Electromyogram Signals Research Articles

Personal Identification Using Long Short-Term Memory with Efficient Features of Electromyogram Biomedical Signals

This study focuses on personal identification using bidirectional long short-term memory (LSTM) with efficient features from electromyogram (EMG) biomedical signals. Personal identification is performed by comparing and analyzing features that can be stably identified and are not significantly affected by noise. For this purpose, 13 efficient features, such as enhanced wavelength, zero crossing, and mean absolute value, were obtained from EMG signals. These features were extracted from segmented signals of a specific length. Then, the bidirectional LSTM was trained on the selected features as sequential data. The features were ranked based on their classification performance. Finally, the most effective features were selected, and the selected features were connected to achieve an improved classification rate. Two public EMG datasets were used to evaluate the proposed model. The first database was acquired from eight-channel Myo bands and was composed of EMG signals from 10 varying motions of 50 individuals. The total numbers of segments for the training and test sets were 30,000 and 20,000, respectively. The second dataset consisted of ten arm motions acquired from 40 individuals. A performance comparison of the dataset revealed that the proposed method exhibited good performance and efficiency compared to other well-known methods.

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

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

Prediction of Gait Kinematics and Kinetics: A Systematic Review of EMG and EEG Signal Use and Their Contribution to Prediction Accuracy.

Human-machine interfaces hold promise in enhancing rehabilitation by predicting and responding to subjects' movement intent. In gait rehabilitation, neural network architectures utilize lower-limb muscle and brain activity to predict continuous kinematics and kinetics during stepping and walking. This systematic review, spanning five databases, assessed 16 papers meeting inclusion criteria. Studies predicted lower-limb kinematics and kinetics using electroencephalograms (EEGs), electromyograms (EMGs), or a combination with kinematic data and anthropological parameters. Long short-term memory (LSTM) and convolutional neural network (CNN) tools demonstrated highest accuracies. EEG focused on joint angles, while EMG predicted moments and torque joints. Useful EEG electrode locations included C3, C4, Cz, P3, F4, and F8. Vastus Lateralis, Rectus Femoris, and Gastrocnemius were the most commonly accessed muscles for kinematic and kinetic prediction using EMGs. No studies combining EEGs and EMGs to predict lower-limb kinematics and kinetics during stepping or walking were found, suggesting a potential avenue for future development in this technology.

A Portable and a Scalable Multi-Channel Wireless Recording System for Wearable Electromyometrial Imaging.

Electromyometrial imaging (EMMI) technology has emerged as one of the promising technology that can be used for non-invasive pregnancy risk stratification and for preventing complications due to pre-term birth. Current EMMI systems are bulky and require a tethered connection to desktop instrumentation, as a result, the system cannot be used in non-clinical and ambulatory settings. In this article, we propose an approach for designing a scalable, portable wireless EMMI recording system that can be used for in-home and remote monitoring. The wearable system uses a non-equilibrium differential electrode multiplexing approach to enhance signal acquisition bandwidth and to reduce the artifacts due to electrode drifts, amplifier 1/f noise, and bio-potential amplifier saturation. A combination of active shielding, a passive filter network, and a high-end instrumentation amplifier ensures sufficient input dynamic range ([Formula: see text]) such that the system can simultaneously acquire different bio-potential signals like maternal electrocardiogram (ECG) in addition to the EMMI electromyogram (EMG) signals. We show that the switching artifacts and the channel cross-talk introduced due to non-equilibrium sampling can be reduced using a compensation technique. This enables the system to be potentially scaled to a large number of channels without significantly increasing the system power dissipation. We demonstrate the feasibility of the proposed approach in a clinical setting using an 8-channel battery-powered prototype which dissipates less than 8 μW per channel for a signal bandwidth of 1 KHz.

Extracting Individual Muscle Drive and Activity From High-Density Surface Electromyography Signals Based on the Center of Gravity of Motor Unit.

Neural interfacing has played an essential role in advancing our understanding of fundamental movement neurophysiology and the development of human-machine interface. However, direct neural interfaces from brain and nerve recording are currently limited in clinical areas for their invasiveness and high selectivity. Here, we applied the surface electromyogram (EMG) in studying the neural control of movement and proposed a new non-invasive way of extracting neural drive to individual muscles. Sixteen subjects performed isometric contractions to complete six hand tasks. High-density surface EMG signals (256 channels in total) recorded from the forearm muscles were decomposed into motor unit firing trains. The location of each decomposed motor unit was represented by its center of gravity and was put into clustering for distinct muscle regions. All the motor units in the same cluster served as a muscle-specific motor pool from which individual muscle drive could be extracted directly. Moreover, we cross-validated the self-clustered muscle regions by magnetic resonance imaging (MRI) recorded from the subjects' forearms. All motor units that fall within the MRI region are considered correctly clustered. We achieved a clustering accuracy of 95.72% ± 4.01% for all subjects. We provided a new framework for collecting experimental muscle-specific drives and generalized the way of surface electrode placement without prior knowledge of the targeting muscle architecture.

Difference in the Electromyographic Behavior of the Masticatory and Swallowing Muscles During Cued Versus Spontaneous Swallowing

The risk of dysphagia and/or aspiration is determined using screening tests, such as the repeated saliva swallowing test and modified water swallowing test, which evaluate cued swallowing. However, humans masticate and swallow foods with various consistencies, forms, and amounts, without conscious awareness. Therefore, this study aimed to examine the difference in the behavior of masticatory and swallowing muscles during spontaneous versus cued swallowing through a series of mastication and swallowing processes by evaluating surface electromyogram (sEMG) signals. The effect of the consistency and amount of food on the behavior of these muscles was also investigated. The sEMG recordings of the masseter muscles and anterior belly of the digastric muscle for 12 subjects, and genioglossus muscle for 5 subjects were obtained. The genioglossus activity was recorded using custom-made ball electrodes. The test foods were cookies and tofu, in amounts of 2 g and 4 g. The normalized muscle activity (integrated EMG), duration of the muscle activity, initial activation timepoint of each muscle, and total duration of swallowing were compared among four conditions. The activity of each muscle was significantly higher during the swallowing of cookies than tofu, for 4 g vs 2 g, and for cued versus spontaneous swallowing. The duration of each muscle activity, initial activation timepoint, and total duration of swallowing were significantly longer for cookies versus tofu, for 4 g vs 2 g, and for spontaneous versus cued swallowing. These results suggest that the behavior of the masticatory and swallowing muscles is affected by cued swallowing and by the consistency and amount of food.

Siamese Neural Network for User Authentication in Field-Programmable Gate Arrays (FPGAs) for Wearable Applications

User authentication has traditionally been performed using methods such as passwords or fingerprints. However, passwords have security vulnerabilities, and fingerprints may hinder user convenience. To address these issues, a novel user authentication method based on biosignals, specifically electromyogram (EMG) signals, is proposed. Using biosignals like EMG offers several advantages, including the ability to acquire data without user awareness, independence from the user’s environment, rapid acquisition, and enhanced security. However, one challenge with using EMG signals for authentication has been their relatively low accuracy. In this paper, a neural network is implemented using a small number of parameters (fewer than 7000) to produce a wearable device using biosignals, and user authentication accuracy is secured using the maximal overlap discrete wavelet transform (MODWT) method and the Siamese network. The MODWT method is highly effective for the time and frequency analysis of time series data, and the Siamese network is a representative method for few-shot learning. The proposed neural network is verified using Chosun University’s user authentication dataset, encompassing data from 100 individuals. Finally, this proposed network is implemented on an edge device such as field-programmable gate arrays (FPGAs) so that it can be applied to a wearable user authentication system. By implementing the Siamese network in FPGA-based edge devices, it was possible to secure user authentication performance at 94% accuracy and an authentication speed within 1.5 ms. In the case of accuracy, it is expected to be further improved by using the multimodal technique of biosignals. Also, the proposed system can be easily fabricated for digital integrated chips (ICs).

Effects of Governor Vessel electroacupuncture on chloridion homeostasis in the cortex of rats with limb spasm after cerebral ischemia-reperfusion

To observe the effect of electroacupuncture (EA) stimulation of Governor Vessel on chloridion (Cl-) homeostasis and the expression of γ-aminobutyric acid (GABA) and Na+-K+-Cl- cotransporter 1 (NKCC1) in the cerebral cortex of cerebral ischemia-reperfusion injury (CIRI) model rats, so as to explore its mechanism underl-ying alleviating limb spasm after stroke. Forty-five male SD rats were randomly divided into normal, sham-operation, model, EA and baclofen groups, with 9 rats in each group. The CIRI model was established by occlusion of the middle cerebral artery and reperfusion. EA(100 Hz) was applied to "Dazhui" (GV14), "Jizhong"(GV6) and "Houhui" for 30 min. Rats of the baclofen group received gavage of baclofen solution (0.4 mg/kg, 1 mL/100 g), once daily for 7 consecutive days. Neurological deficit score was assessed according to Zea Longa's method. The muscular tone of quadriceps femoris of the limb was evaluated by modified Ashworth scale and electrophysiological recor-ding methods, separately. TTC staining was used to detect cerebral infarction volume, and the brain water content of rats in each group was determined by wet and dry weight method. The contents of Cl- and GABA in the cerebral cortex were detected by colorimetric method, and the expression levels of NKCC1 mRNA and protein in the cerebral cortex were detected by quantitative real-time PCR and Western blot, separately. No significant differences were found between the normal and sham-operation groups in all the indexes. Compared with the normal and sham-operation groups, the neurological deficit score, modified Ashworth muscle tone score, brain water content, cerebral infarct volu-me percent, Cl- content and expression levels of NKCC1 mRNA and protein were all evidently increased (P<0.01), and muscle tone of electrophyiological electromyogram (EMG) signal and GABA content were strikingly decreased (P<0.01) in the model group. Compared with the model group, both EA and baclofen groups had an obvious increase in EMG signal displayed muscle tone, and GABA content (P<0.05, P<0.01), and a marked decrease in the neurological deficit score, modified Ashworth score, brain water content, cerebral infarct percent, Cl- content and expression levels of NKCC1 mRNA and protein (P<0.05, P<0.01). EA stimulation of acupoints of the Governor Vessel can improve the degree of limb spasm and reduce the degree of cerebral edema and infarction in rats with stroke, which may be related to its functions in protecting Cl- homeostasis, up-regulating GABA concentration, and down-regulating the expression of NKCC1 protein and mRNA in the cerebral cortex.

Wearable Liquid Metal Composite with Skin-Adhesive Chitosan-Alginate-Chitosan Hydrogel for Stable Electromyogram Signal Monitoring.

In wearable bioelectronics, various studies have focused on enhancing prosthetic control accuracy by improving the quality of physiological signals. The fabrication of conductive composites through the addition of metal fillers is one way to achieve stretchability, conductivity, and biocompatibility. However, it is difficult to measure stable biological signals using these soft electronics during physical activities because of the slipping issues of the devices, which results in the inaccurate placement of the device at the target part of the body. To address these limitations, it is necessary to reduce the stiffness of the conductive materials and enhance the adhesion between the device and the skin. In this study, we measured the electromyography (EMG) signals by applying a three-layered hydrogel structure composed of chitosan-alginate-chitosan (CAC) to a stretchable electrode fabricated using a composite of styrene-ethylene-butylene-styrene and eutectic gallium-indium. We observed stable adhesion of the CAC hydrogel to the skin, which aided in keeping the electrode attached to the skin during the subject movement. Finally, we fabricated a multichannel array of CAC-coated composite electrodes (CACCE) to demonstrate the accurate classification of the EMG signals based on hand movements and channel placement, which was followed by the movement of the robot arm.

Classification of Myopathy and Normal Electromyogram (EMG) Data with a New Deep Learning Architecture

Electromyograms (EMG) are recorded movements of nerves and muscles that help diagnose muscles and nerve-related disorders. It is frequently used in the diagnosis of neuromuscular diseases such as myopathy, which causes many changes in EMG signal properties. The most useful auxiliary test in the diagnosis of myopathy is EMG. Therefore, it has become imperative to identify computer-assisted anomalies with full accuracy and to develop an efficient classifier. In this study, a new machine learning method with a deep learning architecture that can score normal and myopathy EMG from the EMGLAB database is proposed. Using the discrete wavelet transform Coiflets 5 (Coif 5) wavelet, the EMG signals are decomposed into subbands and various statistical features are obtained from the wavelet coefficients. The success rates of the decision tree C4.5 algorithm, which is one of the traditional learning architectures, and the Long Short-term Memory (LSTM) algorithm, which is one of the deep learning architectures, were compared. Unlike the studies in the literature, with the LSTM algorithm, a 100% success rate was achieved with the proposed model. In addition, a real-time approach is presented by analyzing the test data classification time of the model.

Raw EMG classification using extreme value machine

Electromyogram (EMG) signal is considered as an easy-to-capture (i.e. skin-mounted) and promissing biometric for the control of prosthetic hands. Despite the plethora number of researches on EMG-based control of prosthetics, two major challenges have not sufficiently been addressed , i.e. realtime classification, and robustness against noise. Our contribution in this paper is two fold. First, we have proposed a deep neural network (DNN) model with customized architecture to learn features directly from raw EMG data. In this model, a self-improvement module enhances the accuracy and robustness against artifact. Second, we utilize extreme value machine (EVM) for classification of the learnt feature. EVM models the statistical distribution of the latent space and classifies finger movements based on the maximum cumulative distribution probability to the fitted model. Our experimental results, using public domain EMG data, are very promising. They indicate the average accuracy of 98.5% for 750 msec window for 10-class classification. This result is superior or competitive compared with other online classifications reported in the literature on the same dataset. Additionally, our results illustrate that self-improvement feature learner (SIFL) is much more resistant against the noise than the models that employ engineered features. For example, in presence of severe white noise, the accuracy of our methodology degrades 10−15% compared to 30−50% of others.

Stretchable porous conductive hydrogel films prepared by emulsion template method as flexible sensors

Conductive hydrogels with stretchability, breathability and long-term stability have attracted increasing attention for the applications in interactive wearable devices, artificial prosthetics, and intelligent robots. In this paper, a stretchable (up to 254 %), well breathable (vapor transmission up to 1.231×10−2 g·cm−2·h−1), and stable conductive (1.21 S/m) hydrogel films (Gel/PPy/Ag) was prepared by gel-template immersion method using gelatin as gel networks, polypyrrole (PPy) and silver (Ag) as conductive reinforcing filler and Span 80 as emulsion template. The film could maintain flexibility and conductivity after stored in an environment of –20 °C or 25 °C for 20 days. The excellent frost resistance and water retention ensured the practical application of the porous organic hydrogel film with environmental adaptability and long-term stability. The strain sensor made from the Gel/PPy/Ag films presented excellent sensitivity (GF reached 2.034), good durability, fast response (0.34 s) and recovery ability (0.36 s). It monitored weak and vigorous human motions effectively and sensitively. The Gel/PPy/Ag flexible electrodes realized the real-time sensitive detection of human Electrocardiogram (ECG) and electromyogram (EMG) signals and precision sensing control of the manipulator arm. The Gel/PPy/Ag hydrogel and the prepared flexible electronic devices have broad application prospects in the field of health monitoring, motion monitoring, operation control and other soft electronic devices.

Comparative analysis of the effect of electromyogram to bispectral index and 95% spectral edge frequency under remimazolam and propofol anesthesia: a prospective, randomized, controlled clinical trial.

Bispectral index (BIS), an index used to monitor the depth of anesthesia, can be interfered with by the electromyogram (EMG) signal. The 95% spectral edge frequency (SEF95) also can reflect the sedation depth. Remimazolam in monitored anesthesia care results in higher BIS values than propofol, though in the same sedation level assessed by Modified Observers Assessment of Alertness and Sedation (MOAA/S). Our study aims to illustrate whether EMG is involved in remimazolam causing higher BIS value than propofol preliminarily and to explore the correlations among BIS, EMG, and SEF95 under propofol and remimazolam anesthesia. Twenty-eight patients were randomly divided into propofol (P) and remimazolam (RM) groups. Patients in the two groups received alfentanil 10 μg/kg, followed by propofol 2 mg/kg and remimazolam 0.15 mg/kg. Blood pressure (BP), heart rate (HR), and oxygen saturation (SpO2) were routinely monitored. The BIS, EMG, and SEF95 were obtained through BIS VISTATM. The primary outcomes were BIS, EMG, and the correlation between BIS and EMG in both groups. Other outcomes were SEF95, the correlation between BIS and SEF95, and the correlation between EMG and SEF95. And all the statistical and comparative analysis between these signals was conducted with SPSS 26.0 and GraphPad Prism 8. BIS values, EMG, and SEF95 were significantly higher in the RM group than in the P group (all p < 0.001). There was a strong positive correlation between BIS and EMG in the RM group (r = 0.416). Nevertheless, the BIS in the P group showed a weak negative correlation with EMG (r = -0.219). Both P (r = 0.787) and RM group (r = 0.559) had a reasonably significant correlation coefficient between BIS and SEF95. SEF95 almost did not correlate with EMG in the RM group (r = 0.101). Bispectral index can be interfered with high EMG intensity under remimazolam anesthesia. However, EMG can hardly affect the accuracy of BIS under propofol anesthesia due to low EMG intensity and a weak negative correlation between EMG and BIS. Moreover, SEF95 may have a great application prospect in predicting the sedation condition of remimazolam.

MULTIFRACTAL ANALYSIS OF EMG FOR CLASSIFICATION AND PROGRESSIVE ASSESSMENT OF BICEPS BRACHII MUSCLE STRENGTH

The proposed research demonstrates an attempt to introduce a systematic procedure for studying the multifractal dynamics of biceps brachii muscle actions during light exercises. The intrinsic patterns in the Surface Electromyogram (sEMG) signals were extracted by fruitfully exploiting the Multifractal features of the signal. The Multifractal features are derived from the multifractal singularity spectrum of the EMG signals. This multifractal feature vector could be utilized for signal characterization, which was successfully extended for the classification of EMG signals. Experimental verification has been done to validate the feature extraction and classification algorithm proposed in this article. A pilot study was conducted on signals from the Physionet database, which was then extended to a medium database developed with biceps brachii EMG signals of 32 healthy male subjects. From this study, we could validate that the Multifractal features fit as a differentiating multi-feature set and also for the progressive assessment of EMG signals of different classes. The observations of the proposed method revealed that the strength of multifractality and area under the spectrum increase as a result of fast movements of the forearm or increases in muscle fatigue. The classification is performed using well-recognized supervised classification algorithms such as k-Nearest Neighbor and Support Vector Machine (SVM) Classifiers. The performance analysis of the classifiers are studied on various measures such as Accuracy, Precision, Recall, F1 score. The statistical significance analysis of the feature vector was carried out by one-way ANOVA test.

Deep Scattering Transform with Attention Mechanisms Improves EMG-based Hand Gesture Recognition.

Electromyogram (EMG) signals provide valuable insights into the muscles' activities supporting the different hand movements, but their analysis can be challenging due to their stochastic nature, noise, and non-stationary variations in the signal. We are pioneering the use of a unique combination of wavelet scattering transform (WST) and attention mechanisms adopted from recent sequence modelling developments of deep neural networks for the classification of EMG patterns. Our approach utilizes WST, which decomposes the signal into different frequency components, and then applies a non-linear operation to the wavelet coefficients to create a more robust representation of the extracted features. This is coupled with different variations of attention mechanisms, typically employed to focus on the most important parts of the input data by considering weighted combinations of all input vectors. By applying this technique to EMG signals, we hypothesized that improvement in the classification accuracy could be achieved by focusing on the correlation between the different muscles' activation states associated with the different hand movements. To validate the proposed hypothesis, the study was conducted using three commonly used EMG datasets collected from various environments based on laboratory and wearable devices. This approach shows significant improvement in myoelectric pattern recognition (PR) compared to other methods, with average accuracies of up to 98%.

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

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

Curve Fitting Based Minimum Norm Estimation (CFB-MNE) for motor unit spatial localization using high density surface electromyogram signals

The purpose of the study is the real time spatial localization of single motor units using simulated Motor Unit Action Potential dictionary from a cylindrical muscle volume conductor model by means of a state-of-the-art curve fitting method. This Curve Fitting Based Minimum Norm Estimation (CFB-MNE) was made possible by using minimum norm estimation methods to solve an underdetermined inverse problem knowing produced HD-sEMG signals. Specific data extracted from the inverse problem of a pre-determined number of simulated motor units were used to create a 3D curve, which can be used as a fitting curve to anticipate the unknown location of motor units. Results show that the proposed algorithms succeeded in accurately localizing motor units with varying noise levels in a fast duration (less than 100 ms). From all the simulations, a mean root mean square error of maximum 1 mm was recorded for the localization of the depth (less than 1 mm) and a negligible error for the angular position (less than 1°). The proposed work is an innovative algorithm that aids in non-invasively localizing motor units within a muscle in real time. Further efforts are planned to manage MUAP superposition and type. Final applications are related to prosthetic control, rehabilitation guidance or aging monitoring.

Evaluation of intraoperative neuromonitoring (IONM) data with the Mainz IONM Quality Assurance and Analysis tool

Abstract Background Intraoperative neuromonitoring is widely used in thyroid and parathyroid surgery to prevent unilateral and especially bilateral recurrent nerve paresis. Reference values for amplitude and latency for the recurrent laryngeal nerve and vagus nerve have been published. However, data quality measures that exclude errors of the underlying intraoperative neuromonitoring (IONM) data (immanent software errors, false data labelling) before statistical analysis have not yet been implemented. Methods The authors developed an easy-to-use application (the Mainz IONM Quality Assurance and Analysis tool) using the programming language R. This tool allows visualization, automated and manual correction, and statistical analysis of complete raw data sets (electromyogram signals of all stimulations) from intermittent and continuous neuromonitoring in thyroid and parathyroid surgery. The Mainz IONM Quality Assurance and Analysis tool was used to evaluate IONM data generated and exported from ‘C2’ and ‘C2 Xplore’ neuromonitoring devices (inomed Medizintechnik GmbH) after surgery. For the first time, reference values for latency and amplitude were calculated based on ‘cleaned’ IONM data. Results Intraoperative neuromonitoring data files of 1935 patients consecutively operated on from June 2014 to May 2020 were included. Of 1921 readable files, 34 were excluded for missing data labelling. Automated plausibility checks revealed: less than 3 per cent device errors for electromyogram signal detection; 1138 files (approximately 60 per cent) contained potential labelling errors or inconsistencies necessitating manual review; and 915 files (48.5 per cent) were indeed erroneous. Mean(s.d.) reference onset latencies for the left vagus nerve, right vagus nerve, recurrent laryngeal nerve, and external branch of the superior laryngeal nerve were 6.8(1.1), 4.2(0.8), 2.5(1.1), and 2.1(0.5) ms, respectively. Conclusion Due to high error frequencies, IONM data should undergo in-depth review and multi-step cleaning processes before analysis to standardize scientific reporting. Device software calculates latencies differently; therefore reference values are device-specific (latency) and/or set-up-specific (amplitude). Novel C2-specific reference values for latency and amplitude deviate considerably from published values.

Wearable Electromyogram Design for Finger Movements Based Real-Time Human-Machine Interfaces

In this study, a wearable electromyogram (EMG) system on the forearm was designed to analyze finger movements for use in human-machine interfaces. The designed system measures the EMG signals without restricting the user's movements, analyzes these measurements through the software embedded in the system, and transmits the generated response to the output units to be controlled in real-time with wireless communication techniques. In the study, a three-channel EMG amplifier was designed and a system in which the NodeMCU V3 development board could be integrated was realized.With the system, the features of finger movements were obtained using the Mean Absolute Value (MAV) and classified using Support Vector Machines (SVM) and Random Forest (RF) methods. In offline tests, 99.47% accursacy with RF and 98.2% accuracy with SVM were obtained. The RF algorithm with 99.47% accuracy in offline tests was selected and integrated into the embedded system for online tests. In the online tests performed with five volunteers, the system was able to analyze finger movements with an average accuracy of 92.16%, and the commands associated with the finger movements analyzed by the system were sent to the clients with the User Datagram Protocol (UDP), and the related movements were displayed on the output unit interface. The system can work in real-time with a delay of 90 ms and instantaneous movements can be seen visually on the designed output unit interface. This study is an important step in the detection of muscle diseases, the control of EMG-based wearable prosthetic systems, and the design of unmanned vehicles that can be controlled by finger movements.

An efficient attention-driven deep neural network approach for continuous estimation of knee joint kinematics via sEMG signals during running

The smooth interaction and coordination between lower-limb amputees and their prosthetics is crucial when performing complex tasks such as running. To address this, simultaneous and proportional control (SPC) based on continuous estimation of joint angles through surface electromyogram (sEMG) signals offers a more seamless interaction between users and their prosthetic limbs than conventional pattern recognition-based control, which relies on recognizing pre-defined movement classes from specific sEMG patterns using classification algorithms. This study proposes a deep learning-based model (AM-BiLSTM) that integrates the attention mechanism (AM) and bidirectional long short-term memory (BiLSTM) network to provide an accurate and robust SPC for estimating knee joint angle during running from a minimal number of sEMG sensors. The sEMG signals of four muscles recorded from 14 subjects during treadmill running at various speeds were utilized by the AM-BiLSTM model to decode knee joint kinematics. To comprehensively investigate the generalizability of the proposed model, it was tested in intra-subject and speed, intra-subject and inter-speed, and inter-subject and speed scenarios and compared with BiLSTM, standard LSTM, and multi-layer perceptron (MLP) approaches. Normalized root-mean-square error and correlation coefficient were used as performance metrics. According to nonparametric statistical tests, the proposed AM-BiLSTM model significantly outperformed the BiLSTM network as well as classical techniques including LSTM and MLP networks in all three experiments (p-value < 0.05) and achieved state-of-the-art performance. Based on our findings, the AM-BiLSTM model may facilitate the deployment of intuitive user-driven deep learning-based control schemes for a wide variety of miniaturized robotic lower-limb devices, including myoelectric prostheses.