Comparison of surface and intramuscular EMG pattern recognition for simultaneous wrist/hand motion classification

New insights into muscle activity associated with phantom hand movements in transhumeral amputees

Introduction

Muscle activity patterns in the residual arm are systematically present during phantom hand movements (PHM) in transhumeral amputees. However, their characteristics have not been directly investigated yet, leaving their neurophysiological origin poorly understood. This study pioneers a neurophysiological perspective in examining PHM-related muscle activity patterns by characterizing and comparing them with those in the arm, forearm, and hand muscles of control participants executing intact hand movements (IHM) of similar types.

Methods

To enable rigorous comparison, we developed meta-variables independent of electrode placement, quantifying the phasic profile of recorded surface EMG signals and the specificity of their patterns across electrode sites and movement types.

Results

Similar to the forearm and hand muscles during IHM, each signal recorded from the residual upper arm during PHM displays a phasic profile, synchronized with the onset and offset of each movement repetition. Furthermore, the PHM-related patterns of phasic muscle activity are specific not only to the type of movement but also to the electrode site, even within the same upper arm muscle, while these muscles exhibit homogeneous activities in intact arms.

Discussion

Our results suggest the existence of peripheral reorganization, eventually leading to the emergence of independently controlled muscular sub-volumes. This reorganization potentially occurs through the sprouting of severed axons and the recapture of muscle fibers in the residual limb. Further research is imperative to comprehend this mechanism and its relationship with PHM, holding significant implications for the rehabilitation process and myoelectric prosthesis control.

Smile analysis in dentistry and orthodontics - a review

The desire for an attractive smile is a major reason people seek orthodontic and other forms of cosmetic dental treatment. An understanding of the features of a smile is important for dental diagnosis and treatment planning. The common methods of smile analysis rely on the visual analysis of smile aesthetics using posed photographs, and videos and gathering information about smiles through patient questionnaires and diaries. Recent emerging trends utilise artificial intelligence and automated systems capable of detecting and analysing smiles using motion capture, computer vision, computer graphics, infrared and thermal imaging, electromyography, and optical sensors. This review aims to provide an up-to-date summary of emerging trends in smile analysis in dentistry and orthodontics. Understanding the advantages and limitations of emerging tools for smile analysis will enable clinicians to provide tailored and up-to-date treatment plans.

Functional assessment of current upper limb prostheses: An integrated clinical and technological perspective

Although recent technological developments in the field of bionic upper limb prostheses, their rejection rate remains excessively high. The reasons are diverse (e.g. lack of functionality, control complexity, and comfortability) and most of these are reported only through self-rated questionnaires. Indeed, there is no quantitative evaluation of the extent to which a novel prosthetic solution can effectively address users' needs compared to other technologies. This manuscript discusses the challenges and limitations of current upper limb prosthetic devices and evaluates their functionality through a standard functional assessment, the Assessment of Capacity for Myoelectric Control (ACMC). To include a good representation of technologies, the authors collect information from participants in the Cybathlon Powered Arm Prostheses Race 2016 and 2020. The article analyzes 7 hour and 41 min of video footage to evaluate the performance of different prosthetic devices in various tasks inspired by activities of daily living (ADL). The results show that commercially-available rigid hands perform well in dexterous grasping, while body-powered solutions are more reliable and convenient for competitive environments. The article also highlights the importance of wrist design and control modality for successful execution of ADL. Moreover, we discuss the limitations of the evaluation methodology and suggest improvements for future assessments. With regard to future development, this work highlights the need for research in intuitive control of multiple degrees of freedom, adaptive solutions, and the integration of sensory feedback.

Use of regenerative peripheral nerve interfaces and intramuscular electrodes to improve prosthetic grasp selection: a case study

Objective.Advanced myoelectric hands enable users to select from multiple functional grasps. Current methods for controlling these hands are unintuitive and require frequent recalibration. This case study assessed the performance of tasks involving grasp selection, object interaction, and dynamic postural changes using intramuscular electrodes with regenerative peripheral nerve interfaces (RPNIs) and residual muscles.Approach.One female with unilateral transradial amputation participated in a series of experiments to compare the performance of grasp selection controllers with RPNIs and intramuscular control signals with controllers using surface electrodes. These experiments included a virtual grasp-matching task with and without a concurrent cognitive task and physical tasks with a prosthesis including standardized functional assessments and a functional assessment where the individual made a cup of coffee ('Coffee Task') that required grasp transitions.Main results.In the virtual environment, the participant was able to select between four functional grasps with higher accuracy using the RPNI controller (92.5%) compared to surface controllers (81.9%). With the concurrent cognitive task, performance of the virtual task was more consistent with RPNI controllers (reduced accuracy by 1.1%) compared to with surface controllers (4.8%). When RPNI signals were excluded from the controller with intramuscular electromyography (i.e. residual muscles only), grasp selection accuracy decreased by up to 24%. The participant completed the Coffee Task with 11.7% longer completion time with the surface controller than with the RPNI controller. She also completed the Coffee Task with 11 fewer transition errors out of a maximum of 25 total errors when using the RPNI controller compared to surface controller.Significance.The use of RPNI signals in concert with residual muscles and intramuscular electrodes can improve grasp selection accuracy in both virtual and physical environments. This approach yielded consistent performance without recalibration needs while reducing cognitive load associated with pattern recognition for myoelectric control (clinical trial registration number NCT03260400).

Evaluation of Simple Algorithms for Proportional Control of Prosthetic Hands Using Intramuscular Electromyography

Although seemingly effortless, the control of the human hand is backed by an elaborate neuro-muscular mechanism. The end result is typically a smooth action with the precise positioning of the joints of the hand and an exerted force that can be modulated to enable precise interaction with the surroundings. Unfortunately, even the most sophisticated technology cannot replace such a comprehensive role but can offer only basic hand functionalities. This issue arises from the drawbacks of the prosthetic hand control strategies that commonly rely on surface EMG signals that contain a high level of noise, thus limiting accurate and robust multi-joint movement estimation. The use of intramuscular EMG results in higher quality signals which, in turn, lead to an improvement in prosthetic control performance. Here, we present the evaluation of fourteen common/well-known algorithms (mean absolute value, variance, slope sign change, zero crossing, Willison amplitude, waveform length, signal envelope, total signal energy, Teager energy in the time domain, Teager energy in the frequency domain, modified Teager energy, mean of signal frequencies, median of signal frequencies, and firing rate) for the direct and proportional control of a prosthetic hand. The method involves the estimation of the forces generated in the hand by using different algorithms applied to iEMG signals from our recently published database, and comparing them to the measured forces (ground truth). The results presented in this paper are intended to be used as a baseline performance metric for more advanced algorithms that will be made and tested using the same database.

A parallel classification strategy to simultaneous control elbow, wrist, and hand movements

Background

In the field of myoelectric control systems, pattern recognition (PR) algorithms have become always more interesting for predicting complex electromyography patterns involving movements with more than 2 Degrees of Freedom (DoFs). The majority of classification strategies, used for the prosthetic control, are based on single, hierarchical and parallel linear discriminant analysis (LDA) classifiers able to discriminate up to 19 wrist/hand gestures (in the 3-DoFs case), considering both combined and discrete motions. However, these strategies were introduced to simultaneously classify only 2 DoFs and their use is limited by the lack of online performance measures. This study introduces a novel classification strategy based on the Logistic Regression (LR) algorithm with regularization parameter to provide simultaneous classification of 3 DoFs motion classes.

Methods

The parallel PR-based strategy was tested on 15 healthy subjects, by using only six surface EMG sensors. Twenty-seven discrete and complex elbow, hand and wrist motions were classified by keeping the number of electromyographic (EMG) electrodes to a bare minimum and the classification error rate under 10 %. To this purpose, the parallel classification strategy was implemented by using three classifiers one for each DoF: the “Elbow classifier”, the “Wrist classifier”, and the “Hand classifier” provided the simultaneous control of the elbow, hand, and wrist joints, respectively.

Results

Both the offline and real-time performance metrics were evaluated and compared with the LDA parallel classification results. The real-time recognition results were statistically better with the LR classifier with respect to the LDA classifier, for all motion classes (elbow, hand and wrist).

Conclusions

In this paper, a novel parallel PR-based strategy was proposed for classifying up to 3 DoFs: three joint classifiers were employed simultaneously for classifying 27 motion classes related to the elbow, wrist, and hand and promising results were obtained.

Quantifying Dysfunction of the Lumbar Multifidus Muscle After Radiofrequency Neurotomy and Fusion Surgery: A Preliminary Study

The multifidus is an important muscle for the active stabilization of the spine. Unfortunately, clinical procedures such as posterior lumbar fusion (PLF) and radio frequency neurotomy (RFN) cause injury to these muscles affecting their function. However, evaluating multifidus function using traditional biomechanical methods is challenging due to its unique anatomical features. The change in muscle shear modulus during contraction has been corrected to force generation for several skeletal muscles. Therefore, the change in shear modulus can be used to quantify muscle contraction. The objective of this study was to evaluate multifidus dysfunction by comparing changes in shear modulus during muscle contraction in healthy individuals and patients who received RFN and PLF in the lumbar spine. We used our recently developed protocol which consists of measuring changes of multifidus shear modulus at lying prone, sitting up, and sitting up with the arms lifted. In healthy individuals, the median multifidus shear modulus increased progressively from prone, sitting, and sitting with arms raised: 18.55 kPa, 27.14 kPa, and 38.45 kPa, respectively. A moderate increase in shear modulus for these body positions was observed in PLF patients: 9.81 kPa, 17.26 kPa, and 21.85 kPa. In RFN patients, the shear modulus remained relatively constant: 14.44 kPa, 16.57 kPa, and 17.26 kPa. Overall, RFN and PLF caused a reduction in the contraction of multifidus muscles. However, the contraction of multifidus muscle slightly increased during multifidus activation in PLF patients, while it did not change in RFN patients. These preliminary measurements suggest that the proposed protocol using SWE can provide important information about the function of individual spine muscles to guide the design and evaluation of postsurgical rehabilitation protocols.

Control Methods for Transradial Prostheses Based on Remnant Muscle Activity and Its Relationship with Proprioceptive Feedback

The loss of a hand can significantly affect one's work and social life. For many patients, an artificial limb can improve their mobility and ability to manage everyday activities, as well as provide the means to remain independent. This paper provides an extensive review of available biosensing methods to implement the control system for transradial prostheses based on the measured activity in remnant muscles. Covered techniques include electromyography, magnetomyography, electrical impedance tomography, capacitance sensing, near-infrared spectroscopy, sonomyography, optical myography, force myography, phonomyography, myokinetic control, and modern approaches to cineplasty. The paper also covers combinations of these approaches, which, in many cases, achieve better accuracy while mitigating the weaknesses of individual methods. The work is focused on the practical applicability of the approaches, and analyses present challenges associated with each technique along with their relationship with proprioceptive feedback, which is an important factor for intuitive control over the prosthetic device, especially for high dexterity prosthetic hands.

EMG-Centered Multisensory Based Technologies for Pattern Recognition in Rehabilitation: State of the Art and Challenges

In the field of rehabilitation, the electromyography (EMG) signal plays an important role in interpreting patients' intentions and physical conditions. Nevertheless, utilizing merely the EMG signal suffers from difficulty in recognizing slight body movements, and the detection accuracy is strongly influenced by environmental factors. To address the above issues, multisensory integration-based EMG pattern recognition (PR) techniques have been developed in recent years, and fruitful results have been demonstrated in diverse rehabilitation scenarios, such as achieving high locomotion detection and prosthesis control accuracy. Owing to the importance and rapid development of the EMG centered multisensory fusion technologies in rehabilitation, this paper reviews both theories and applications in this emerging field. The principle of EMG signal generation and the current pattern recognition process are explained in detail, including signal preprocessing, feature extraction, classification algorithms, etc. Mechanisms of collaborations between two important multisensory fusion strategies (kinetic and kinematics) and EMG information are thoroughly explained; corresponding applications are studied, and the pros and cons are discussed. Finally, the main challenges in EMG centered multisensory pattern recognition are discussed, and a future research direction of this area is prospected.

A Multiday Evaluation of Real-Time Intramuscular EMG Usability with ANN

Recent developments in implantable technology, such as high-density recordings, wireless transmission of signals to a prosthetic hand, may pave the way for intramuscular electromyography (iEMG)-based myoelectric control in the future. This study aimed to investigate the real-time control performance of iEMG over time. A novel protocol was developed to quantify the robustness of the real-time performance parameters. Intramuscular wires were used to record EMG signals, which were kept inside the muscles for five consecutive days. Tests were performed on multiple days using Fitts' law. Throughput, completion rate, path efficiency and overshoot were evaluated as performance metrics using three train/test strategies. Each train/test scheme was categorized on the basis of data quantity and the time difference between training and testing data. An artificial neural network (ANN) classifier was trained and tested on (i) data from the same day (WDT), (ii) data collected from the previous day and tested on present-day (BDT) and (iii) trained on all previous days including the present day and tested on present-day (CDT). It was found that the completion rate (91.6 ± 3.6%) of CDT was significantly better (p < 0.01) than BDT (74.02 ± 5.8%) and WDT (88.16 ± 3.6%). For BDT, on average, the first session of each day was significantly better (p < 0.01) than the second and third sessions for completion rate (77.9 ± 14.0%) and path efficiency (88.9 ± 16.9%). Subjects demonstrated the ability to achieve targets successfully with wire electrodes. Results also suggest that time variations in the iEMG signal can be catered by concatenating the data over several days. This scheme can be helpful in attaining stable and robust performance.

Simultaneous Prediction of Wrist/Hand Motion via Wearable Ultrasound Sensing

The ability to predict wrist and hand motions simultaneously is essential for natural controls of hand protheses. In this paper, we propose a novel method that includes subclass discriminant analysis (SDA) and principal component analysis for the simultaneous prediction of wrist rotation (pronation/supination) and finger gestures using wearable ultrasound. We tested the method on eight finger gestures with concurrent wrist rotations. Results showed that SDA was able to achieve accurate classification of both finger gestures and wrist rotations under dynamic wrist rotations. When grouping the wrist rotations into three subclasses, about 99.2 ± 1.2% of finger gestures and 92.8 ± 1.4% of wrist rotations can be accurately classified. Moreover, we found that the first principal component (PC1) of the selected ultrasound features was linear to the wrist rotation angle regardless of finger gestures. We further used PC1 in an online tracking task for continuous wrist control and demonstrated that a wrist tracking precision ( R² ) of 0.954 ± 0.012 and a finger gesture classification accuracy of 96.5 ± 1.7% can be simultaneously achieved, with only two minutes of user training. Our proposed simultaneous wrist/hand control scheme is training-efficient and robust, paving the way for musculature-driven artificial hand control and rehabilitation treatment.

Changes in Shear Modulus of the Lumbar Multifidus Muscle during Different Body Positions

Multifidus function is important for active stabilization of the spine, but it can be compromised in patients with chronic low back pain and other spine pathologies. Force production and strength of back muscles are often evaluated using isometric or isokinetic tests, which lack the ability to quantify multifidi contribution independent of the erector spinae and adjacent hip musculature. The objective of this study is to evaluate localized force production capability in multifidus muscle using ultrasound Shear Wave Elastography (SWE) in healthy individuals. Three different body positions were considered: lying prone, sitting up, and sitting up with the right arm lifted. This positions were chosen to progressively increase multifidus contraction and to minimize body motion during measurements. Shear modulus was measured at the superficial and deeper layers of the multifidus. Repeatability and possible sources of error of the shear modulus measurements were analyzed. Multifidus shear modulus (median (IQR)) increased from prone, i.e. 16.15 (6.69) kPa, to sitting up, i.e. 27.28 (15.72) kPa, to sitting up with the right arm lifted position, i.e. 45.02 (25.27) kPa. Multifidi shear modulus in the deeper layer of the multifidi were lower than the superficial layer, suggesting lower muscle contraction. Intraclass correlation coefficients (ICCs) for evaluation of shear modulus by muscle layer were found to be excellent (ICCs=0.76-0.80). Results suggest the proposed protocol could quantify local changes in spinal muscle function in healthy adults; further research in patients with spine pathology is warranted.

Improving the functionality, robustness, and adaptability of myoelectric control for dexterous motion restoration

The development of advanced and effective human-machine interfaces, especially for amputees to control their prostheses, is very high priority and a very active area of research. An intuitive control method should retain an adequate level of functionality for dexterous operation, provide robustness against confounding factors, and supply adaptability for diverse long-term usage, all of which are current problems being tackled by researchers. This paper reviews the state-of-the-art, as well as, the limitations of current myoelectric signal control (MSC) methods. To address the research topic on functionality, we review different approaches to prosthetic hand control (DOF configuration, discrete or simultaneous, etc.), and how well the control is performed (accuracy, response, intuitiveness, etc.). To address the research on robustness, we review the confounding factors (limb positions, electrode shift, force variance, and inadvertent activity) that affect the stability of the control performance. Lastly, to address adaptability, we review the strategies that can automatically adjust the classifier for different individuals and for long-term usage. This review provides a thorough overview of the current MSC methods and helps highlight the current areas of research focus and resulting clinic usability for the MSC methods for upper-limb prostheses.

Performance of Combined Surface and Intramuscular EMG for Classification of Hand Movements

The surface EMG (sEMG) has been used as control source for upper limb prosthetics since decades. Previous studies suggested that intramuscular EMG showed promising results for upper limb prosthetics. This study investigates the strength of combined surface and intramuscular EMG (cEMG) for improved myoelectric control. Five able-bodied subjects and three transradial amputees were evaluated using offline classification error as performance metric. Six surface and intramuscular channels were recorded concurrently from each subject for seven consecutive days and Stacked sparse autoencoders (SSAE) and LDA classifiers were used for classification. As a control source, either sEMG channels were used or combined channels were used with reduced features using PCA. In the within session analysis, cEMG $( 2.21 \pm 1.19${%) outperformed the sEMG ($4.63 \pm 2.07${%) for both able-bodied and amputee subjects using SSAE. For between session analysis, cEMG outperformed the sEMG for both able-bodied and amputee subjects with percentage points difference of 7.93. These results imply cEMG can significantly improve the performance of pattern recognition based myoelectric control scheme for amputee subjects too and further improvement can be made by utilizing SSAE which show improved performance as compared to LDA.

Real-time, simultaneous myoelectric control using a convolutional neural network

The evolution of deep learning techniques has been transformative as they have allowed complex mappings to be trained between control inputs and outputs without the need for feature engineering. In this work, a myoelectric control system based on convolutional neural networks (CNN) is proposed as a possible alternative to traditional approaches that rely on specifically designed features. This CNN-based system is validated using a real-time Fitts' law style target acquisition test requiring single and combined wrist motions. The performance of the proposed system is then compared to that of a standard support vector machine (SVM) based myoelectric system using a set of time-domain features. Despite the prevalence and demonstrated performance of these well-known features, no significant difference (p>0.05) was found between the two methods for any of the computed control metrics. This demonstrates the potential for automated learning approaches to extract complex and rich information from stochastic biological signals. This first evaluation of the usability of a CNN in a real-time myoelectric control environment provides a basis for further exploration.

Multiday EMG-Based Classification of Hand Motions with Deep Learning Techniques

Pattern recognition of electromyography (EMG) signals can potentially improve the performance of myoelectric control for upper limb prostheses with respect to current clinical approaches based on direct control. However, the choice of features for classification is challenging and impacts long-term performance. Here, we propose the use of EMG raw signals as direct inputs to deep networks with intrinsic feature extraction capabilities recorded over multiple days. Seven able-bodied subjects performed six active motions (plus rest), and EMG signals were recorded for 15 consecutive days with two sessions per day using the MYO armband (MYB, a wearable EMG sensor). The classification was performed by a convolutional neural network (CNN) with raw bipolar EMG samples as the inputs, and the performance was compared with linear discriminant analysis (LDA) and stacked sparse autoencoders with features (SSAE-f) and raw samples (SSAE-r) as inputs. CNN outperformed (lower classification error) both LDA and SSAE-r in the within-session, between sessions on same day, between the pair of days, and leave-out one-day evaluation (p < 0.001) analyses. However, no significant difference was found between CNN and SSAE-f. These results demonstrated that CNN significantly improved performance and increased robustness over time compared with standard LDA with associated handcrafted features. This data-driven features extraction approach may overcome the problem of the feature calibration and selection in myoelectric control.

Multiday EMG-Based Classification of Hand Motions with Deep Learning Techniques

Pattern recognition of electromyography (EMG) signals can potentially improve the performance of myoelectric control for upper limb prostheses with respect to current clinical approaches based on direct control. However, the choice of features for classification is challenging and impacts long-term performance. Here, we propose the use of EMG raw signals as direct inputs to deep networks with intrinsic feature extraction capabilities recorded over multiple days. Seven able-bodied subjects performed six active motions (plus rest), and EMG signals were recorded for 15 consecutive days with two sessions per day using the MYO armband (MYB, a wearable EMG sensor). The classification was performed by a convolutional neural network (CNN) with raw bipolar EMG samples as the inputs, and the performance was compared with linear discriminant analysis (LDA) and stacked sparse autoencoders with features (SSAE-f) and raw samples (SSAE-r) as inputs. CNN outperformed (lower classification error) both LDA and SSAE-r in the within-session, between sessions on same day, between the pair of days, and leave-out one-day evaluation (p < 0.001) analyses. However, no significant difference was found between CNN and SSAE-f. These results demonstrated that CNN significantly improved performance and increased robustness over time compared with standard LDA with associated handcrafted features. This data-driven features extraction approach may overcome the problem of the feature calibration and selection in myoelectric control.

Comparing Surface and Intramuscular Electromyography for Simultaneous and Proportional Control Based on a Musculoskeletal Model: A Pilot Study

Simultaneous and proportional control (SPC) of neural-machine interfaces uses magnitudes of smoothed electromyograms (EMG) as control inputs. Though surface EMG (sEMG) electrodes are common for clinical neural-machine interfaces, intramuscular EMG (iEMG) electrodes may be indicated in some circumstances (e.g., for controlling many degrees of freedom). However, differences in signal characteristics between sEMG and iEMG may influence SPC performance. We conducted a pilot study to determine the effect of electrode type (sEMG and iEMG) on real-time task performance with SPC based on a novel 2-degree-of-freedom EMG-driven musculoskeletal model of the wrist and hand. Four able-bodied subjects and one transradial amputee performed a virtual posture matching task with either sEMG or iEMG. There was a trend of better task performance with sEMG than iEMG for both able-bodied and amputee subjects, though the difference was not statistically significant. Thus, while iEMG may permit targeted recording of EMG, its signal characteristics may not be as ideal for SPC as those of sEMG. The tradeoff between recording specificity and signal characteristics is an important consideration for development and clinical implementation of SPC for neural-machine interfaces.

The effect of time on EMG classification of hand motions in able-bodied and transradial amputees

While several studies have demonstrated the short-term performance of pattern recognition systems, long-term investigations are very limited. In this study, we investigated changes in classification performance over time. Ten able-bodied individuals and six amputees took part in this study. EMG signals were recorded concurrently from surface and intramuscular electrodes, with intramuscular electrodes kept in the muscles for seven days. Seven hand motions were evaluated daily using linear discriminant analysis and the classification error quantified within (WCE) and between (BCE) days. BCE was computed for all possible combinations between the days. For all subjects, surface sEMG (7.2 ± 7.6%), iEMG (11.9 ± 9.1%) and cEMG (4.6 ± 4.8%) were significantly different (P < 0.001) from each other. A regression between WCE and days (1-7) was on average not significant implying that performance may be considered similar within each day. Regression between BCE and time difference (Df) in days was significant. The slope between BCE and Df (0-6) was significantly different from zero for sEMG (R² = 89%) and iEMG (R² = 95%) in amputees. Results indicate that performance continuously degrades as the time difference between training and testing day increases. Furthermore, for iEMG, performance in amputees was directly proportional to the size of the residual limb.

Voluntary phantom hand and finger movements in transhumerai amputees could be used to naturally control polydigital prostheses

An arm amputation is extremely invalidating since many of our daily tasks require bi-manual and precise control of hand movements. Perfect hand prostheses should therefore offer a natural, intuitive and cognitively simple control over their numerous biomimetic active degrees of freedom. While efficient polydigital prostheses are commercially available, their control remains complex to master and offers limited possibilities, especially for high amputation levels. In this pilot study, we demonstrate the possibility for upper-arm amputees to intuitively control a polydigital hand prosthesis by using surface myoelectric activities of residual limb muscles (sEMG) associated with phantom limb movements, even if these residual arm muscles on which the phantom activity is measured were not naturally associated with hand movements before amputation. Using pattern recognition methods, three arm amputees were able, without training, to initiate 5-8 movements of a robotic hand (including individual finger movements) by simply mobilizing their phantom limb while the robotic hand was mimicking the action in real time. This innovative control approach could offer to numerous upper-limb amputees an access to recent biomimetic prostheses with multiple controllable joints, without requiring surgery or complex training; and might deeply change the way the phantom limb is apprehended by both patients and clinicians.

Using spatial features for classification of combined motions based on common spatial pattern

Motion recognition is an important application of electromyography (EMG) analysis. While discrete motions such as hand open, hand close and wrist pronation have been extensively investigated, studies on combined motions involving two or more degrees of freedom (DOFs) are relatively few and the classification accuracy of the combined motions reported in previous studies is barely satisfactory. To improve the accuracy of the combined motion recognition, common spatial pattern (CSP) was employed in this study to extract spatial features. 18 forearm motion classes, consisted of 8 discrete motions and 10 combined motions, were classified by the proposed method. Our results showed that the accuracy rate of CSP features was 96.3%, which outperformed the commonly used time-domain (TD) features by 2.4% and TD combined with auto-regression coefficients (TDAR) by 0.6%. Moreover, CSP features cost noticeable much less time than TDAR and quite less time than TD in testing. These results suggest that CSP features could be a better feature set for multi-DOF myoelectric control than conventional features.

EMG Processing Based Measures of Fatigue Assessment during Manual Lifting

Manual lifting is one of the common practices used in the industries to transport or move objects to a desired place. Nowadays, even though mechanized equipment is widely available, manual lifting is still considered as an essential way to perform material handling task. Improper lifting strategies may contribute to musculoskeletal disorders (MSDs), where overexertion contributes as the highest factor. To overcome this problem, electromyography (EMG) signal is used to monitor the workers' muscle condition and to find maximum lifting load, lifting height and number of repetitions that the workers are able to handle before experiencing fatigue to avoid overexertion. Past researchers have introduced several EMG processing techniques and different EMG features that represent fatigue indices in time, frequency, and time-frequency domain. The impact of EMG processing based measures in fatigue assessment during manual lifting are reviewed in this paper. It is believed that this paper will greatly benefit researchers who need a bird's eye view of the biosignal processing which are currently available, thus determining the best possible techniques for lifting applications.

Muscle Activity Map Reconstruction from High Density Surface EMG Signals With Missing Channels Using Image Inpainting and Surface Reconstruction Methods

OBJECTIVE

The aim of this study was to reconstruct low-quality High-density surface EMG (HDsEMG) signals, recorded with 2-D electrode arrays, using image inpainting and surface reconstruction methods.

METHODS

It is common that some fraction of the electrodes may provide low-quality signals. We used variety of image inpainting methods, based on partial differential equations (PDEs), and surface reconstruction methods to reconstruct the time-averaged or instantaneous muscle activity maps of those outlier channels. Two novel reconstruction algorithms were also proposed. HDsEMG signals were recorded from the biceps femoris and brachial biceps muscles during low-to-moderate-level isometric contractions, and some of the channels (5-25%) were randomly marked as outliers. The root-mean-square error (RMSE) between the original and reconstructed maps was then calculated.

RESULTS

Overall, the proposed Poisson and wave PDE outperformed the other methods (average RMSE 8.7 μV_rms ± 6.1 μV_rms and 7.5 μV_rms ± 5.9 μV_rms) for the time-averaged single-differential and monopolar map reconstruction, respectively. Biharmonic Spline, the discrete cosine transform, and the Poisson PDE outperformed the other methods for the instantaneous map reconstruction. The running time of the proposed Poisson and wave PDE methods, implemented using a Vectorization package, was 4.6 ± 5.7 ms and 0.6 ± 0.5 ms, respectively, for each signal epoch or time sample in each channel.

CONCLUSION

The proposed reconstruction algorithms could be promising new tools for reconstructing muscle activity maps in real-time applications.

SIGNIFICANCE

Proper reconstruction methods could recover the information of low-quality recorded channels in HDsEMG signals.

Nonlinear mappings between discrete and simultaneous motions to decrease training burden of simultaneous pattern recognition myoelectric control

Real-time simultaneous pattern recognition (PR) control of multiple degrees of freedom (DOF) has been demonstrated using a set of parallel linear discriminant analysis (LDA) classifiers trained with both discrete (1-DOF) and simultaneous (2-DOF) motion data. However, this training method presents a clinical challenge, requiring large amounts of data necessary to re-train the system. This study presents a parallel classifier training method that aims to reduce the training burden. Artificial neural networks (ANNs) were used to determine a nonlinear mapping between surface EMG features of 2-DOF motions and their 1-DOF motion components. The mapping was then used to transform experimentally collected features of 1-DOF motions into simulated features of 2-DOF motions. A set of parallel LDA classifiers were trained using the novel training method and two previously reported training methods. The training methods evaluated were (1) using experimentally collected 1-DOF data and ANN-simulated 2-DOF data, (2) using only experimentally collected 1-DOF data and (3) using experimentally collected 1- and 2-DOF data. Using the novel training method resulted in significantly lower classification error overall (p<;0.01) and in predicting 2-DOF motions (p<;0.01) compared to training with experimental 1-DOF data only. These findings demonstrate that using a set of ANNs to predict 2-DOF data from 1-DOF data can improve system performance when only discrete training data are available, thus reducing the training burden of simultaneous PR control.

Enhancing the versatility of wireless biopotential acquisition for myoelectric prosthetic control

OBJECTIVE

A significant challenge in rehabilitating upper-limb amputees with sophisticated, electric-powered prostheses is sourcing reliable and independent channels of motor control information sufficient to precisely direct multiple degrees of freedom simultaneously.

APPROACH

In response to the expressed needs of clinicians, we have developed a miniature, batteryless recording device that utilizes emerging integrated circuit technology and optimal impedance matching for magnetic resonantly coupled (MRC) wireless power transfer to improve the performance and versatility of wireless electrode interfaces with muscle.

MAIN RESULTS

In this work we describe the fabrication and performance of a fully wireless and batteryless EMG recording system and use of this system to direct virtual and electric-powered limbs in real-time. The advantage of using MRC to optimize power transfer to a network of wireless devices is exhibited by EMG collected from an array of eight devices placed circumferentially around a human subject's forearm.

SIGNIFICANCE

This is a comprehensive, low-cost, and non-proprietary solution that provides unprecedented versatility of configuration to direct myoelectric prostheses without wired connections to the body. The amenability of MRC to varied coil geometries and arrangements has the potential to improve the efficiency and robustness of wireless power transfer links at all levels of upper-limb amputation. Additionally, the wireless recording device's programmable flash memory and selectable features will grant clinicians the unique ability to adapt and personalize the recording system's functional protocol for patient- or algorithm-specific needs.

Use of probabilistic weights to enhance linear regression myoelectric control

OBJECTIVE

Clinically available prostheses for transradial amputees do not allow simultaneous myoelectric control of degrees of freedom (DOFs). Linear regression methods can provide simultaneous myoelectric control, but frequently also result in difficulty with isolating individual DOFs when desired. This study evaluated the potential of using probabilistic estimates of categories of gross prosthesis movement, which are commonly used in classification-based myoelectric control, to enhance linear regression myoelectric control.

APPROACH

Gaussian models were fit to electromyogram (EMG) feature distributions for three movement classes at each DOF (no movement, or movement in either direction) and used to weight the output of linear regression models by the probability that the user intended the movement. Eight able-bodied and two transradial amputee subjects worked in a virtual Fitts' law task to evaluate differences in controllability between linear regression and probability-weighted regression for an intramuscular EMG-based three-DOF wrist and hand system.

MAIN RESULTS

Real-time and offline analyses in able-bodied subjects demonstrated that probability weighting improved performance during single-DOF tasks (p < 0.05) by preventing extraneous movement at additional DOFs. Similar results were seen in experiments with two transradial amputees. Though goodness-of-fit evaluations suggested that the EMG feature distributions showed some deviations from the Gaussian, equal-covariance assumptions used in this experiment, the assumptions were sufficiently met to provide improved performance compared to linear regression control.

SIGNIFICANCE

Use of probability weights can improve the ability to isolate individual during linear regression myoelectric control, while maintaining the ability to simultaneously control multiple DOFs.

Human-Machine Interface for the Control of Multi-Function Systems Based on Electrocutaneous Menu: Application to Multi-Grasp Prosthetic Hands

Modern assistive devices are very sophisticated systems with multiple degrees of freedom. However, an effective and user-friendly control of these systems is still an open problem since conventional human-machine interfaces (HMI) cannot easily accommodate the system’s complexity. In HMIs, the user is responsible for generating unique patterns of command signals directly triggering the device functions. This approach can be difficult to implement when there are many functions (necessitating many command patterns) and/or the user has a considerable impairment (limited number of available signal sources). In this study, we propose a novel concept for a general-purpose HMI where the controller and the user communicate bidirectionally to select the desired function. The system first presents possible choices to the user via electro-tactile stimulation; the user then acknowledges the desired choice by generating a single command signal. Therefore, the proposed approach simplifies the user communication interface (one signal to generate), decoding (one signal to recognize), and allows selecting from a number of options. To demonstrate the new concept the method was used in one particular application, namely, to implement the control of all the relevant functions in a state of the art commercial prosthetic hand without using any myoelectric channels. We performed experiments in healthy subjects and with one amputee to test the feasibility of the novel approach. The results showed that the performance of the novel HMI concept was comparable or, for some outcome measures, better than the classic myoelectric interfaces. The presented approach has a general applicability and the obtained results point out that it could be used to operate various assistive systems (e.g., prosthesis vs. wheelchair), or it could be integrated into other control schemes (e.g., myoelectric control, brain-machine interfaces) in order to improve the usability of existing low-bandwidth HMIs.

Myoelectric Control System and Task-Specific Characteristics Affect Voluntary Use of Simultaneous Control

Clinically available myoelectric control does not enable simultaneous proportional control of prosthetic degrees of freedom. Multiple studies have proposed systems that provide simultaneous control, though few have investigated whether subjects voluntarily use simultaneous control or how they implement it. Additionally, few studies have explicitly evaluated the effect of providing proportional velocity control. The objective of this study was to evaluate factors influencing when and how subjects use simultaneous myoelectric control, including the ability to proportionally control the velocity and the required task precision. Five able-bodied subjects used simultaneous myoelectric control systems with and without proportional velocity control in a virtual Fitts' Law task. Though subjects used simultaneous control to a substantial degree when proportional velocity control was present, they used very little simultaneous control when using constant-velocity control. Furthermore, use of simultaneous control varied significantly with target distance and width, reflecting a strategy of using simultaneous control for gross cursor positioning and sequential control for fine corrective movements. These results provide insight into how users take advantage of simultaneous control and highlight the need for real-time evaluation of simultaneous control algorithms, as the potential benefit of providing simultaneous control may be affected by other characteristics of the myoelectric control system.

Real-time simultaneous and proportional myoelectric control using intramuscular EMG

OBJECTIVE

Myoelectric prostheses use electromyographic (EMG) signals to control movement of prosthetic joints. Clinically available myoelectric control strategies do not allow simultaneous movement of multiple degrees of freedom (DOFs); however, the use of implantable devices that record intramuscular EMG signals could overcome this constraint. The objective of this study was to evaluate the real-time simultaneous control of three DOFs (wrist rotation, wrist flexion/extension, and hand open/close) using intramuscular EMG.

APPROACH

We evaluated task performance of five able-bodied subjects in a virtual environment using two control strategies with fine-wire EMG: (i) parallel dual-site differential control, which enabled simultaneous control of three DOFs and (ii) pattern recognition control, which required sequential control of DOFs.

MAIN RESULTS

Over the course of the experiment, subjects using parallel dual-site control demonstrated increased use of simultaneous control and improved performance in a Fitts' Law test. By the end of the experiment, performance using parallel dual-site control was significantly better (up to a 25% increase in throughput) than when using sequential pattern recognition control for tasks requiring multiple DOFs. The learning trends with parallel dual-site control suggested that further improvements in performance metrics were possible. Subjects occasionally experienced difficulty in performing isolated single-DOF movements with parallel dual-site control but were able to accomplish related Fitts' Law tasks with high levels of path efficiency.

SIGNIFICANCE

These results suggest that intramuscular EMG, used in a parallel dual-site configuration, can provide simultaneous control of a multi-DOF prosthetic wrist and hand and may outperform current methods that enforce sequential control.

Extrinsic finger and thumb muscles command a virtual hand to allow individual finger and grasp control

Fine-wire intramuscular electrodes were used to obtain electromyogram (EMG) signals from six extrinsic hand muscles associated with the thumb, index, and middle fingers. Subjects' EMG activity was used to control a virtual three-degree-of-freedom (DOF) hand as they conformed the hand to a sequence of hand postures testing two controllers: direct EMG control and pattern recognition control. Subjects tested two conditions using each controller: starting the hand from a predefined neutral posture before each new posture and starting the hand from the previous posture in the sequence. Subjects demonstrated their abilities to simultaneously, yet individually, move all three DOFs during the direct EMG control trials; however, results showed subjects did not often utilize this feature. Performance metrics such as failure rate and completion time showed no significant difference between the two controllers.

Support vector regression for improved real-time, simultaneous myoelectric control

This study describes the first application of a support vector machine (SVM) based scheme for real-time simultaneous and proportional myoelectric control of multiple degrees of freedom (DOFs). Three DOFs including wrist flexion-extension, abduction-adduction and forearm pronation-supination were investigated with 10 able-bodied subjects and two individuals with transradial limb deficiency (LD). A Fitts' law test involving real-time target acquisition tasks was conducted to compare the usability of the SVM-based control system to that of an artificial neural network (ANN) based method. Performance was assessed using the Fitts' law throughput value as well as additional metrics including completion rate, path efficiency and overshoot. The SVM-based approach outperformed the ANN-based system in every performance measure for able-bodied subjects. The SVM outperformed the ANN in path efficiency and throughput with the first LD subject and in throughput with the second LD subject. The superior performance of the SVM-based system appears to be due to its higher estimation accuracy of all DOFs during inactive and low amplitude segments (these periods were frequent during real-time control). Another advantage of the SVM-based method was that it substantially reduced the processing time for both training and real time control.