A Study of Movement Classification of the Lower Limb Based on up to 4-EMG Channels

Design and Analysis of an Upper Limb Rehabilitation Robot Based on Multimodal Control

To address the rehabilitation needs of upper limb hemiplegic patients in various stages of recovery, streamline the workload of rehabilitation professionals, and provide data visualization, our research team designed a six-degree-of-freedom upper limb exoskeleton rehabilitation robot inspired by the human upper limb's structure. We also developed an eight-channel synchronized signal acquisition system for capturing surface electromyography (sEMG) signals and elbow joint angle data. Utilizing Solidworks, we modeled the robot with a focus on modularity, and conducted structural and kinematic analyses. To predict the elbow joint angles, we employed a back propagation neural network (BPNN). We introduced three training modes: a PID control, bilateral control, and active control, each tailored to different phases of the rehabilitation process. Our experimental results demonstrated a strong linear regression relationship between the predicted reference values and the actual elbow joint angles, with an R-squared value of 94.41% and an average error of four degrees. Furthermore, these results validated the increased stability of our model and addressed issues related to the size and single-mode limitations of upper limb rehabilitation robots. This work lays the theoretical foundation for future model enhancements and further research in the field of rehabilitation.

Sign Language Recognition Using the Electromyographic Signal: A Systematic Literature Review

The analysis and recognition of sign languages are currently active fields of research focused on sign recognition. Various approaches differ in terms of analysis methods and the devices used for sign acquisition. Traditional methods rely on video analysis or spatial positioning data calculated using motion capture tools. In contrast to these conventional recognition and classification approaches, electromyogram (EMG) signals, which measure muscle electrical activity, offer potential technology for detecting gestures. These EMG-based approaches have recently gained attention due to their advantages. This prompted us to conduct a comprehensive study on the methods, approaches, and projects utilizing EMG sensors for sign language handshape recognition. In this paper, we provided an overview of the sign language recognition field through a literature review, with the objective of offering an in-depth review of the most significant techniques. These techniques were categorized in this article based on their respective methodologies. The survey discussed the progress and challenges in sign language recognition systems based on surface electromyography (sEMG) signals. These systems have shown promise but face issues like sEMG data variability and sensor placement. Multiple sensors enhance reliability and accuracy. Machine learning, including deep learning, is used to address these challenges. Common classifiers in sEMG-based sign language recognition include SVM, ANN, CNN, KNN, HMM, and LSTM. While SVM and ANN are widely used, random forest and KNN have shown better performance in some cases. A multilayer perceptron neural network achieved perfect accuracy in one study. CNN, often paired with LSTM, ranks as the third most popular classifier and can achieve exceptional accuracy, reaching up to 99.6% when utilizing both EMG and IMU data. LSTM is highly regarded for handling sequential dependencies in EMG signals, making it a critical component of sign language recognition systems. In summary, the survey highlights the prevalence of SVM and ANN classifiers but also suggests the effectiveness of alternative classifiers like random forests and KNNs. LSTM emerges as the most suitable algorithm for capturing sequential dependencies and improving gesture recognition in EMG-based sign language recognition systems.

An Attention-based Bidirectional LSTM Model for Continuous Cross-Subject Estimation of Knee Joint Angle during Running from sEMG Signals

Accurate and robust estimation of joint kinematics via surface electromyogram (sEMG) signals provides a human-machine interaction (HMI)-based method that can be used to adequately control rehabilitation robots while performing complex movements, such as running, for motor function restoration in affected individuals. To this end, this paper proposes a deep learning-based model (AM-BiLSTM) that integrates a bidirectional long short-term memory (BiLSTM) network and an attention mechanism (AM) for robust estimation of joint kinematics. The proposed model was appraised using knee joint kinematic and sEMG signals collected from fourteen subjects who performed running at the speed of 2 m/s. The proposed model's generalizability was tested for both within- and cross-subject scenarios and compared with long short-term memory (LSTM) and multi-layer perceptron (MLP) networks in terms of normalized root-mean-square error and correlation coefficient metrics. Based on the statistical tests, the proposed AM-BiLSTM model significantly outperformed the LSTM and MLP methods in both within- and cross-subject scenarios (p<0.05) and achieved state-of-the-art performance.Clinical Relevance- The promising results of this study suggest that the AM-BiLSTM model has the potential for continuous cross-subject estimation of lower limb kinematics during running, which can be used to control sEMG-driven exoskeleton robots oriented towards rehabilitation training.

Surface electromyogram, kinematic, and kinetic dataset of lower limb walking for movement intent recognition

Surface electromyogram (sEMG) offers a rich set of motor information for decoding limb motion intention that serves as a control input to Intelligent human-machine synergy systems (IHMSS). Despite growing interest in IHMSS, the current publicly available datasets are limited and can hardly meet the growing demands of researchers. This study presents a novel lower limb motion dataset (designated as SIAT-LLMD), comprising sEMG, kinematic, and kinetic data with corresponding labels acquired from 40 healthy humans during 16 movements. The kinematic and kinetic data were collected using a motion capture system and six-dimensional force platforms and processed using OpenSim software. The sEMG data were recorded using nine wireless sensors placed on the subjects' thigh and calf muscles on the left limb. Besides, SIAT-LLMD provides labels to classify the different movements and different gait phases. Analysis of the dataset verified the synchronization and reproducibility, and codes for effective data processing are provided. The proposed dataset can serve as a new resource for exploring novel algorithms and models for characterizing lower limb movements.

Repeatability and Temporal Consistency of Lower Limb Biomechanical Variables Expressing Interlimb Coordination during the Double-Support Phase in People with and without Stroke Sequelae

Reliable biomechanical methods to assess interlimb coordination during the double-support phase in post-stroke subjects are needed for assessing movement dysfunction and related variability. The data obtained could provide a significant contribution for designing rehabilitation programs and for their monitorisation. The present study aimed to determine the minimum number of gait cycles needed to obtain adequate values of repeatability and temporal consistency of lower limb kinematic, kinetic, and electromyographic parameters during the double support of walking in people with and without stroke sequelae. Eleven post-stroke and thirteen healthy participants performed 20 gait trials at self-selected speed in two separate moments with an interval between 72 h and 7 days. The joint position, the external mechanical work on the centre of mass, and the surface electromyographic activity of the tibialis anterior, soleus, gastrocnemius medialis, rectus femoris, vastus medialis, biceps femoris, and gluteus maximus muscles were extracted for analysis. Both the contralesional and ipsilesional and dominant and non-dominant limbs of participants with and without stroke sequelae, respectively, were evaluated either in trailing or leading positions. The intraclass correlation coefficient was used for assessing intra-session and inter-session consistency analysis. For most of the kinematic and the kinetic variables studied in each session, two to three trials were required for both groups, limbs, and positions. The electromyographic variables presented higher variability, requiring, therefore, a number of trials ranging from 2 to >10. Globally, the number of trials required inter-session ranged from 1 to >10 for kinematic, from 1 to 9 for kinetic, and 1 to >10 for electromyographic variables. Thus, for the double support analysis, three gait trials were required in order to assess the kinematic and kinetic variables in cross-sectional studies, while for longitudinal studies, a higher number of trials (>10) were required for kinematic, kinetic, and electromyographic variables.

Low limb prostheses and complex human prosthetic interaction: A systematic literature review

A few years ago, powered prostheses triggered new technological advances in diverse areas such as mobility, comfort, and design, which have been essential to improving the quality of life of individuals with lower limb disability. The human body is a complex system involving mental and physical health, meaning a dependant relationship between its organs and lifestyle. The elements used in the design of these prostheses are critical and related to lower limb amputation level, user morphology and human-prosthetic interaction. Hence, several technologies have been employed to accomplish the end user's needs, for example, advanced materials, control systems, electronics, energy management, signal processing, and artificial intelligence. This paper presents a systematic literature review on such technologies, to identify the latest advances, challenges, and opportunities in developing lower limb prostheses with the analysis on the most significant papers. Powered prostheses for walking in different terrains were illustrated and examined, with the kind of movement the device should perform by considering the electronics, automatic control, and energy efficiency. Results show a lack of a specific and generalised structure to be followed by new developments, gaps in energy management and improved smoother patient interaction. Additionally, Human Prosthetic Interaction (HPI) is a term introduced in this paper since no other research has integrated this interaction in communication between the artificial limb and the end-user. The main goal of this paper is to provide, with the found evidence, a set of steps and components to be followed by new researchers and experts looking to improve knowledge in this field.

Supervised Myoelectrical Hand Gesture Recognition in Post-Acute Stroke Patients with Upper Limb Paresis on Affected and Non-Affected Sides

In clinical practice, acute post-stroke paresis of the extremities fundamentally complicates timely rehabilitation of motor functions; however, recently, residual and distorted musculoskeletal signals have been used to initiate feedback-driven solutions for establishing motor rehabilitation. Here, we investigate the possibilities of basic hand gesture recognition in acute stroke patients with hand paresis using a novel, acute stroke, four-component multidomain feature set (ASF-4) with feature vector weight additions (ASF-14NP, ASF-24P) and supervised learning algorithms trained only by surface electromyography (sEMG). A total of 19 (65.9 ± 12.4 years old; 12 men, seven women) acute stroke survivors (12.4 ± 6.3 days since onset) with hand paresis (Brunnstrom stage 4 ± 1/4 ± 1, SIAS 3 ± 1/3 ± 2, FMA-UE 40 ± 20) performed 10 repetitive hand movements reflecting basic activities of daily living (ADLs): rest, fist, pinch, wrist flexion, wrist extension, finger spread, and thumb up. Signals were recorded using an eight-channel, portable sEMG device with electrode placement on the forearms and thenar areas of both limbs (four sensors on each extremity). Using data preprocessing, semi-automatic segmentation, and a set of extracted feature vectors, support vector machine (SVM), linear discriminant analysis (LDA), and k-nearest neighbors (k-NN) classifiers for statistical comparison and validity (paired t-tests, p-value < 0.05), we were able to discriminate myoelectrical patterns for each gesture on both paretic and non-paretic sides. Despite any post-stroke conditions, the evaluated total accuracy rate by the 10-fold cross-validation using SVM among four-, five-, six-, and seven-gesture models were 96.62%, 94.20%, 94.45%, and 95.57% for non-paretic and 90.37%, 88.48%, 88.60%, and 89.75% for paretic limbs, respectively. LDA had competitive results using PCA whereas k-NN was a less efficient classifier in gesture prediction. Thus, we demonstrate partial efficacy of the combination of sEMG and supervised learning for upper-limb rehabilitation procedures for early acute stroke motor recovery and various treatment applications.

A Simulation Study to Assess the Factors of Influence on Mean and Median Frequency of sEMG Signals during Muscle Fatigue

Mean and Median frequency are typically used for detecting and monitoring muscle fatigue. These parameters are extracted from power spectral density whose estimate can be obtained by several techniques, each one characterized by advantages and disadvantages. Previous works studied how the implementation settings can influence the performance of these techniques; nevertheless, the estimation results have never been fully evaluated when the power density spectrum is in a low-frequency zone, as happens to the surface electromyography (sEMG) spectrum during muscle fatigue. The latter is therefore the objective of this study that has compared the Welch and the autoregressive parametric approaches on synthetic sEMG signals simulating severe muscle fatigue. Moreover, the sensitivity of both the approaches to the observation duration and to the level of noise has been analyzed. Results showed that the mean frequency greatly depends on the noise level, and that for Signal to Noise Ratio (SNR) less than 10dB the errors make the estimate unacceptable. On the other hand, the error in calculating the median frequency is always in the range 2-10 Hz, so this parameter should be preferred in the tracking of muscle fatigue. Results show that the autoregressive model always outperforms the Welch technique, and that the 3rd order continuously produced accurate and precise estimates; consequently, the latter should be used when analyzing severe fatiguing contraction.

A Review of EMG-, FMG-, and EIT-Based Biosensors and Relevant Human–Machine Interactivities and Biomedical Applications

Wearables developed for human body signal detection receive increasing attention in the current decade. Compared to implantable sensors, wearables are more focused on body motion detection, which can support human–machine interaction (HMI) and biomedical applications. In wearables, electromyography (EMG)-, force myography (FMG)-, and electrical impedance tomography (EIT)-based body information monitoring technologies are broadly presented. In the literature, all of them have been adopted for many similar application scenarios, which easily confuses researchers when they start to explore the area. Hence, in this article, we review the three technologies in detail, from basics including working principles, device architectures, interpretation algorithms, application examples, merits and drawbacks, to state-of-the-art works, challenges remaining to be solved and the outlook of the field. We believe the content in this paper could help readers create a whole image of designing and applying the three technologies in relevant scenarios.

The Effect of Sun Tan Lotion on Skin by Using Skin TEWL and Skin Water Content Measurements

Stratum corneum (SC) is the outermost skin layer. SC hydration is important for its cosmetic properties and barrier function. SC trans-epidermal water loss (TEWL) measurements and skin water content measurements are two key indexes used for SC characterisation. The instrument stability and accuracy are vitally important when measuring small changes. In this paper, we present our latest study on the effect of sun tan lotion on skin by using skin TEWL and skin water content measurements. We developed techniques to improve the measurement stability and to visualise small changes, as well as developed machine learning algorithms for processing the skin capacitive images. The overall results show that TEWL and skin water content measurements are capable of measuring the subtle changes of skin conditions due to the application of sun tan lotions. The results show that the TEWL values decreased after the sun tan lotion application. The sun tan lotion with SPF 20 had the lowest decrease, whilst the sun tan lotion with SPF 50+ had the highest decrease. The results also show that the skin water content increased after the sun tan lotion application, with SPF 20 having the highest increase, whilst SPF 50+ had the lowest increase.

Asymmetric Free-Hand Interaction on a Large Display and Inspirations for Designing Natural User Interfaces

Hand motion sensing-based interaction, abbreviated as ‘free-hand interaction’, provides a natural and intuitive method for touch-less interaction on a large display. But due to inherent usability deficiencies of the unconventional size of the large display and the kinematic limitations of the user’s arm joint movement, a large display-based free-hand interaction is suspected to have different performance across the whole areas of the large display. To verify this, a multi-directional target pointing and selection experiment was designed and conducted based on the ISO 9241-9 evaluation criteria. Results show that (1) free-hand interaction in display areas close to the center of the body had a higher accuracy than that in peripheral-body areas; (2) free-hand interaction was asymmetric at the left side and the right side of the body. More specifically, left-hand interaction in the left-sided display area was more efficient and accurate than in the right-sided display area. For the right-hand interaction, the result was converse; moreover, (3) the dominant hand generated a higher interaction accuracy than the non-dominant hand. Lessons and strategies are discussed for designing user-friendly natural user interfaces in large displays-based interactive applications.

Prediction of Upper Limb Action Intention Based on Long Short-Term Memory Neural Network

The use of an inertial measurement unit (IMU) to measure the motion data of the upper limb is a mature method, and the IMU has gradually become an important device for obtaining information sources to control assistive prosthetic hands. However, the control method of the assistive prosthetic hand based on the IMU often has problems with high delay. Therefore, this paper proposes a method for predicting the action intentions of upper limbs based on a long short-term memory (LSTM) neural network. First, the degree of correlation between palm movement and arm movement is compared, and the Pearson correlation coefficient is calculated. The correlation coefficients are all greater than 0.6, indicating that there is a strong correlation between palm movement and arm movement. Then, the motion state of the upper limb is divided into the acceleration state, deceleration state and rest state. The rest state of the upper limb is used as a sign to control the assistive prosthetic hand. Using the LSTM to identify the motion state of the upper limb, the accuracy rate is 99%. When predicting the action intention of the upper limb based on the angular velocity of the shoulder and forearm, the LSTM is used to predict the angular velocity of the palm, and the average prediction error of palm motion is 1.5 rad/s. Finally, the feasibility of the method is verified through experiments, in the form of holding an assistive prosthetic hand to imitate a disabled person wearing a prosthesis. The assistive prosthetic hand is used to reproduce foot actions, and the average delay time of foot action was 0.65 s, which was measured by using the method based on the LSTM neural network. However, the average delay time of the manipulator control method based on threshold analysis is 1.35 s. Our experiments show that the prediction method based on the LSTM can achieve low prediction error and delay.

Similarities and disparities between visual analysis and high-resolution electromyography of facial expressions

Computer vision (CV) is widely used in the investigation of facial expressions. Applications range from psychological evaluation to neurology, to name just two examples. CV for identifying facial expressions may suffer from several shortcomings: CV provides indirect information about muscle activation, it is insensitive to activations that do not involve visible deformations, such as jaw clenching. Moreover, it relies on high-resolution and unobstructed visuals. High density surface electromyography (sEMG) recordings with soft electrode array is an alternative approach which provides direct information about muscle activation, even from freely behaving humans. In this investigation, we compare CV and sEMG analysis of facial muscle activation. We used independent component analysis (ICA) and multiple linear regression (MLR) to quantify the similarity and disparity between the two approaches for posed muscle activations. The comparison reveals similarity in event detection, but discrepancies and inconsistencies in source identification. Specifically, the correspondence between sEMG and action unit (AU)-based analyses, the most widely used basis of CV muscle activation prediction, appears to vary between participants and sessions. We also show a comparison between AU and sEMG data of spontaneous smiles, highlighting the differences between the two approaches. The data presented in this paper suggests that the use of AU-based analysis should consider its limited ability to reliably compare between different sessions and individuals and highlight the advantages of high-resolution sEMG for facial expression analysis.

Flexible Strain-Sensitive Silicone-CNT Sensor for Human Motion Detection

This article describes the manufacturing technology of biocompatible flexible strain-sensitive sensor based on Ecoflex silicone and multi-walled carbon nanotubes (MWCNT). The sensor demonstrates resistive behavior. Structural, electrical, and mechanical characteristics are compared. It is shown that laser radiation significantly reduces the resistance of the material. Through laser radiation, electrically conductive networks of MWCNT are formed in a silicone matrix. The developed sensor demonstrates highly sensitive characteristics: gauge factor at 100% elongation −4.9, gauge factor at 90° bending −0.9%/deg, stretchability up to 725%, tensile strength 0.7 MPa, modulus of elasticity at 100% 46 kPa, and the temperature coefficient of resistance in the range of 30–40 °C is −2 × 10⁻³. There is a linear sensor response (with 1 ms response time) with a low hysteresis of ≤3%. An electronic unit for reading and processing sensor signals based on the ATXMEGA8E5-AU microcontroller has been developed. The unit was set to operate the sensor in the range of electrical resistance 5–150 kOhm. The Bluetooth module made it possible to transfer the received data to a personal computer. Currently, in the field of wearable technologies and health monitoring, a vital need is the development of flexible sensors attached to the human body to track various indicators. By integrating the sensor with the joints of the human hand, effective movement sensing has been demonstrated.

sEMG-Based Motion Recognition of Upper Limb Rehabilitation Using the Improved Yolo-v4 Algorithm

The surface electromyography (sEMG) signal is widely used as a control source of the upper limb exoskeleton rehabilitation robot. However, the traditional way of controlling the exoskeleton robot by the sEMG signal requires one to specially extract and calculate for complex sEMG features. Moreover, due to the huge amount of calculation and individualized difference, the real-time control of the exoskeleton robot cannot be realized. Therefore, this paper proposes a novel method using an improved detection algorithm to recognize limb joint motion and detect joint angle based on sEMG images, aiming to obtain a high-security and fast-processing action recognition strategy. In this paper, MobileNetV2 combined the Ghost module as the feature extraction network to obtain the pretraining model. Then, the target detection network Yolo-V4 was used to estimate the six movement categories of the upper limb joints and to predict the joint movement angles. The experimental results showed that the proposed motion recognition methods were available. Every 100 pictures can be accurately identified in approximately 78 pictures, and the processing speed of every single picture on the PC side was 17.97 ms. For the train data, the mAP@0.5 could reach 82.3%, and mAP@0.5–0.95 could reach 0.42; for the verification data, the average recognition accuracy could reach 80.7%.

A Mirror Bilateral Neuro-Rehabilitation Robot System with the sEMG-Based Real-Time Patient Active Participant Assessment

In this paper, a novel mirror visual feedback-based (MVF) bilateral neurorehabilitation system with surface electromyography (sEMG)-based patient active force assessment was proposed for upper limb motor recovery and improvement of limb inter-coordination. A mirror visual feedback-based human–robot interface was designed to facilitate the bilateral isometric force output training task. To achieve patient active participant assessment, an sEMG signals-based elbow joint isometric force estimation method was implemented into the proposed system for real-time affected side force assessment and participation evaluation. To assist the affected side limb efficiently and precisely, a mirror bilateral control framework was presented for bilateral limb coordination. Preliminary experiments were conducted to evaluate the estimation accuracy of force estimation method and force tracking accuracy of system performance. The experimental results show the proposed force estimation method can efficiently calculate the elbow joint force in real-time, and the affected side limb of patients can be assisted to track output force of the non-paretic side limb for better limb coordination by the proposed bilateral rehabilitation system.

A Novel EMG-Based Hand Gesture Recognition Framework Based on Multivariate Variational Mode Decomposition

Surface electromyography (sEMG) is a kind of biological signal that records muscle activity noninvasively, which is of great significance in advanced human-computer interaction, prosthetic control, clinical therapy, and biomechanics. However, the number of hand gestures that can be recognized is limited and the recognition accuracy needs to be further improved. These factors lead to the fact that sEMG products are not widely used in practice. The main contributions of this paper are as follows. Firstly, considering the increasing number of gestures to be recognized and the complexity of gestures, an extensible two-stage machine learning lightweight framework was innovatively proposed for multi-gesture task recognition. Secondly, the multivariate variational mode decomposition (MVMD) is applied to extract the spatial–temporal features from the multiple channels to the EMG signals, and the separable convolutional neural network is used for modelling. In this work, the experimental results for 52 hand gestures recognition task show that the average accuracy on each stage is about 90%. The potential movement information is mainly contained in the low-frequency oscillator of the sEMG signal, and the model performs better with the low-frequency oscillation from the MVMD algorithm on the second stage classification than that of other decomposition methods.

Action Recognition of Lower Limbs Based on Surface Electromyography Weighted Feature Method

To improve the recognition rate of lower limb actions based on surface electromyography (sEMG), an effective weighted feature method is proposed, and an improved genetic algorithm support vector machine (IGA-SVM) is designed in this paper. First, for the problem of high feature redundancy and low discrimination in the surface electromyography feature extraction process, the weighted feature method is proposed based on the correlation between muscles and actions. Second, to solve the problem of the genetic algorithm selection operator easily falling into a local optimum solution, the improved genetic algorithm-support vector machine is designed by championship with sorting method. Finally, the proposed method is used to recognize six types of lower limb actions designed, and the average recognition rate reaches 94.75%. Experimental results indicate that the proposed method has definite potentiality in lower limb action recognition.

Speed controller-based fuzzy logic for a biosignal-feedbacked cycloergometer

Nowadays, fuzzy-logic systems are implemented to control machinery or processes that previously required human manipulation. The main objective of this research is to propose a controller based on fuzzy-logic that uses bio-signals for decision making. The study presents the implementation of a fuzzy-speed controller for a therapeutic machine called cycloergometer. It is used in patients who require rehabilitation therapy to improve their mobility in the lower body or to increase their relaxation or flexibility. Basic controllers have been developed where the speed is decided through a user interface, and the therapist must constantly increase or decrease the speed according to the condition of the patient. In this paper, the speed of the therapy equipment is adjusted using the heart rate of the patient. In this way, a bio-signal is used to determine whether a person is tired or relaxed. Therefore, a mechanism is obtained that is not subject to the visual criteria of the therapist. A detailed review of the literature illustrates that one of the main limitations of electroencephalography and electromyography recordings is the low signal-to-noise ratio and the fact that the signals captured at the electrodes are a mixture of sources that cannot be observed directly with noninvasive methods. Therefore, it was decided to work with electrocardiogram-based signals for better robustness of the proposed system. The controller output is a voltage signal in PWM, which is determined by the membership and error functions. The behavior of the implemented controller is validated by different experimental tests based on the increase and decrease of the simulated and real heart rate of a patient. Finally, the results obtained and the possible areas of opportunity for the proposed design are discussed.

A Home-Based Bilateral Rehabilitation System With sEMG-based Real-Time Variable Stiffness

Bilateral rehabilitation allows patients with hemiparesis to exploit the cooperative capabilities of both arms to promote the recovery process. Although various approaches have been proposed to facilitate synchronized robot-assisted bilateral movements, few studies have focused on addressing the varying joint stiffness resulting from dynamic motions. This paper presents a novel bilateral rehabilitation system that implements a surface electromyography (sEMG)-based stiffness control to achieve real-time stiffness adjustment based on the user's dynamic motion. An sEMG-driven musculoskeletal model that incorporates the muscle activation and muscular contraction dynamics is developed to provide reference signals for the robot's real-time stiffness control. Preliminary experiments were conducted to evaluate the system performance in tracking accuracy and comfortability, which showed the proposed rehabilitation system with sEMG-based real-time stiffness variation achieved fast adaption to the patient's dynamic movement as well as improving the comfort in robot-assisted bilateral training.

Fast Wearable Sensor-Based Foot-Ground Contact Phase Classification Using a Convolutional Neural Network with Sliding-Window Label Overlapping

Classification of foot–ground contact phases, as well as the swing phase is essential in biomechanics domains where lower-limb motion analysis is required; this analysis is used for lower-limb rehabilitation, walking gait analysis and improvement, and exoskeleton motion capture. In this study, sliding-window label overlapping of time-series wearable motion data in training dataset acquisition is proposed to accurately detect foot–ground contact phases, which are composed of 3 sub-phases as well as the swing phase, at a frequency of 100 Hz with a convolutional neural network (CNN) architecture. We not only succeeded in developing a real-time CNN model for learning and obtaining a test accuracy of 99.8% or higher, but also confirmed that its validation accuracy was close to 85%.

Real-Time Hand Gesture Recognition Using Surface Electromyography and Machine Learning: A Systematic Literature Review

Today, daily life is composed of many computing systems, therefore interacting with them in a natural way makes the communication process more comfortable. Human-Computer Interaction (HCI) has been developed to overcome the communication barriers between humans and computers. One form of HCI is Hand Gesture Recognition (HGR), which predicts the class and the instant of execution of a given movement of the hand. One possible input for these models is surface electromyography (EMG), which records the electrical activity of skeletal muscles. EMG signals contain information about the intention of movement generated by the human brain. This systematic literature review analyses the state-of-the-art of real-time hand gesture recognition models using EMG data and machine learning. We selected and assessed 65 primary studies following the Kitchenham methodology. Based on a common structure of machine learning-based systems, we analyzed the structure of the proposed models and standardized concepts in regard to the types of models, data acquisition, segmentation, preprocessing, feature extraction, classification, postprocessing, real-time processing, types of gestures, and evaluation metrics. Finally, we also identified trends and gaps that could open new directions of work for future research in the area of gesture recognition using EMG.

Estimation of Knee Movement from Surface EMG Using Random Forest with Principal Component Analysis

To study the relationship between surface electromyography (sEMG) and joint movement, and to provide reliable reference information for the exoskeleton control, the sEMG and the corresponding movement of the knee during the normal walking of adults have been measured. After processing the experimental data, the estimation model for knee movement from sEMG was established using the novel method of random forest with principal component analysis (RFPCA). The influence of the sample size and the previous sEMG data on the prediction efficiency was analyzed. The estimation model was not sensitive to the sample size when samples increased to a certain value, and the results of different previous sEMG showed that the prediction accuracy of the estimation models did not always improve with the increasing features of input. By comparing the estimation model of back propagation neural network with principal component analysis (BPPCA), it was found that RFPCA was suitable for all participants in the experiment with less execution time, and the root mean square error was around 5° which was lower than BPPCA with errors varying from 7° to 25°. Therefore, it was concluded that the RFPCA method for the estimation of knee movement from sEMG is feasible and could be used for motion analysis and the control of exoskeleton.

A Deep Learning Approach to EMG-Based Classification of Gait Phases during Level Ground Walking

Correctly identifying gait phases is a prerequisite to achieve a spatial/temporal characterization of muscular recruitment during walking. Recent approaches have addressed this issue by applying machine learning techniques to treadmill-walking data. We propose a deep learning approach for surface electromyographic (sEMG)-based classification of stance/swing phases and prediction of the foot–floor-contact signal in more natural walking conditions (similar to everyday walking ones), overcoming constraints of a controlled environment, such as treadmill walking. To this aim, sEMG signals were acquired from eight lower-limb muscles in about 10.000 strides from 23 healthy adults during level ground walking, following an eight-shaped path including natural deceleration, reversing, curve, and acceleration. By means of an extensive evaluation, we show that using a multi layer perceptron to learn hidden features provides state of the art performances while avoiding features engineering. Results, indeed, showed an average classification accuracy of 94.9 for learned subjects and 93.4 for unlearned ones, while mean absolute difference ( ± S D ) between phase transitions timing predictions and footswitch data was 21.6 ms and 38.1 ms for heel-strike and toe off, respectively. The suitable performance achieved by the proposed method suggests that it could be successfully used to automatically classify gait phases and predict foot–floor-contact signal from sEMG signals during level ground walking.

Development of an EMG-Based Muscle Health Model for Elbow Trauma Patients

Wearable robotic braces have the potential to improve rehabilitative therapies for patients suffering from musculoskeletal (MSK) conditions. Ideally, a quantitative assessment of health would be incorporated into rehabilitative devices to monitor patient recovery. The purpose of this work is to develop a model to distinguish between the healthy and injured arms of elbow trauma patients based on electromyography (EMG) data. Surface EMG recordings were collected from the healthy and injured limbs of 30 elbow trauma patients while performing 10 upper-limb motions. Forty-two features and five feature sets were extracted from the data. Feature selection was performed to improve the class separation and to reduce the computational complexity of the feature sets. The following classifiers were tested: linear discriminant analysis (LDA), support vector machine (SVM), and random forest (RF). The classifiers were used to distinguish between two levels of health: healthy and injured (50% baseline accuracy rate). Maximum fractal length (MFL), myopulse percentage rate (MYOP), power spectrum ratio (PSR) and spike shape analysis features were identified as the best features for classifying elbow muscle health. A majority vote of the LDA classification models provided a cross-validation accuracy of 82.1%. The work described in this paper indicates that it is possible to discern between healthy and injured limbs of patients with MSK elbow injuries. Further assessment and optimization could improve the consistency and accuracy of the classification models. This work is the first of its kind to identify EMG metrics for muscle health assessment by wearable rehabilitative devices.

sEMG-Based Hand-Gesture Classification Using a Generative Flow Model

Conventional pattern-recognition algorithms for surface electromyography (sEMG)-based hand-gesture classification have difficulties in capturing the complexity and variability of sEMG. The deep structures of deep learning enable the method to learn high-level features of data to improve both accuracy and robustness of a classification. However, the features learned through deep learning are incomprehensible, and this issue has precluded the use of deep learning in clinical applications where model comprehension is required. In this paper, a generative flow model (GFM), which is a recent flourishing branch of deep learning, is used with a SoftMax classifier for hand-gesture classification. The proposed approach achieves 63.86±5.12% accuracy in classifying 53 different hand gestures from the NinaPro database 5. The distribution of all 53 hand gestures is modelled by the GFM, and each dimension of the feature learned by the GFM is comprehensible using the reverse flow of the GFM. Moreover, the feature appears to be related to muscle synergy to some extent.