Classification of the mechanomyogram signal using a wavelet packet transform and singular value decomposition for multifunction prosthesis control

AI-Enabled Soft Sensing Array for Simultaneous Detection of Muscle Deformation and Mechanomyography for Metaverse Somatosensory Interaction

Motion recognition (MR)-based somatosensory interaction technology, which interprets user movements as input instructions, presents a natural approach for promoting human-computer interaction, a critical element for advancing metaverse applications. Herein, this work introduces a non-intrusive muscle-sensing wearable device, that in conjunction with machine learning, enables motion-control-based somatosensory interaction with metaverse avatars. To facilitate MR, the proposed device simultaneously detects muscle mechanical activities, including dynamic muscle shape changes and vibrational mechanomyogram signals, utilizing a flexible 16-channel pressure sensor array (weighing ≈0.38 g). Leveraging the rich information from multiple channels, a recognition accuracy of ≈96.06% is achieved by classifying ten lower-limb motions executed by ten human subjects. In addition, this work demonstrates the practical application of muscle-sensing-based somatosensory interaction, using the proposed wearable device, for enabling the real-time control of avatars in a virtual space. This study provides an alternative approach to traditional rigid inertial measurement units and electromyography-based methods for achieving accurate human motion capture, which can further broaden the applications of motion-interactive wearable devices for the coming metaverse age.

Targeting Transcutaneous Spinal Cord Stimulation Using a Supervised Machine Learning Approach Based on Mechanomyography

Transcutaneous spinal cord stimulation (tSCS) provides a promising therapy option for individuals with injured spinal cords and multiple sclerosis patients with spasticity and gait deficits. Before the therapy, the examiner determines a suitable electrode position and stimulation current for a controlled application. For that, amplitude characteristics of posterior root muscle (PRM) responses in the electromyography (EMG) of the legs to double pulses are examined. This laborious procedure holds potential for simplification due to time-consuming skin preparation, sensor placement, and required expert knowledge. Here, we investigate mechanomyography (MMG) that employs accelerometers instead of EMGs to assess muscle activity. A supervised machine-learning classification approach was implemented to classify the acceleration data into no activity and muscular/reflex responses, considering the EMG responses as ground truth. The acceleration-based calibration procedure achieved a mean accuracy of up to 87% relative to the classical EMG approach as ground truth on a combined cohort of 11 healthy subjects and 11 patients. Based on this classification, the identified current amplitude for the tSCS therapy was in 85%, comparable to the EMG-based ground truth. In healthy subjects, where both therapy current and position have been identified, 91% of the outcome matched well with the EMG approach. We conclude that MMG has the potential to make the tuning of tSCS feasible in clinical practice and even in home use.

A Novel Mechanomyography (MMG) Sensor Based on Piezo-Resistance Principle and with a Pyramidic Microarray

Flexible piezoresistive sensors built by printing nanoparticles onto soft substrates are crucial for continuous health monitoring and wearable devices. In this study, a mechanomyography (MMG) sensor was developed using a flexible piezoresistive MMG signal sensor based on a pyramidal polydimethylsiloxane (PDMS) microarray sprayed with carbon nanotubes (CNTs). The experiment was conducted, and the results show that the sensitivity of the sensor can reach 0.4 kPa-1 in the measurement range of 0~1.5 kPa, and the correlation reached 96%. This has further implications for the possibility that muscle activation can be converted into mechanical movement. The integrity of the sensor in terms of its MMG signal acquisition was tested based on five subjects who were performing arm bending and arm extending movements. The results of this test were promising.

Analysis of anthropometrics and mechanomyography signals as forearm flexion, pronation and supination torque predictors

This study aimed to analyze anthropometrics and mechanomyography (MMG) signals as forearm flexion, pronation, and supination torque predictors. 25 young, healthy, male participants performed isometric forearm flexion, pronation, and supination tasks from 20 to 100% maximal voluntary isometric contraction (MVIC) while maintaining 90° at the elbow joint. Nine anthropometric measures were recorded, and MMG signals from the biceps brachii (BB), brachialis (BRA), and brachioradialis (BRD) muscles were digitally acquired using triaxial accelerometers. These were then correlated with torque values. Significant positive correlations were found for arm circumference (CA) and MMG root mean square (RMS) values with flexion torque. Flexion torque might be predicted using CA (r = 0.426–0.575), a pseudo for muscle size while MMG_RMS (r = 0.441), an indication of muscle activation.

A Simultaneous Gesture Classification and Force Estimation Strategy Based on Wearable A-Mode Ultrasound and Cascade Model

The existing Human-Machine Interfaces (HMI) based on gesture recognition using surface electromyography (sEMG) have made significant progress. However, the sEMG has inherent limitations as well as the gesture classification and force estimation have not been effectively combined. There are limitations in applications such as prosthetic control and clinical rehabilitation, etc. In this paper, a grasping gesture and force recognition strategy based on wearable A-mode ultrasound and two-stage cascade model is proposed, which can simultaneously estimate the force while classifying the grasping gesture. This paper experiments five grasping gestures and four force levels (5-50%MVC). The results demonstrate that the performance of the proposed model is significantly better than that of the traditional model both in classification and regression (p < 0.001). Additionally, the two-stage cascade regression model (TSCRM) used the Gaussian Process regression model (GPR) with the mean and standard deviation (MSD) feature obtains excellent results, with normalized root-mean-square error (nRMSE) and correlation coefficient (CC) of 0.10490.0374 and 0.94610.0354, respectively. Besides, the latency of the model meets the requirement of real-time recognition (T < 15ms). Therefore, the research outcomes prove the feasibility of the proposed recognition strategy and provide a reference for the field of prosthetic control, etc.

A Systematic Review of Sensor Fusion Methods Using Peripheral Bio-Signals for Human Intention Decoding

Humans learn about the environment by interacting with it. With an increasing use of computer and virtual applications as well as robotic and prosthetic devices, there is a need for intuitive interfaces that allow the user to have an embodied interaction with the devices they are controlling. Muscle-machine interfaces can provide an intuitive solution by decoding human intentions utilizing myoelectric activations. There are several different methods that can be utilized to develop MuMIs, such as electromyography, ultrasonography, mechanomyography, and near-infrared spectroscopy. In this paper, we analyze the advantages and disadvantages of different myography methods by reviewing myography fusion methods. In a systematic review following the PRISMA guidelines, we identify and analyze studies that employ the fusion of different sensors and myography techniques, while also considering interface wearability. We also explore the properties of different fusion techniques in decoding user intentions. The fusion of electromyography, ultrasonography, mechanomyography, and near-infrared spectroscopy as well as other sensing such as inertial measurement units and optical sensing methods has been of continuous interest over the last decade with the main focus decoding the user intention for the upper limb. From the systematic review, it can be concluded that the fusion of two or more myography methods leads to a better performance for the decoding of a user's intention. Furthermore, promising sensor fusion techniques for different applications were also identified based on the existing literature.

Elements Influencing sEMG-Based Gesture Decoding: Muscle Fatigue, Forearm Angle and Acquisition Time

The surface Electromyography (sEMG) signal contains information about movement intention generated by the human brain, and it is the most intuitive and common solution to control robots, orthotics, prosthetics and rehabilitation equipment. In recent years, gesture decoding based on sEMG signals has received a lot of research attention. In this paper, the effects of muscle fatigue, forearm angle and acquisition time on the accuracy of gesture decoding were researched. Taking 11 static gestures as samples, four specific muscles (i.e., superficial flexor digitorum (SFD), flexor carpi ulnaris (FCU), extensor carpi radialis longus (ECRL) and finger extensor (FE)) were selected to sample sEMG signals. Root Mean Square (RMS), Waveform Length (WL), Zero Crossing (ZC) and Slope Sign Change (SSC) were chosen as signal eigenvalues; Linear Discriminant Analysis (LDA) and Probabilistic Neural Network (PNN) were used to construct classification models, and finally, the decoding accuracies of the classification models were obtained under different influencing elements. The experimental results showed that the decoding accuracy of the classification model decreased by an average of 7%, 10%, and 13% considering muscle fatigue, forearm angle and acquisition time, respectively. Furthermore, the acquisition time had the biggest impact on decoding accuracy, with a maximum reduction of nearly 20%.

Biosignal-Based Human-Machine Interfaces for Assistance and Rehabilitation: A Survey

As a definition, Human–Machine Interface (HMI) enables a person to interact with a device. Starting from elementary equipment, the recent development of novel techniques and unobtrusive devices for biosignals monitoring paved the way for a new class of HMIs, which take such biosignals as inputs to control various applications. The current survey aims to review the large literature of the last two decades regarding biosignal-based HMIs for assistance and rehabilitation to outline state-of-the-art and identify emerging technologies and potential future research trends. PubMed and other databases were surveyed by using specific keywords. The found studies were further screened in three levels (title, abstract, full-text), and eventually, 144 journal papers and 37 conference papers were included. Four macrocategories were considered to classify the different biosignals used for HMI control: biopotential, muscle mechanical motion, body motion, and their combinations (hybrid systems). The HMIs were also classified according to their target application by considering six categories: prosthetic control, robotic control, virtual reality control, gesture recognition, communication, and smart environment control. An ever-growing number of publications has been observed over the last years. Most of the studies (about 67%) pertain to the assistive field, while 20% relate to rehabilitation and 13% to assistance and rehabilitation. A moderate increase can be observed in studies focusing on robotic control, prosthetic control, and gesture recognition in the last decade. In contrast, studies on the other targets experienced only a small increase. Biopotentials are no longer the leading control signals, and the use of muscle mechanical motion signals has experienced a considerable rise, especially in prosthetic control. Hybrid technologies are promising, as they could lead to higher performances. However, they also increase HMIs’ complexity, so their usefulness should be carefully evaluated for the specific application.

Quantification of patellar tendon reflex using portable mechanomyography and electromyography devices

Deep tendon reflexes are one of the main components of the clinical nervous system examinations. These assessments are inexpensive and quick. However, evaluation can be subjective and qualitative. This study aimed to objectively evaluate hyperreflexia of the patellar tendon reflex using portable mechanomyography (MMG) and electromyography (EMG) devices. This study included 10 preoperative patients (20 legs) who had a pathology that could cause bilateral patellar tendon hyperreflexia and 12 healthy volunteers (24 legs) with no prior history of neurological disorders. We attached MMG/EMG sensors onto the quadriceps and tapped the patellar tendon with maximal and constant force. Our results showed a significantly high amplitude of the root mean square (RMS) and low frequency of the mean power frequency (MPF) in the rectus femoris, vastus medialis, and vastus lateralis muscles in both EMG and MMG with both maximal and constant force. Especially in the patients with cervical and thoracic myelopathy, the receiver operating characteristic (ROC) curve for diagnosing hyperreflexia of the patellar tendon showed a moderate to very high area under the curve for all EMG–RMS, EMG–MPF, MMG–RMS, and MMG–MPF values. The use of EMG and MMG for objectively quantifying the patellar tendon reflex is simple and desirable for future clinical applications and could help diagnose neurological disorders.

Wearable MMG-Plus-One Armband: Evaluation of Normal Force on Mechanomyography (MMG) to Enhance Human-Machine Interfacing

In this paper, we introduce a new mode of mechanomyography (MMG) signal capture for enhancing the performance of human-machine interfaces (HMIs) through modulation of normal pressure at the sensor location. Utilizing this novel approach, increased MMG signal resolution is enabled by a tunable degree of freedom normal to the sensor-skin contact area. We detail the mechatronic design, experimental validation, and user study of an armband with embedded acoustic sensors demonstrating this capacity. The design is motivated by the nonlinear viscoelasticity of the tissue, which increases with the normal surface pressure. This, in theory, results in higher conductivity of mechanical waves and hypothetically allows to interface with deeper muscle; thus, enhancing the discriminative information context of the signal space. Ten subjects (seven able-bodied and three trans-radial amputees) participated in a study consisting of the classification of hand gestures through MMG while increasing levels of contact force were administered. Four MMG channels were positioned around the forearm and placed over the flexor carpi radialis, brachioradialis, extensor digitorum communis, and flexor carpi ulnaris muscles. A total of 852 spectrotemporal features were extracted (213 features per each channel) and passed through a Neighborhood Component Analysis (NCA) technique to select the most informative neurophysiological subspace of the features for classification. A linear support vector machine (SVM) then classified the intended motion of the user. The results indicate that increasing the normal force level between the MMG sensor and the skin can improve the discriminative power of the classifier, and the corresponding pattern can be user-specific. These results have significant implications enabling embedding MMG sensors in sockets for prosthetic limb control and HMI.

Improved hand prostheses control for transradial amputees based on hybrid of voice recognition and electromyography

The control of prostheses and their complexities is one of the greatest challenges limiting wide amputees' use of upper limb prostheses. The main challenges include the difficulty of extracting signals for controlling the prostheses, limited number of degrees of freedom (DoF), and cost-prohibitive for complex controlling systems. In this study, a real-time hybrid control system, based on electromyography (EMG) and voice commands (VC) is designed to render the prosthesis more dexterous with the ability to accomplish amputee's daily activities proficiently. The voice and EMG systems were combined in three proposed hybrid strategies, each strategy had different number of movements depending on the combination protocol between voice and EMG control systems. Furthermore, the designed control system might serve a large number of amputees with different amputation levels, and since it has a reasonable cost and be easy to use. The performance of the proposed control system, based on hybrid strategies, was tested by intact-limbed and amputee participants for controlling the HANDi hand. The results showed that the proposed hybrid control system was robust, feasible, with an accuracy of 94%, 98%, and 99% for Strategies 1, 2, and 3, respectively. It was possible to specify the grip force applied to the prosthetic hand within three gripping forces. The amputees participated in this study preferred combination Strategy 3 where the voice and EMG are working concurrently, with an accuracy of 99%.

A PILOT STUDY OF MECHANOMYOGRAPHY-BASED HAND MOVEMENTS RECOGNITION EMPHASIZING ON THE INFLUENCE OF FABRICS BETWEEN SENSOR AND SKIN

Multi-channel mechanomyography (MMG) signals were acquired from the forearm when the subjects were performing eight classes of hand movements related to rehabilitation training. Ten time domain (TD) features and wavelet packet node energy (WPNE) features were extracted from each channel of MMG, and the hand movements were classified by support vector machine (SVM), extreme learning machine (ELM), linear discriminant analysis (LDA) and [Formula: see text]-nearest neighborhood (KNN) and the classifying results of three methods of collecting MMG (sensors directly on skin, sensors on cotton fabric and sensors on acrylic fiber) were compared. When all TD features were selected and SVM was adopted as the classifier, the total recognition rates of hand movements were 94.0%, 93.9% and 93.6%, respectively, of three collection methods. Using ELM can obtain similar results as SVM, with the recognition rates of 94.3%, 94.3% and 94.1%, respectively, better than using LDA (88.5%, 88.6% and 88.0%) or KNN (88.9%, 89.4% and 89.0%). For each algorithm, using TD features can acquire the highest recognition rates. Once the feature set and the classifier were selected, the total recognition rates were almost equally among three collection methods (especially for some feature sets, the differences are smaller than 1%). The results confirmed that satisfactory effects could be acquired even when the MMG was collected from sensors on fabrics with specific material, thus indicating that MMG has a unique potential value for developing wearable devices.

A preliminary study of classification of upper limb motions and forces based on mechanomyography

Rehabilitation training is essential for patients who have a history of certain illnesses, such as stroke. As a crucial part of rehabilitation training, upper limb training involves such key factors as upper limb motions and forces. This study investigated three upper limb motions (elbow flexion of 135°, Motion 1; shoulder flexion of 90°, Motion 2; and shoulder abduction of 90°, Motion 3) and various forces (muscle Force 0, no force; holding one 1.4 kg dumbbell, muscle Force 1; holding one 2.4 kg dumbbell, muscle Force 2) in combination to evaluate nine motion patterns. These patterns were completed by twelve healthy volunteers. Mechanomyography (MMG) measurements of the biceps brachii (Channel 1), triceps (Channel 2), and deltoid (Channel 3) muscles were collected. These were subsequently divided into signal segments corresponding to each of the motions using a segmentation method based on average energy. After extracting time-domain features and wavelet packet energy features, support vector machine analysis (SVM) was used for the classification of the upper limb motions and forces based on the MMG measurements. Channel 2 and Channel 3 were shown to play an important role in the classification of upper limb motions, and Channel 1 played a role in the classification of the forces. These results demonstrate that collection of MMG measurements from the three muscles is feasible and suggest a foundation for further studies in which rehabilitation training is evaluated based on MMG measurements.

Pattern recognition of head movement based on mechanomyography and its application

The first part of this study investigated pattern recognition of head movements based on mechanomyography (MMG) signals. Four channel MMG signals were collected from the sternocleidomastoid (SCM) muscles and the splenius capitis (SPL) muscles in the subjects’ neck when they bowed the head, raised the head, side-bent to left, side-bent to right, turned to left and turned to right. The MMG signals were then filtered, normalized and divided using an unequal length segmentation algorithm into a single action frame. After extracting the energy features of the wavelet packet coefficients and the feature of the principal diagonal slices of the bispectrum, the dimension of the energy features were reduced by the Fisher linear discriminant analysis (FLDA). Finally, all the features were classified through the support vector machine (SVM) classifier. The recognition rate was up to 95.92%. On this basis, the second part of this study used the head movements to control a car model for simulating the control of a wheelchair, and the success rate was 85.74%.

Association of anthropometric parameters with amplitude and crosstalk of mechanomyographic signals during forearm flexion, pronation and supination torque tasks

This study aimed to quantify the association of four anthropometric parameters of the human arm, namely, the arm circumference (CA), arm length (LA), skinfold thickness (ST) and inter-sensor distance (ISD), with amplitude (RMS) and crosstalk (CT) of mechanomyography (MMG) signals. Twenty-five young, healthy, male participants were recruited to perform forearm flexion, pronation and supination torque tasks. Three accelerometers were employed to record the MMG signals from the biceps brachii (BB), brachialis (BRA) and brachioradialis (BRD) at 80% maximal voluntary contraction (MVC). Signal RMS was used to quantify the amplitude of the MMG signals from a muscle, and cross-correlation coefficients were used to quantify the magnitude of the CT among muscle pairs (BB & BRA, BRA & BRD, and BB & BRD). For all investigated muscles and pairs, RMS and CT showed negligible to low negative correlations with CA, LA and ISD (r = −0.0001–−0.4611), and negligible to moderate positive correlations with ST (r = 0.004–0.511). However, almost all of these correlations were statistically insignificant (p > 0.05). These findings suggest that RMS and CT values for the elbow flexor muscles recorded and quantified using accelerometers appear invariant to anthropometric parameters.

Electrically evoked wrist extensor muscle fatigue throughout repetitive motion as measured by mechanomyography and near-infrared spectroscopy

Repetitive electrically-evoked muscle contraction leads to accelerated muscle fatigue. This study assessed electrically-evoked fatiguing muscle with changes to mechanomyography root mean square percentage (%RMS-MMG) and tissue saturation index (%TSI) in extensor carpi radialis. Forty healthy volunteers (n=40) performed repetitive electrical-evoked wrist extension to fatigue and results were analyzed pre- and post-fatigue, i.e. 50% power output (%PO) drop. Responses of %PO, %TSI and %RMS-MMG were correlated while the relationships between %RMS-MMG and %TSI were investigated using linear regression. The %TSI for both groups were negatively correlated with declining %PO as the ability of the muscle to take up oxygen became limited due to fatigued muscle. The %RMS-MMG behaved in two different patterns post-fatigue against declining %PO whereby; (i) group A showed positive correlation (%RMS-MMG decreased) throughout the session and (ii) group B demonstrated negative correlation (%RMS-MMG increased) with declining %PO until the end of the session. Regression analysis showed %TSI was inversely proportional to %RMS-MMG during post-fatigue in group A. Small gradients in both groups suggested that %TSI was not sensitive to the changes in %RMS-MMG and they were mutually exclusive. Most correlation and regression changed significantly post-fatigue indicating that after fatigue, the condition of muscle had changed mechanically and physiologically.

Research on GA-SVM Based Head-Motion Classification via Mechanomyography Feature Analysis

This study investigated classification of six types of head motions using mechanomyography (MMG) signals. An unequal segmenting algorithm was adopted to segment the MMG signals generated by head motions. Three types of features (time domain, time-frequency domain and nonlinear dynamics) were extracted to construct five feature sets as candidate datasets for classification analysis. Genetic algorithm optimized support vector machine (GA-SVM) was used to classify the MMG signals. Three different kernel functions, different combinations of feature sets, different number of signal channels and training samples were selected for comparative analysis to evaluate the classification accuracy. Experimental results showed that the classifier had the best overall classification accuracy when using the radial basis function (RBF). Any combination of three different types of feature sets guaranteed an average accuracy of over 80%. In the case of the best combination (feature set 2 + 3 + 5), the classification accuracy was up to 88.2%. Using four channels to acquire MMG signal and no less than 60 training samples can assure a satisfactory classification accuracy.

Segmenting Mechanomyography Measures of Muscle Activity Phases Using Inertial Data

Electromyography (EMG) is the standard technology for monitoring muscle activity in laboratory environments, either using surface electrodes or fine wire electrodes inserted into the muscle. Due to limitations such as cost, complexity, and technical factors, including skin impedance with surface EMG and the invasive nature of fine wire electrodes, EMG is impractical for use outside of a laboratory environment. Mechanomyography (MMG) is an alternative to EMG, which shows promise in pervasive applications. The present study used an exerting squat-based task to induce muscle fatigue. MMG and EMG amplitude and frequency were compared before, during, and after the squatting task. Combining MMG with inertial measurement unit (IMU) data enabled segmentation of muscle activity at specific points: entering, holding, and exiting the squat. Results show MMG measures of muscle activity were similar to EMG in timing, duration, and magnitude during the fatigue task. The size, cost, unobtrusive nature, and usability of the MMG/IMU technology used, paired with the similar results compared to EMG, suggest that such a system could be suitable in uncontrolled natural environments such as within the home.

Hand Gesture Recognition and Finger Angle Estimation via Wrist-Worn Modified Barometric Pressure Sensing

This paper presents a new approach to wearable hand gesture recognition and finger angle estimation based on the modified barometric pressure sensing. Barometric pressure sensors were encased and injected with VytaFlex rubber such that the rubber directly contacted the sensing element allowing pressure change detection when the encasing rubber was pressed. A wearable prototype consisting of an array of ten modified barometric pressure sensors around the wrist was developed and validated with experimental testing for three different hand gesture sets and finger flexion/extension trials for each of the five fingers. The overall hand gesture recognition classification accuracy was 94%. Further analysis revealed that the most important sensor location was the underside of the wrist and that when reducing the sensor number to only five optimally placed sensors, classification accuracy was still 90%. For continuous finger angle estimation, aggregate R² values between actual and predicted angles were thumb: 0.81 ± 0.10, index finger: 0.85±0.06, middle finger: 0.77±0.08, ring finger: 0.77 ± 0.12, and pinkie finger: 0.75 ± 0.10, and the overall average was 0.79 ± 0.05. These results demonstrate that a modified barometric pressure wristband can be used to classify hand gestures and to estimate individual finger joint angles. This approach could serve to improve the clinical treatment for upper extremity deficiencies, such as for stroke rehabilitation, by providing objective patient motor control metrics to inform and aid physicians and therapists throughout the rehabilitation process.

Mechanomyography-based muscle fatigue detection during electrically elicited cycling in patients with spinal cord injury

Patients with spinal cord injury (SCI) benefit from muscle training with functional electrical stimulation (FES). For safety reasons and to optimize training outcome, the fatigue state of the target muscle must be monitored. Detection of muscle fatigue from mel frequency cepstral coefficient (MFCC) feature of mechanomyographic (MMG) signal using support vector machine (SVM) classifier is a promising new approach. Five individuals with SCI performed FES cycling exercises for 30 min. MMG signals were recorded on the quadriceps muscle group (rectus femoris (RF), vastus lateralis (VL), vastus medialis (VM)) and categorized into non-fatigued and fatigued muscle contractions for the first and last 10 min of the cycling session. For each subject, a total of 1800 contraction-related MMG signals were used to train the SVM classifier and another 300 signals were used for testing. The average classification accuracy (4-fold) of non-fatigued and fatigued state was 90.7% using MFCC feature, 74.5% using root mean square (RMS), and 88.8% with combined MFCC and RMS features. Inter-subject prediction accuracy suggested training and testing data to be based on a particular subject or large collection of subjects to improve fatigue prediction capacity. Graphical abstract ᅟ.

A review on crosstalk in myographic signals

PURPOSE

Crosstalk in myographic signals is a major hindrance to the understanding of local information related to individual muscle function. This review aims to analyse the problem of crosstalk in electromyography and mechanomyography.

METHODS

An initial search of the SCOPUS database using an appropriate set of keywords yielded 290 studies, and 59 potential studies were selected after all the records were screened using the eligibility criteria. This review on crosstalk revealed that signal contamination due to crosstalk remains a major challenge in the application of surface myography techniques. Various methods have been employed in previous studies to identify, quantify and reduce crosstalk in surface myographic signals.

RESULTS

Although correlation-based methods for crosstalk quantification are easy to use, there is a possibility that co-contraction could be interpreted as crosstalk. High-definition EMG has emerged as a new technique that has been successfully applied to reduce crosstalk.

CONCLUSIONS

The phenomenon of crosstalk needs to be investigated carefully because it depends on many factors related to muscle task and physiology. This review article not only provides a good summary of the literature on crosstalk in myographic signals but also discusses new directions related to techniques for crosstalk identification, quantification and reduction. The review also provides insights into muscle-related issues that impact crosstalk in myographic signals.

A Piezoresistive Sensor to Measure Muscle Contraction and Mechanomyography

Measurement of muscle contraction is mainly achieved through electromyography (EMG) and is an area of interest for many biomedical applications, including prosthesis control and human machine interface. However, EMG has some drawbacks, and there are also alternative methods for measuring muscle activity, such as by monitoring the mechanical variations that occur during contraction. In this study, a new, simple, non-invasive sensor based on a force-sensitive resistor (FSR) which is able to measure muscle contraction is presented. The sensor, applied on the skin through a rigid dome, senses the mechanical force exerted by the underlying contracting muscles. Although FSR creep causes output drift, it was found that appropriate FSR conditioning reduces the drift by fixing the voltage across the FSR and provides voltage output proportional to force. In addition to the larger contraction signal, the sensor was able to detect the mechanomyogram (MMG), i.e., the little vibrations which occur during muscle contraction. The frequency response of the FSR sensor was found to be large enough to correctly measure the MMG. Simultaneous recordings from flexor carpi ulnaris showed a high correlation (Pearson's r > 0.9) between the FSR output and the EMG linear envelope. Preliminary validation tests on healthy subjects showed the ability of the FSR sensor, used instead of the EMG, to proportionally control a hand prosthesis, achieving comparable performances.

A CNN-SVM combined model for pattern recognition of knee motion using mechanomyography signals

The commonly used classifiers for pattern recognition of human motion, like backpropagation neural network (BPNN) and support vector machine (SVM), usually implement the classification by extracting some hand-crafted features from the human biological signals. These features generally require the domain knowledge for researchers to be designed and take a long time to be tested and selected for high classification performance. In contrast, convolutional neural network (CNN), which has been widely applied to computer vision, can learn to automatically extract features from the training data by means of convolution and subsampling, but CNN training usually requires large sample data and has the overfitting problem. On the other hand, SVM has good generalization ability and can solve the small sample problem. Therefore, we proposed a CNN-SVM combined model to make use of their advantages. In this paper, we detected 4-channel mechanomyography (MMG) signals from the thigh muscles and fed them in the form of time series signals to the CNN-SVM combined model for the pattern recognition of knee motion. Compared with the common classifier performing the classification with hand-crafted features, the CNN-SVM combined model could automatically extract features using CNN, and better improved the generalization ability of CNN and the classification accuracy by means of combining the SVM. This study would provide reference for human motion recognition using other time series signals and further expand the application fields of CNN.

Investigation of the Relationship Between Electrical Stimulation Frequency and Muscle Frequency Response Under Submaximal Contractions

Neuromuscular electrical stimulation (NMES) is a common tool that is used in clinical and laboratory experiments and can be combined with mechanomyography (MMG) for biofeedback in neuroprostheses. However, it is not clear if the electrical current applied to neuromuscular tissues influences the MMG signal in submaximal contractions. The objective of this study is to investigate whether the electrical stimulation frequency influences the mechanomyographic frequency response of the rectus femoris muscle during submaximal contractions. Thirteen male participants performed three maximal voluntary isometric contractions (MVIC) recorded in isometric conditions to determine the maximal force of knee extensors. This was followed by the application of nine modulated NMES frequencies (20, 25, 30, 35, 40, 45, 50, 75, and 100 Hz) to evoke 5% MVIC. Muscle behavior was monitored by the analysis of MMG signals, which were decomposed into frequency bands by using a Cauchy wavelet transform. For each applied electrical stimulus frequency, the mean MMG spectral/frequency response was estimated for each axis (X, Y, and Z axes) of the MMG sensor with the values of the frequency bands used as weights (weighted mean). Only with respect to the Z (perpendicular) axis of the MMG signal, the stimulus frequency of 20 Hz did not exhibit any difference with the weighted mean (P = 0.666). For the frequencies of 20 and 25 Hz, the MMG signal displayed the bands between 12 and 16 Hz in the three axes (P < 0.050). In the frequencies from 30 to 100 Hz, the muscle presented a higher concentration of the MMG signal between the 22 and 29 Hz bands for the X and Z axes, and between 16 and 34 Hz bands for the Y axis (P < 0.050 for all cases). We observed that MMG signals are not dependent on the applied NMES frequency, because their frequency contents tend to mainly remain between the 20- and 25-Hz bands. Hence, NMES does not interfere with the use of MMG in neuroprosthesis.

An Individual Finger Gesture Recognition System Based on Motion-Intent Analysis Using Mechanomyogram Signal

Motion-intent-based finger gesture recognition systems are crucial for many applications such as prosthesis control, sign language recognition, wearable rehabilitation system, and human–computer interaction. In this article, a motion-intent-based finger gesture recognition system is designed to correctly identify the tapping of every finger for the first time. Two auto-event annotation algorithms are firstly applied and evaluated for detecting the finger tapping frame. Based on the truncated signals, the Wavelet packet transform (WPT) coefficients are calculated and compressed as the features, followed by a feature selection method that is able to improve the performance by optimizing the feature set. Finally, three popular classifiers including naive Bayes (NBC), K-nearest neighbor (KNN), and support vector machine (SVM) are applied and evaluated. The recognition accuracy can be achieved up to 94%. The design and the architecture of the system are presented with full system characterization results.

Real-time continuous recognition of knee motion using multi-channel mechanomyography signals detected on clothes

Mechanomyography (MMG) signal has been recently investigated for pattern recognition of human motion. In theory, it is no need of direct skin contact to be detected and unaffected by changes in skin impedance. So, it is hopeful for developing wearable sensing device with clothes. However, there have been no studies so far to detect MMG signal on clothes and verify the feasibility of pattern recognition. For this study, 4-channel MMG signals were detected on clothes from the thigh muscles of 8 able-bodied participants. The support vector machines (SVM) classifier with 4 common features was used to recognize 6 knee motions and the average accuracy of nearly 88% was achieved. The accuracy can be further improved up to 91% by introducing a new proposed feature of the difference of mean absolute value (DMAV), but not by root mean square (RMS) or mean absolute value (MAV). Furthermore, the first-order Markov chain model was combined with the SVM classifier and it can avoid the misclassifications in some cases. For application to wearable power-assisted devices, this study would promote the developments of more flexible, more comfortable, and minimally obtrusive wearable sensing devices with clothes and recognition techniques of human motion intention.

Unilateral fatiguing exercise and its effect on ipsilateral and contralateral resting mechanomyographic mean frequency between aerobic populations

The purpose of this investigation was to establish a better understanding of contralateral training and its effects between homologous muscles following unilateral fatiguing aerobic exercise during variable resting postural positions, and to determine if any observable disparities could be attributed to the differences between the training ages of the participants. Furthermore, we hypothesized that we would observe a contralateral cross-over effect for both groups, with the novice trained group having the higher mechanomyographic mean frequency values in both limbs, across all resting postural positions. Twenty healthy male subjects exercised on an upright cycle ergometer, using only their dominate limb, for 30 min at 60% of their VO2 peak. Resting electromyographic and mechanomyographic signals were measured prior to and following fatiguing aerobic exercise. We found that there were resting mechanomyographic mean frequency differences of approximately 1.9 ± 0.8% and 0.9 ± 0.7%; 9.1 ± 0.3% and 10.2 ± 3.7%; 2 ± 1.8% and 3 ± 1.4%; and 0.9 ± 0.6% and 0.2 ± 1.3% between the novice and advanced trained groups (for the upright sitting position with legs extended 180°; upright sitting position with legs bent 90°; lying supine position with legs extended 180°; and lying supine with legs bent 90°, respectively), from the dominant and nondominant limbs, respectively. We have concluded that despite the relative matching of exercise intensity between groups, acute responses to contralateral training become less accentuated as one progresses in training age. Additionally, our results lend support to the notion that there are multiple, overlapping neural and mechanical mechanisms concurrently contributing to the contralateral cross-over effects observed across the postexercise resting time course.

Features for muscle fatigue computed from electromyogram and mechanomyogram: A new one

Muscle fatigue produces negative effects in the performance and it may lead to a muscle failure. This problem makes the quantitative grading of muscle fatigue a necessity in ergonomic and physiological research. Moreover, the quantitative grading of muscle fatigue is needed to increase work and sport productivity and prevent several accidents that result from muscle fatigue. Even though there are many studies for this aim, there is no quantitative criterion for the evaluation of muscle fatigue. The main reason is that muscle fatigue is a complex physiological situation that is dependent on several parameters. Our aim in this study is to present a new feature to evaluate muscle fatigue and prove the reliability of the new feature by making correlation analyses between this with other features. For this aim, electromyography and mechanomyography signals were simultaneously recorded from the biceps brachii and triceps brachii muscles during the isometric and isotonic contractions of 60 healthy volunteers (30 females, 30 males). The mean power frequency and median frequency, which are used in the literature, were compared to the frequency ratio change, the new measure; correlations between the frequency ratio change and the mean power frequency and median frequency were analysed. There was a high correlation between the features, and frequency ratio change can be used to quantitatively evaluate muscle fatigue.

Estimation of Electrically-Evoked Knee Torque from Mechanomyography Using Support Vector Regression

The difficulty of real-time muscle force or joint torque estimation during neuromuscular electrical stimulation (NMES) in physical therapy and exercise science has motivated recent research interest in torque estimation from other muscle characteristics. This study investigated the accuracy of a computational intelligence technique for estimating NMES-evoked knee extension torque based on the Mechanomyographic signals (MMG) of contracting muscles that were recorded from eight healthy males. Simulation of the knee torque was modelled via Support Vector Regression (SVR) due to its good generalization ability in related fields. Inputs to the proposed model were MMG amplitude characteristics, the level of electrical stimulation or contraction intensity, and knee angle. Gaussian kernel function, as well as its optimal parameters were identified with the best performance measure and were applied as the SVR kernel function to build an effective knee torque estimation model. To train and test the model, the data were partitioned into training (70%) and testing (30%) subsets, respectively. The SVR estimation accuracy, based on the coefficient of determination (R²) between the actual and the estimated torque values was up to 94% and 89% during the training and testing cases, with root mean square errors (RMSE) of 9.48 and 12.95, respectively. The knee torque estimations obtained using SVR modelling agreed well with the experimental data from an isokinetic dynamometer. These findings support the realization of a closed-loop NMES system for functional tasks using MMG as the feedback signal source and an SVR algorithm for joint torque estimation.

Symplectic geometry spectrum regression for prediction of noisy time series

We present the symplectic geometry spectrum regression (SGSR) technique as well as a regularized method based on SGSR for prediction of nonlinear time series. The main tool of analysis is the symplectic geometry spectrum analysis, which decomposes a time series into the sum of a small number of independent and interpretable components. The key to successful regularization is to damp higher order symplectic geometry spectrum components. The effectiveness of SGSR and its superiority over local approximation using ordinary least squares are demonstrated through prediction of two noisy synthetic chaotic time series (Lorenz and Rössler series), and then tested for prediction of three real-world data sets (Mississippi River flow data and electromyographic and mechanomyographic signal recorded from human body).

Mechanomyographic parameter extraction methods: an appraisal for clinical applications

The research conducted in the last three decades has collectively demonstrated that the skeletal muscle performance can be alternatively assessed by mechanomyographic signal (MMG) parameters. Indices of muscle performance, not limited to force, power, work, endurance and the related physiological processes underlying muscle activities during contraction have been evaluated in the light of the signal features. As a non-stationary signal that reflects several distinctive patterns of muscle actions, the illustrations obtained from the literature support the reliability of MMG in the analysis of muscles under voluntary and stimulus evoked contractions. An appraisal of the standard practice including the measurement theories of the methods used to extract parameters of the signal is vital to the application of the signal during experimental and clinical practices, especially in areas where electromyograms are contraindicated or have limited application. As we highlight the underpinning technical guidelines and domains where each method is well-suited, the limitations of the methods are also presented to position the state of the art in MMG parameters extraction, thus providing the theoretical framework for improvement on the current practices to widen the opportunity for new insights and discoveries. Since the signal modality has not been widely deployed due partly to the limited information extractable from the signals when compared with other classical techniques used to assess muscle performance, this survey is particularly relevant to the projected future of MMG applications in the realm of musculoskeletal assessments and in the real time detection of muscle activity.

Symplectic geometry spectrum analysis of nonlinear time series

Various time-series decomposition techniques, including wavelet transform, singular spectrum analysis, empirical mode decomposition and independent component analysis, have been developed for non-linear dynamic system analysis. In this paper, we describe a symplectic geometry spectrum analysis (SGSA) method to decompose a time series into a set of independent additive components. SGSA is performed in four steps: embedding, symplectic QR decomposition, grouping and diagonal averaging. The obtained components can be used for de-noising, prediction, control and synchronization. We demonstrate the effectiveness of SGSA in reconstructing and predicting two noisy benchmark nonlinear dynamic systems: the Lorenz and Mackey-Glass attractors. Examples of prediction of a decadal average sunspot number time series and a mechanomyographic signal recorded from human skeletal muscle further demonstrate the applicability of the SGSA method in real-life applications.

Longitudinal, lateral and transverse axes of forearm muscles influence the crosstalk in the mechanomyographic signals during isometric wrist postures

Problem Statement

In mechanomyography (MMG), crosstalk refers to the contamination of the signal from the muscle of interest by the signal from another muscle or muscle group that is in close proximity.

Purpose

The aim of the present study was two-fold: i) to quantify the level of crosstalk in the mechanomyographic (MMG) signals from the longitudinal (L_o), lateral (L_a) and transverse (T_r) axes of the extensor digitorum (ED), extensor carpi ulnaris (ECU) and flexor carpi ulnaris (FCU) muscles during isometric wrist flexion (WF) and extension (WE), radial (RD) and ulnar (UD) deviations; and ii) to analyze whether the three-directional MMG signals influence the level of crosstalk between the muscle groups during these wrist postures.

Methods

Twenty, healthy right-handed men (mean ± SD: age = 26.7±3.83 y; height = 174.47±6.3 cm; mass = 72.79±14.36 kg) participated in this study. During each wrist posture, the MMG signals propagated through the axes of the muscles were detected using three separate tri-axial accelerometers. The x-axis, y-axis, and z-axis of the sensor were placed in the L_o, L_a, and T_r directions with respect to muscle fibers. The peak cross-correlations were used to quantify the proportion of crosstalk between the different muscle groups.

Results

The average level of crosstalk in the MMG signals generated by the muscle groups ranged from: 34.28–69.69% for the L_o axis, 27.32–52.55% for the L_a axis and 11.38–25.55% for the T_r axis for all participants and their wrist postures. The T_r axes between the muscle groups showed significantly smaller crosstalk values for all wrist postures [F (2, 38) = 14–63, p<0.05, η² = 0.416–0.769].

Significance

The results may be applied in the field of human movement research, especially for the examination of muscle mechanics during various types of the wrist postures.

Mechanomyography and muscle function assessment: a review of current state and prospects

Previous studies have explored to saturation the efficacy of the conventional signal (such as electromyogram) for muscle function assessment and found its clinical impact limited. Increasing demand for reliable muscle function assessment modalities continues to prompt further investigation into other complementary alternatives. Application of mechanomyographic signal to quantify muscle performance has been proposed due to its inherent mechanical nature and ability to assess muscle function non-invasively while preserving muscular neurophysiologic information. Mechanomyogram is gaining accelerated applications in evaluating the properties of muscle under voluntary and evoked muscle contraction with prospects in clinical practices. As a complementary modality and the mechanical counterpart to electromyogram; mechanomyogram has gained significant acceptance in analysis of isometric and dynamic muscle actions. Substantial studies have also documented the effectiveness of mechanomyographic signal to assess muscle performance but none involved comprehensive appraisal of the state of the art applications with highlights on the future prospect and potential integration into the clinical practices. Motivated by the dearth of such critical review, we assessed the literature to investigate its principle of acquisition, current applications, challenges and future directions. Based on our findings, the importance of rigorous scientific and clinical validation of the signal is highlighted. It is also evident that as a robust complement to electromyogram, mechanomyographic signal may possess unprecedented potentials and further investigation will be enlightening.

Novel pseudo-wavelet function for MMG signal extraction during dynamic fatiguing contractions

The purpose of this study was to develop an algorithm to classify muscle fatigue content in sports related scenarios. Mechanomyography (MMG) signals of the biceps muscle were recorded from thirteen subjects performing dynamic contractions until fatigue. For training and testing purposes, the signals were labeled in two classes (Non-Fatigue and Fatigue). A genetic algorithm was used to evolve a pseudo-wavelet function for optimizing the detection of muscle fatigue. Tuning of the generalized evolved pseudo-wavelet function was based on the decomposition of 70% of the conducted MMG trials. After completing 25 independent pseudo-wavelet evolution runs, the best run was selected and then tested on the remaining 30% of the data to measure the classification performance. Results show that the evolved pseudo-wavelet improved the classification rate of muscle fatigue by 4.70 percentage points to 16.61 percentage points when compared to other standard wavelet functions, giving an average correct classification of 80.63%, with statistical significance (p < 0.05).

Torque and mechanomyogram correlations during muscle relaxation: effects of fatigue and time-course of recovery

To assess the validity and reliability of the mechanomyogram (MMG) as a tool to investigate the fatigue-induced changes in the muscle during relaxation, the torque and MMG signals from the gastrocnemius medialis muscle of 23 participants were recorded during tetanic electrically-elicited contractions before and immediately after fatigue, as well as at min 2 and 7 of recovery. The peak torque (pT), contraction time (CT) and relaxation time (RT), and the acceleration of force development (d2RFD) and relaxation (d2RFR) were calculated. The slope and τ of force relaxation were also determined. MMG peak-to-peak was assessed during contraction (MMG p-p) and relaxation (R-MMG p-p). After fatigue, pT, d2RFD, d2RFR, slope, MMG p-p and R-MMG p-p decreased significantly, while CT, RT and τ increased (P < 0.05 for all comparisons), remaining altered throughout the entire recovery period. R-MMG p-p correlated with pT, MMG p-p, slope, τ and d2RFR both before and after fatigue. Reliability measurements always ranged from high to very high. In conclusion, MMG may represent a valid and reliable index to monitor the fatigue-induced changes in muscle mechanical behavior, and could be therefore considered an effective alternative to the force signal, also during relaxation.

A hybrid symplectic principal component analysis and central tendency measure method for detection of determinism in noisy time series with application to mechanomyography

We present a hybrid symplectic geometry and central tendency measure (CTM) method for detection of determinism in noisy time series. CTM is effective for detecting determinism in short time series and has been applied in many areas of nonlinear analysis. However, its performance significantly degrades in the presence of strong noise. In order to circumvent this difficulty, we propose to use symplectic principal component analysis (SPCA), a new chaotic signal de-noising method, as the first step to recover the system dynamics. CTM is then applied to determine whether the time series arises from a stochastic process or has a deterministic component. Results from numerical experiments, ranging from six benchmark deterministic models to 1/f noise, suggest that the hybrid method can significantly improve detection of determinism in noisy time series by about 20 dB when the data are contaminated by Gaussian noise. Furthermore, we apply our algorithm to study the mechanomyographic (MMG) signals arising from contraction of human skeletal muscle. Results obtained from the hybrid symplectic principal component analysis and central tendency measure demonstrate that the skeletal muscle motor unit dynamics can indeed be deterministic, in agreement with previous studies. However, the conventional CTM method was not able to definitely detect the underlying deterministic dynamics. This result on MMG signal analysis is helpful in understanding neuromuscular control mechanisms and developing MMG-based engineering control applications.

Mechanomyogram for muscle function assessment: a review

BACKGROUND

Mechanomyography (MMG) has been extensively applied in clinical and experimental practice to examine muscle characteristics including muscle function (MF), prosthesis and/or switch control, signal processing, physiological exercise, and medical rehabilitation. Despite several existing MMG studies of MF, there has not yet been a review of these. This study aimed to determine the current status on the use of MMG in measuring the conditions of MFs.

METHODOLOGY/PRINCIPAL FINDINGS

Five electronic databases were extensively searched for potentially eligible studies published between 2003 and 2012. Two authors independently assessed selected articles using an MS-Word based form created for this review. Several domains (name of muscle, study type, sensor type, subject's types, muscle contraction, measured parameters, frequency range, hardware and software, signal processing and statistical analysis, results, applications, authors' conclusions and recommendations for future work) were extracted for further analysis. From a total of 2184 citations 119 were selected for full-text evaluation and 36 studies of MFs were identified. The systematic results find sufficient evidence that MMG may be used for assessing muscle fatigue, strength, and balance. This review also provides reason to believe that MMG may be used to examine muscle actions during movements and for monitoring muscle activities under various types of exercise paradigms.

CONCLUSIONS/SIGNIFICANCE

Overall judging from the increasing number of articles in recent years, this review reports sufficient evidence that MMG is increasingly being used in different aspects of MF. Thus, MMG may be applied as a useful tool to examine diverse conditions of muscle activity. However, the existing studies which examined MMG for MFs were confined to a small sample size of healthy population. Therefore, future work is needed to investigate MMG, in examining MFs between a sufficient number of healthy subjects and neuromuscular patients.

Design and evaluation of a novel microphone-based mechanomyography sensor with cylindrical and conical acoustic chambers

Mechanomyography has recently been proposed as a control modality for alternative access technologies for individuals with disabilities. However, MMG recordings are highly susceptible to contamination from limb movements. Pressure-based transducers are touted to be the most robust to external movement although there is some debate about their optimal chamber geometry, in terms of low frequency gain and spectral flatness. To investigate the question of preferred geometry, transducers with cylindrical and conical chambers of varying dimensions were designed, manufactured and tested. Using a computer-controlled electrodynamic shaker, the frequency response of each chamber geometry was empirically derived. Of the cylindrical chambers, the highest gain and the flattest frequency response was exhibited by a chamber 10 mm in diameter and 5-7 mm in height. However, conical chambers offered an average rise in gain of 6.79 ± 1.06 dB/Hz over that achievable with cylindrical geometries. The highest gain and flattest response was achieved with a transducer consisting of a low-frequency MEMS microphone, a 4 μm aluminized mylar membrane and a rigid conical chamber 7 mm in diameter and 5mm in height. This design is recommended for MMG applications where limb movement is prevalent.