[Research Progress in Data Acquisition and Intelligent Sensing Methods for Lumbar Electromyographic Signals].

Population aging trend is taking place in our country, and low back pain is a symptom of neuromuscular diseases of concern in the elderly. Accurately analyzing the disease of low back pain is important for both timely intervention and rehabilitation of patients. As a kind of bioelectrical signal, the acquisition and analysis of lumbar electromyography (EMG) signal is an important direction for the study of low back pain. The study reviews the acquisition of lumbar EMG by different types of sensors, introduces the signal characteristics of needle electrodes, surface electromyography electrodes and array electrodes, describes the use of signal algorithms, points out that wireless sensors and the use of deep learning algorithms are the direction of development, and puts forward prospects for its further development.

Multi-layer CNN-LSTM network with self-attention mechanism for robust estimation of nonlinear uncertain systems.

Introduction: With the help of robot technology, intelligent rehabilitation of patients with lower limb motor dysfunction caused by stroke can be realized. A key factor constraining the clinical application of rehabilitation robots is how to realize pattern recognition of human movement intentions by using the surface electromyography (sEMG) sensors to ensure unhindered human-robot interaction. Methods: A multilayer CNN-LSTM prediction network incorporating the self-attention mechanism (SAM) is proposed, in this paper, which can extract and learn the periodic and trend characteristics of the sEMG signals, and realize the accurate autoregressive prediction of the human motion information. Firstly, the multilayer CNN-LSTM network utilizes the CNN layer for initial feature extraction of data, and the LSTM network is used to improve the enhancement of the historical time-series features. Then, the SAM is used to improve the global feature extraction performance and parallel computation speed of the network. Results: In comparison with existing test is carried out using actual data from five healthy subjects as well as a clinical hemiplegic patient to verify the superiority and practicality of the proposed algorithm. The results show that most of the model's prediction R > 0.9 for different motion states of healthy subjects; in the experiments oriented to the motion characteristics of patient subjects, the angle prediction results of R > 0.99 for the untrained data on the affected side, which proves that our proposed model also has a better effect on the angle prediction of the affected side. Discussion: The main contribution of this paper is to realize continuous motion estimation of ankle joint for healthy and hemiplegic individuals under non-ideal conditions (weak sEMG signals, muscle fatigue, high muscle tension, etc.), which improves the pattern recognition accuracy and robustness of the sEMG sensor-based system.

Assessment of Patient Treatment and Rehabilitation Processes Using Electromyography Signals and Selected Industry 4.0 Solutions.

Funding treatment and rehabilitation processes for patients with musculoskeletal conditions is an important part of public health insurance in European Union countries. By 2030, these processes will be planned in national health strategies (sequential process activities will be identified, care packages will be defined, service standards will be described, roles in the implementation of activities will be distinguished). Today, in many countries of the world (including the EU countries), these processes tend not to be very effective and to be expensive for both patients and insurance companies. This article aims to raise awareness of the need for process re-engineering and describes possible tools for assessing patient treatment and rehabilitation processes (using electromyographic signals-EMG and selected Industry 4.0 solutions). This article presents the research methodology prepared for the purpose of process evaluation. The use of this methodology will confirm the hypothesis that the use of EMG signals and selected Industry 4.0 solutions will improve the effectiveness and efficiency of treatment and rehabilitation processes for patients with musculoskeletal injuries.

Local muscle load and fatigue of simulated high-voltage cable climbing task of operation inspection personnel by surface electromyography / 环境与职业医学

Background Climbing pylons during high-voltage cable maintenance is not only a labor-intensive task, but also a challenge bringing about heat stress and mental pressure from working at height, which may lead to accumulation of muscle fatigue and work-related musculoskeletal disorders. Objective To record the local muscle fatigue during a simulated climbing task by high-voltage cable electricians based on surface electromyography (sEMG) signals, explore the characteristic changes in sEMG signals and their relationship with subjective fatigue evaluation of the task, and provide data support for developing task specific objective assessment tools for local muscle fatigue and prevention of work-related musculoskeletal disorders. Methods Ten male college students were recruited to conduct a test of a simulated pylon climbing task. The climbing distance was 60 m, and a task segment was set for every 20 m (about 100 s), recorded as T1, T2, and T3, respectively. After completing each task segment, the subjects were required to rate their subjective fatigue using the Borg's RPE Scale. Fatigue was defined by rating of perceived exertion (RPE) score ≥ 14 in this study. The sEMG signals of trapezius, erector spinae, rectus femoris, and gastrocnemius muscles were recorded wirelessly. The standardized maximal voluntary electrical activation (MVE) obtained by standardizing the root mean square (RMS) of the time domain index and the median frequency (MF) of the frequency domain index were estimated for the recorded sEMG signals, and joint amplitude and spectrum analysis (JASA) was used to evaluate local muscle fatigue of target muscles involving in the climbing task. Results The RPE scores of T1, T2, and T3 were 11.9, 15.3, and 17.4, respectively. Subjective fatigue was found in T2 and T3 but not in T1. With the extension of climbing time, the MVE values of left and right erector spinae muscles, left and right rectus femoris, and right gastrocnemius muscle increased gradually, while the MVE values of left and right trapezius muscles and left gastrocnemius muscle increased first and then decreased. The MF values of left and right rectus femoris increased at first, then remained unchanged, while the MF values of the other muscles remained basically unchanged. In T1, three muscles, including left trapezius muscle and both side of erector spinae muscles, showed fatigue; in T2, five muscles, including both sides of erector spina muscles, right trapezius muscle, and both sides of gastrocnemius muscle appeared fatigue; in T3 , except for left rectus femoris, the other seven muscles were fatigue. Conclusion The characteristic changes of electromyography signals in the simulated climbing task are not completely consistent with the typical amplitude increase and left shift of the frequency spectrum of sEMG signals in static tasks, indicating that the application of time-domain and frequency-domain analysis methods in the evaluation of muscle fatigue in climbing tasks needs further discussion. Trapezius muscles and erector spinae muscles are the first to show fatigue in the simulation, and may be the sensitive muscle groups of muscle fatigue associated with climbing movement. Compared with subjective evaluation, surface electromyography is more sensitive in the assessment of body fatigue. Fatigue is reported about 100 s of climbing (the climbing length is about 20 m).

Human lower limb activity recognition techniques, databases, challenges and its applications using sEMG signal: an overview.

Human lower limb activity recognition (HLLAR) has grown in popularity over the last decade mainly because to its applications in the identification and control of neuromuscular disorders, security, robotics, and prosthetics. Surface electromyography (sEMG) sensors provide various advantages over other wearable or visual sensors for HLLAR applications, including quick response, pervasiveness, no medical monitoring, and negligible infection. Recognizing lower limb activity from sEMG signals is also challenging owing to the noise in the sEMG signal. Pre- processing of sEMG signals is extremely desirable before the classification because they allow a more consistent and precise evaluation in the above applications. This article provides a segment-by-segment overview of: (1) Techniques for eliminating artifacts from sEMG signals from the lower limb. (2) A survey of existing datasets of lower limb sEMG. (3) A concise description of the various techniques for processing and classifying sEMG data for various applications involving lower limb activity. Finally, an open discussion is presented, which may result in the identification of a variety of future research possibilities for human lower limb activity recognition. Therefore, it is possible to anticipate that the framework presented in this study can aid in the advancement of sEMG-based recognition of human lower limb activity.

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.

Analysis of the quadratus lumborum muscle activity on leg length discrepancy: A randomized controlled trial.

BACKGROUND: Quadratus lumborum (QL) discrete region extensions might change depending on whether leg length discrepancy (LLD) individually has any extra erector spinae action in the lumbar spine, which can result in serious injury to the lower extremities and lumbar vertebrae. OBJECTIVE: This study aims to investigate the effect of QL muscle activity on LLD by using electromyography (EMG) signals. METHODS: The study employed a randomized controlled design. A total of 100 right-handed volunteers were included in this study. All participants were assessed manually by tape measurement for LLD. EMG signals were recorded during the resting and maximal isometric contraction positions to determine QL muscle activity. The power spectral density (PSD) methods were applied to compute EMG signals. RESULTS: In maximal isometric contraction position, comparing the short right LLD (Right side = 0.00064 ± 0.00001, Left side = 0.00033 ± 0.0006) and short left LLD (Right side = 0.00001 ± 0.00008, Left side = 0.00017 ± 0.0001), it was found that the short right LLD group had significantly increased PSD of EMG values. In resting position, the short right LLD (Right side = 0.0002 ± 0.0073, Left side = 0.00016 ± 0.0065) had significantly increased PSD of EMG compared to the short left LLD (Right side = 0.00004 ± 0.0003, Left side = 0.0001 ± 0.0008) values of the QL muscle activity. The results of both groups were also statistically significant (p< 0.05). CONCLUSIONS: The present study showed that it is possible to determine effective experimental interventions for functional LLD using EMG signal analysis of QL muscle activity on an asymptomatic normal population.

An Improvement of Robot Stiffness-Adaptive Skill Primitive Generalization Using the Surface Electromyography in Human-Robot Collaboration.

Learning from Demonstration in robotics has proved its efficiency in robot skill learning. The generalization goals of most skill expression models in real scenarios are specified by humans or associated with other perceptual data. Our proposed framework using the Probabilistic Movement Primitives (ProMPs) modeling to resolve the shortcomings of the previous research works; the coupling between stiffness and motion is inherently established in a single model. Such a framework can request a small amount of incomplete observation data to infer the entire skill primitive. It can be used as an intuitive generalization command sending tool to achieve collaboration between humans and robots with human-like stiffness modulation strategies on either side. Experiments (human-robot hand-over, object matching, pick-and-place) were conducted to prove the effectiveness of the work. Myo armband and Leap motion camera are used as surface electromyography (sEMG) signal and motion capture sensors respective in the experiments. Also, the experiments show that the proposed framework strengthened the ability to distinguish actions with similar movements under observation noise by introducing the sEMG signal into the ProMP model. The usage of the mixture model brings possibilities in achieving automation of multiple collaborative tasks.

[Intermuscular coupling based on wavelet packet-cross frequency coherence].

Human motion control system has a high degree of nonlinear characteristics. Through quantitative evaluation of the nonlinear coupling strength between surface electromyogram (sEMG) signals, we can get the functional state of the muscles related to the movement, and then explore the mechanism of human motion control. In this paper, wavelet packet decomposition and n: m coherence analysis are combined to construct an intermuscular cross-frequency coupling analysis model based on wavelet packet- n: m coherence. In the elbow flexion and extension state with 30% maximum voluntary contraction force (MVC), sEMG signals of 20 healthy adults were collected. Firstly, the subband components were obtained based on wavelet packet decomposition, and then the n: m coherence of subband signals was calculated to analyze the coupling characteristics between muscles. The results show that the linear coupling strength (frequency ratio 1:1) of the cooperative and antagonistic pairs is higher than that of the nonlinear coupling (frequency ratio 1:2, 2:1 and 1:3, 3:1) under the elbow flexion motion of 30% MVC; the coupling strength decreases with the increase of frequency ratio for the intermuscular nonlinear coupling, and there is no significant difference between the frequency ratio n: m and m: n. The intermuscular coupling in beta and gamma bands is mainly reflected in the linear coupling (1:1), nonlinear coupling of low frequency ratio (1:2, 2:1) between synergetic pair and the linear coupling between antagonistic pairs. The results show that the wavelet packet- n: m coherence method can qualitatively describe the nonlinear coupling strength between muscles, which provides a theoretical reference for further revealing the mechanism of human motion control and the rehabilitation evaluation of patients with motor dysfunction.

Intermuscular coupling based on wavelet packet-cross frequency coherence / 生物医学工程学杂志

Human motion control system has a high degree of nonlinear characteristics. Through quantitative evaluation of the nonlinear coupling strength between surface electromyogram (sEMG) signals, we can get the functional state of the muscles related to the movement, and then explore the mechanism of human motion control. In this paper, wavelet packet decomposition and : coherence analysis are combined to construct an intermuscular cross-frequency coupling analysis model based on wavelet packet- : coherence. In the elbow flexion and extension state with 30% maximum voluntary contraction force (MVC), sEMG signals of 20 healthy adults were collected. Firstly, the subband components were obtained based on wavelet packet decomposition, and then the : coherence of subband signals was calculated to analyze the coupling characteristics between muscles. The results show that the linear coupling strength (frequency ratio 1:1) of the cooperative and antagonistic pairs is higher than that of the nonlinear coupling (frequency ratio 1:2, 2:1 and 1:3, 3:1) under the elbow flexion motion of 30% MVC; the coupling strength decreases with the increase of frequency ratio for the intermuscular nonlinear coupling, and there is no significant difference between the frequency ratio : and : . The intermuscular coupling in beta and gamma bands is mainly reflected in the linear coupling (1:1), nonlinear coupling of low frequency ratio (1:2, 2:1) between synergetic pair and the linear coupling between antagonistic pairs. The results show that the wavelet packet- : coherence method can qualitatively describe the nonlinear coupling strength between muscles, which provides a theoretical reference for further revealing the mechanism of human motion control and the rehabilitation evaluation of patients with motor dysfunction.

Driver drowsiness detection based on classification of surface electromyography features in a driving simulator.

Driver drowsiness is a significant cause of fatal crashes every year in the world. In this research, driver's drowsiness is detected by classifying surface electromyography signal features. The tests are conducted on 13 healthy subjects in a driving simulator with a monotonous route. The surface electromyography signal from the upper arm and shoulder muscles are measured including mid deltoid, clavicular portion of the pectoralis major, and triceps and biceps long heads. Signals are separated into 30-s epochs. Five features including range, variance, relative spectral power, kurtosis, and shape factor are extracted. The Observer Rating of Drowsiness evaluates the level of drowsiness. A binormal function is fitted for each feature. For classification, six classifiers are applied. The results show that the k-nearest neighbor classifier predicts drowsiness by 90% accuracy, 82% precision, 77% sensitivity, and 92% specificity.

The Use of Wearable Sensors for the Movement Assessment on Muscle Contraction Sequences in Post-Stroke Patients during Sit-to-Stand.

Electromyography (EMG) sensors have been used to study the sequence of muscle contractions during sit-to-stand (STS) in post-stroke patients. However, the majority of the studies used wired sensors with a limited number of placements. Using the latest improved wearable technology with 16 sensors, the current study was a thorough investigation to evaluate the contraction sequences of eight key muscles on the trunk and bilateral limbs during STS in post-stroke patients, as it became feasible. Multiple wearable sensors for the detection of muscle contraction sequences showed that the post-stroke patients performed STS with abnormal firing sequences, not only in the primary mover on the sagittal plane during raising, but also in the tibialis anterior, which may affect anticipatory postural adjustment in the gluteus medius, which may affect balance control. The abnormal tibialis anterior contraction until the early ascending phase and the delayed firing of the gluteus muscles highlight the importance of whole-kinetic-chain monitoring of contraction sequences using wearable sensors. The findings can be helpful for the design of therapeutic exercises.

[Effect of Dry Needling Stimulation of Myofascial Trigger Point on Sample Entropy of Electromyography of Gastrocnemius Injured Site in Rats].

OBJECTIVE: To attempt to establish an objective quantitative indicator to characterize the trigger point activity, so as to evaluate the effect of dry needling on myofascial trigger point activity. METHODS: Twenty-four male Sprague-Dawley rats were randomly divided into blank control group, dry needling (needling) group, stretching exercise (stretching) group and needling plus stretching group (n＝6 per group). The chronic myofascial pain (trigger point) model was established by freedom vertical fall of a wooden striking device onto the mid-point of gastrocnemius belly of the left hind-limb to induce contusion, followed by forcing the rat to make a continuous downgrade running exercise at a speed of 16 m/min for 90 min on the next day which was conducted once a week for 8 weeks. Electromyography (EMG) of the regional myofascial injured point was monitored and recorded using an EMG recorder via electrodes. It was considered success of the model if spontaneous electrical activities appeared in the injured site. After a 4 weeks' recovery, rats of the needling group were treated by filiform needle stimulation (lifting-thrusting-rotating) of the central part of the injured gastrocnemius belly (about 10 mm deep) for 6 min, and those of the stretching group treated by holding the rat's limb to make the hip and knee joints to an angle of about 180°, and the ankle-joint about 90° for 1 min every time, 3 times altogether (with an interval of 1 min between every 2 times). The activity of the trigger point was estimated by the sample entropy of the EMG signal sequence in reference to Richman's and Moorman's methods to estimate the curative effect of both needling and exercise. RESULTS: After the modeling cycle, the mean sample entropies of EMG signals was significantly decreased in the model groups (needling group [0.034±0.010], stretching group [0.045±0.023], needling plus stretching group [0.047±0.034]) relevant to the blank control group (0.985±0.196, P<0.01). After the treatment, the mean sample entropy of EMG signals was evidently increased in both needling (0.819±0.088), stretching (0.532±0.25) and needling plus stretching (0.810±0.117) groups (P<0.01). The mean sample entropy of the needling and needling plus stretching groups were significantly higher than that of the stretching group (P<0.01), without remarkable difference between the two needling groups in the mean sample entropy (P>0.05), suggesting a better efficacy of dry needling in easing trigger point activity. CONCLUSION: Dry needling is able to relieve myofascial trigger point activity in rats, which is better than that of simple passive stretching therapy.

Effect of Dry Needling Stimulation of Myofascial Trigger Point on Sample Entropy of Electromyography of Gastrocnemius Injured Site in Rats / 针刺研究

OBJECTIVE: To attempt to establish an objective quantitative indicator to characterize the trigger point activity, so as to evaluate the effect of dry needling on myofascial trigger point activity. METHODS: Twenty-four male Sprague-Dawley rats were randomly divided into blank control group, dry needling (needling) group, stretching exercise (stretching) group and needling plus stretching group (n＝6 per group). The chronic myofascial pain (trigger point) model was established by freedom vertical fall of a wooden striking device onto the mid-point of gastrocnemius belly of the left hind-limb to induce contusion, followed by forcing the rat to make a continuous downgrade running exercise at a speed of 16 m/min for 90 min on the next day which was conducted once a week for 8 weeks. Electromyography (EMG) of the regional myofascial injured point was monitored and recorded using an EMG recorder via electrodes. It was considered success of the model if spontaneous electrical activities appeared in the injured site. After a 4 weeks' recovery, rats of the needling group were treated by filiform needle stimulation (lifting-thrusting-rotating) of the central part of the injured gastrocnemius belly (about 10 mm deep) for 6 min, and those of the stretching group treated by holding the rat's limb to make the hip and knee joints to an angle of about 180°, and the ankle-joint about 90° for 1 min every time, 3 times altogether (with an interval of 1 min between every 2 times). The activity of the trigger point was estimated by the sample entropy of the EMG signal sequence in reference to Richman's and Moorman's methods to estimate the curative effect of both needling and exercise. RESULTS: After the modeling cycle, the mean sample entropies of EMG signals was significantly decreased in the model groups (needling group [0.034±0.010], stretching group [0.045±0.023], needling plus stretching group [0.047±0.034]) relevant to the blank control group (0.985±0.196, P0.05), suggesting a better efficacy of dry needling in easing trigger point activity. CONCLUSION: Dry needling is able to relieve myofascial trigger point activity in rats, which is better than that of simple passive stretching therapy.

Reflex-mediated dynamic neuromuscular stabilization in stroke patients: EMG processing and ultrasound imaging.

BACKGROUND: Postural core instability is associated with poor dynamic balance and a high risk of serious falls. Both neurodevelopmental treatment (NDT) and dynamic neuromuscular stabilization (DNS) core stabilization exercises have been used to improve core stability, but the outcomes of these treatments remain unclear. OBJECTIVE: This study was undertaken to examine the therapeutic effects of NDT and DNS core stabilization exercises on muscular activity, core stability, and core muscle thickness. METHODS: Ten participants (5 healthy adults; 5 hemiparetic stroke patients) were recruited. Surface electromyography (EMG) was used to determine core muscle activity of the transversus abdominis/internal oblique (TrA/IO), external oblique (EO), and rectus abdominis (RA) muscles. Ultrasound imaging was used to measure transversus abdominals/internal oblique (TrA/IO) thickness, and a pressure biofeedback unit (PBU) was used to measure core stability during the DNS and NDT core exercise conditions. Data are reported as median and range and were compared using nonparametric Mann - Whitney U test and Wilcoxon signed rank test at p< 0.05. RESULTS: Both healthy and hemiparetic stroke groups showed greater median EMG amplitude in the TrA/IO muscles, core stability, and muscle thickness values during the DNS exercise condition than during the NDT core exercise condition, respectively (p< 0.05). However, the relative changes in the EMG amplitude, core stability, and muscle thickness values were greater during the DNS exercise condition than during the NDT core exercise condition in the hemiparetic stroke patient group (p< 0.05). CONCLUSIONS: Our novel results provide the first clinical evidence that DNS is more effective than NDT in both healthy and hemiparetic stroke subjects to provide superior deep core muscle activation, core stabilization, and muscle thickness. Moreover, such advantageous therapeutic benefits of the DNS core stabilization exercise over the NDT exercise were more apparent in the hemiparetis stroke patients than normal controls.

Design and fuzzy logic control of an active wrist orthosis.

People who perform excessive wrist movements throughout the day because of their professions have a higher risk of developing lateral and medial epicondylitis. If proper precautions are not taken against these diseases, serious consequences such as job loss and early retirement can occur. In this study, the design and control of an active wrist orthosis that is mobile, powerful and lightweight is presented as a means to avoid the occurrence and/or for the treatment of repetitive strain injuries in an effective manner. The device has an electromyography-based control strategy so that the user's intention always comes first. In fact, the device-user interaction is mainly activated by the electromyography signals measured from the forearm muscles that are responsible for the extension and flexion wrist movements. Contractions of the muscles are detected using surface electromyography sensors, and the desired quantity of the velocity value of the wrist is extracted from a fuzzy logic controller. Then, the actuator system of the device comes into play by conveying the necessary motion support to the wrist. Experimental studies show that the presented device actually reduces the demand on the muscles involved in repetitive strain injuries while performing challenging daily life activities including extension and flexion wrist motions.

Features extraction and multi-classification of sEMG using a GPU-Accelerated GA/MLP hybrid algorithm.

BACKGROUND: Surface electromyography (sEMG) signal is the combined effect of superficial muscle EMG and neural electrical activity. In recent years, researchers did large amount of human-machine system studies by using the physiological signals as control signals. OBJECTIVE: To develop and test a new multi-classification method to improve performance of analyzing sEMG signals based on public sEMG dataset. METHODS: First, ten features were selected as candidate features. Second, a genetic algorithm (GA) was applied to select representative features from the initial ten candidates. Third, a multi-layer perceptron (MLP) classifier was trained by the selected optimal features. Last, the trained classifier was used to predict the classes of sEMG signals. A special graphics processing unit (GPU) was used to speed up the learning process. RESULTS: Experimental results show that the classification accuracy of the new method reached higher than 90%. Comparing to other previously reported results, using the new method yielded higher performance. CONCLUSIONS: The proposed features selection method is effective and the classification result is accurate. In addition, our method could have practical application value in medical prosthetics and the potential to improve robustness of myoelectric pattern recognition.

A two-dimensional matrix image based feature extraction method for classification of sEMG: A comparative analysis based on SVM, KNN and RBF-NN.

BACKGROUND: The computer mouse is an important human-computer interaction device. But patients with physical finger disability are unable to operate this device. Surface EMG (sEMG) can be monitored by electrodes on the skin surface and is a reflection of the neuromuscular activities. Therefore, we can control limbs auxiliary equipment by utilizing sEMG classification in order to help the physically disabled patients to operate the mouse. OBJECTIVE: To develop a new a method to extract sEMG generated by finger motion and apply novel features to classify sEMG. METHODS: A window-based data acquisition method was presented to extract signal samples from sEMG electordes. Afterwards, a two-dimensional matrix image based feature extraction method, which differs from the classical methods based on time domain or frequency domain, was employed to transform signal samples to feature maps used for classification. In the experiments, sEMG data samples produced by the index and middle fingers at the click of a mouse button were separately acquired. Then, characteristics of the samples were analyzed to generate a feature map for each sample. Finally, the machine learning classification algorithms (SVM, KNN, RBF-NN) were employed to classify these feature maps on a GPU. RESULTS: The study demonstrated that all classifiers can identify and classify sEMG samples effectively. In particular, the accuracy of the SVM classifier reached up to 100%. CONCLUSIONS: The signal separation method is a convenient, efficient and quick method, which can effectively extract the sEMG samples produced by fingers. In addition, unlike the classical methods, the new method enables to extract features by enlarging sample signals' energy appropriately. The classical machine learning classifiers all performed well by using these features.

Preliminary study on touch screen VDT operation musculoskeletal injuries and design implications / 医疗卫生装备

Objective To analyze the musculoskeletal injuries related to touch screen VDT operation and design implications.Methods The effects of touch screen size and angles on touch-screen-VDT-operation-related muscle load and fatigue were explored using thorough experiment and EMG acquisition method,and the independent variables included the size and angle and the dependant variables consisted of the load and fatigue of flexor digitorum superficialis (FDS),extensor digitorum communis (EDC),extensor carpi radialis (ECR) and extensor carpi ulnaris (ECU).Results No significant difference was found with regard to pointing success rate and accuracy at all screen sizes and angles levels.FDS and EDC MVC％ increased with increasing touch screen size at all levels of angles.FDS MVC％ decreased while EDC MVC％ increased with inclining angles at all levels of touch screen sizes.All measured muscles' MF did not decrease with time.Conclusion This study helps to provide basis for the optimization of equipment design,reduce exposure to musculoskeletal injuries risks and implement primary prevention.

DCT domain feature extraction scheme based on motor unit action potential of EMG signal for neuromuscular disease classification.

A feature extraction scheme based on discrete cosine transform (DCT) of electromyography (EMG) signals is proposed for the classification of normal event and a neuromuscular disease, namely the amyotrophic lateral sclerosis. Instead of employing DCT directly on EMG data, it is employed on the motor unit action potentials (MUAPs) extracted from the EMG signal via a template matching-based decomposition technique. Unlike conventional MUAP-based methods, only one MUAP with maximum dynamic range is selected for DCT-based feature extraction. Magnitude and frequency values of a few high-energy DCT coefficients corresponding to the selected MUAP are used as the desired feature which not only reduces computational burden, but also offers better feature quality with high within-class compactness and between-class separation. For the purpose of classification, the K-nearest neighbourhood classifier is employed. Extensive analysis is performed on clinical EMG database and it is found that the proposed method provides a very satisfactory performance in terms of specificity, sensitivity and overall classification accuracy.