistance) enables robust torque predictions, and that a convolutional neural network (CNN), but not a Kalman filter (KF), can capture the non-linear transformations in EMG due to exoskeleton assistance. With diverse training, the CNN could reliably predict joint torque from EMG during zero, low, medium, and high levels of exoskeleton assistance [root mean squared error (RMSE) below 0.096 N-m/kg]. In contrast, without diverse training, RMSE of the CNN ranged from 0.106 to 0.144 N-m/kg. RMSE of the KF ranged from 0.137 to 0.182 N-m/kg without diverse training, and did not improve with diverse training. When participant time is limited, training data should emphasize the highest levels of assistance first and utilize at least 35 full gait cycles for the CNN. The results presented here constitute an important step toward adaptive and robust human augmentation via robotic exoskeletons. This work also highlights the non-linear reorganization of locomotor output when using assistive exoskeletons; significant reductions in EMG activity were observed for the soleus and gastrocnemius, and a significant increase in EMG activity was observed for the erector spinae. Control algorithms that can accommodate spatiotemporal changes in muscle activity have broad implications for exoskeleton-based assistance and rehabilitation following neuromuscular injury.

A Hand Exoskeleton for Stroke Survivors' Activities of Daily Life.

Stroke is a leading cause of disability in the U.S. Hand impairment is a common consequence of stroke, potentially impacting all facets of life as the hands are the primary means of interacting with the world. Typically, therapy is the prescribed treatment after stroke. However, a majority of stroke survivors have limited recovery and thus chronic impairment. Assistive, rather than therapeutic, devices may help these individuals restore lost function and improve independence and engagement in society. Current assistive devices, however, typically fail to address the greatest barriers to successful use with stroke survivors. In the hand, weakness and incoordination arise from a seemingly paradoxical combination of limited voluntary activation of muscles and involuntary neuromuscular hyperexcitability. Thus, profound strength deficits can be accompanied by substantial forces opposing the intended movement. The assistive device presented in this paper can provide both sufficient flexion and extension assistance to overcome these barriers. A single actuator for each digit provides flexion or extension assistance through push-pull cables guided along the dorsal side of the hand. User intent can be decoded from Electromyographic (EMG) signals to drive the device throughout the movement. EMG control is customized to the capabilities of each user by examining the voluntary EMG workspace.

Restoration of Neck Extension after Severe Oncological Surgery of the Posterior Cervical Trunk.

SummaryReconstruction of posterior cervical trunk defects secondary to tumor resection carries significant morbidity when vertebral hardware or the spinal cord is exposed, and neck extension is interrupted. Complete reconstruction includes the coverage and obliteration of dead spaces, but functional outcomes are necessary to prevent the head dropping. This report documents the first known technique, using a free latissimus dorsi neurovascular flap to provide neck extension after ablative oncological surgery affecting trapezium and paraspinal muscles of the neck. The author explains the method by using a branch of the accessory nerve as the donor nerve. While keeping the head in a neutral position, the tendinous part of the neurovascular flap was firmly attached to the occipital periosteum and to the cephalad remnants of the trapezius, splenius capitis, and semispinalis muscles. At the caudal portion of the defect, cardinal notches were used to set the muscle at rest, avoiding excessive fiber tension. The maximal length of the muscle at rest was measured before flap elevation, calculated via the anatomical 3D print model. The thoracodorsal nerve was stimulated until the muscle shortened its length to 50%. Head extension was tested several times via neurostimulation and electromyographic control. The described procedure may provide neck extension and circumvent the problem with donor nerve providing synergy to the desired function.

Performance potential of classical machine learning and deep learning classifiers for isometric upper-body myoelectric control of direction in virtual reality with reduced muscle inputs

Electromyography (EMG) signals can be classified by machine learning (ML) algorithms to command prosthetic devices that functionally assist persons after neuromuscular traumas, including amputation and spinal cord injury. This pilot study evaluated several ML algorithms in mapping isometric EMG signals from the upper body (dominant-side arm, chest, back) of able-bodied participants to directional commands across multiple muscle recording sets. Each set (up to 14 muscles) was based on muscles presumed under volitional control following various levels of nerve lesion or amputation. Among the evaluated ML algorithms were those that did and did not rely on feature extraction. The ML algorithms included: support vector machine, adaptive boosting, bootstrap aggregating, Naïve Bayes, linear discriminant analysis, and variations of neural networks (NN). Specifically, we examined a shallow (single-layer feedforward) NN and two ‘deep’ NN structures (ten-layer feedforward network, convolutional NN). The ML algorithms were evaluated according to classification accuracy and performance in a maze navigation task in virtual reality. Adaptive boosting and bootstrap aggregating demonstrated significantly greater (p < 0.05) classification accuracy across most muscle sets. Maze task performance depended on the combination of classifier and muscle set utilized. Advantages in classification accuracy from adaptive boosting and bootstrap aggregating should be balanced against the cost of increased time to train EMG control for persons with motor impairment.

A database of high-density surface electromyogram signals comprising 65 isometric hand gestures

Control of contemporary, multi-joint prosthetic hands is commonly realized by using electromyographic signals from the muscles remaining after amputation at the forearm level. Although this principle is trying to imitate the natural control structure where muscles control the joints of the hand, in practice, myoelectric control provides only basic hand functions to an amputee using a dexterous prosthesis. This study aims to provide an annotated database of high-density surface electromyographic signals to aid the efforts of designing robust and versatile electromyographic control interfaces for prosthetic hands. The electromyographic signals were recorded using 128 channels within two electrode grids positioned on the forearms of 20 able-bodied volunteers. The participants performed 65 different hand gestures in an isometric manner. The hand movements were strictly timed using an automated recording protocol which also synchronously recorded the electromyographic signals and hand joint forces. To assess the quality of the recorded signals several quantitative assessments were performed, such as frequency content analysis, channel crosstalk, and the detection of poor skin-electrode contacts.