Explore the vast range of titles available.

This review is a comprehensive guide for electromyography (EMG) researchers, providing a comparison of skin EMG recording (surface EMG: sEMG and high-density sEMG: HD-sEMG) and intramuscular EMG recording (multi-motor unit-MMU and single motor unit electromyography-SMU). We delve into the nuances of techniques, highlighting their strengths and limitations in quantifying muscle activation during dynamic and static conditions. We first examine how EMG signals change with time, focussing on the interplay between motor unit synchronisation and signal amplitude. The review then explores the impact of electrode placement on signal quality. We further discuss the challenges of signal cancellation, crosstalk from neighbouring muscles, and motion artifacts, which can significantly affect signal integrity. Finally, we address the temporal changes in electrode impedance and its implications for data interpretation. Our analysis proposes that specific research objectives should guide the choice amongst sEMG, HD-sEMG, SMU and MMU. MMU, which records the peak counts of individual motor unit action potentials from a localised muscle area, is particularly suited for studying deep or small muscles during static and dynamic activities. Its high sensitivity to motor unit recruitment and discharge rates minimises the impact of factors such as signal cancellation and motion artefacts. Conversely, sEMG is well-suited for short-duration, isometric assessments of large, superficial muscles. HD-sEMG helps study single motor unit properties under isometric conditions. SMU is particularly suited for studying neuronal networks between stimulated sites and motor neurons. This review aims to provide researchers with the information to select the most appropriate EMG technique for their investigations. Graphical abstract

Objectives: Surface electromyography (sEMG) is a standard tool in clinical routine, clinical or psychosocial experiments including also speech research and orthodontics to measure the activity of selected facial muscles to objectify facial movements during specific facial exercises or experiments with emotional expressions. Such muscle-specific approaches neglect that facial muscles act more as an interconnected network than as single facial muscles for specific movements. What is missing is an optimal sEMG setting allowing a synchronous measurement of the activity of all facial muscles as a whole. Methods: 36 healthy adult participants (53% female, 18-67 years) were included. Electromyograms were recorded from both sides of the face using an arrangement of electrodes oriented by the underlying topography of the facial muscles (Fridlund scheme) and simultaneously by a geometric and symmetrical arrangement on the face (Kuramoto scheme). The participants performed a standard set of different facial movement tasks. Linear mixed-effects models and adjustment for multiple comparisons were used to evaluate differences between the facial movement tasks, separately for both applied schemes. Data analysis utilized sEMG amplitudes and also their maximum-normalized values to account for amplitude differences between the different facial movements. Results: sEMG activation characteristics showed systematic regional distribution patterns of facial muscle activation for both schemes with very low inter-individual variability. The statistical significance to discriminate between the different sEMG patterns was good for both schemes (significant comparisons for sEMG amplitudes: 87.3%, both schemes, normalized values: 90.9 %, Fridlund scheme, 94.5% Kuramoto scheme), but the Kuramoto scheme performed considerably superior. Conclusion: Facial movement tasks evoke specific patterns in the complex network of facial muscles rather than activating single muscles. A geometric and symmetrical sEMG recording from the entire face seems to allow a more specific detection of facial muscle activity patterns during facial movement tasks. Such a sEMG patterns should be explored on more clinical and psychological experiments in the future.

By training the deep neural network model, the hidden features in Surface Electromyography(sEMG) signals can be extracted. The motion intention of the human can be predicted by analysis of sEMG. However, the models recently proposed by researchers often have a large number of parameters. Therefore, we designed a compact Convolution Neural Network (CNN) model, which not only improves the classification accuracy but also reduces the number of parameters in the model. Our proposed model was validated on the Ninapro DB5 Dataset and the Myo Dataset. The classification accuracy of gesture recognition achieved good results.

A number of researchers prefer using multi-channel surface electromyography (sEMG) pattern recognition in hand gesture recognition to increase classification accuracy. Using this method can lead to computational complexity. Hand gesture classification by employing single channel sEMG signal acquisition is quite challenging, especially for low-rate sampling frequency. In this paper, a study on the pattern recognition method for sEMG signals of nine finger movements is presented. Common surface single channel electromyography (sEMG) was used to measure five different subjects with no neurological or muscular disorder by having nine hand movements. This research had several sequential processes (i.e., feature extraction, feature reduction, and feature classification). Sixteen time-domain features were employed for feature extraction. The features were then reduced using principal component analysis (PCA) into two and three-dimensional feature space. The artificial neural network (ANN) classifier was tested on two different feature sets: (1) using all principal components obtained from PCA (PC1–PC3) and (2) using selected principal components (PC2 and PC3). The third best principal components were then used for classification using ANN. The average accuracy using all subject signals was 86.7% to discriminate the nine finger movements.

High-density surface electromyography (HD-sEMG) and deep learning technology are becoming increasingly used in gesture recognition. Based on electrode grid data, information can be extracted in the form of images that are generated with instant values of multi-channel sEMG signals. In previous studies, image-based, two-dimensional convolutional neural networks (2D CNNs) have been applied in order to recognize patterns in the electrical activity of muscles from an instantaneous image. However, 2D CNNs with 2D kernels are unable to handle a sequence of images that carry information concerning how the instantaneous image evolves with time. This paper presents a 3D CNN with 3D kernels to capture both spatial and temporal structures from sequential sEMG images and investigates its performance on HD-sEMG-based gesture recognition in comparison to the 2D CNN. Extensive experiments were carried out on two benchmark datasets (i.e., CapgMyo DB-a and CSL-HDEMG). The results show that, where the same network architecture is used, 3D CNN can achieve a better performance than 2D CNN, especially for CSL-HDEMG, which contains the dynamic part of finger movement. For CapgMyo DB-a, the accuracy of 3D CNN was 1% higher than 2D CNN when the recognition window length was equal to 40 ms, and was 1.5% higher when equal to 150 ms. For CSL-HDEMG, the accuracies of 3D CNN were 15.3% and 18.6% higher than 2D CNN when the window length was equal to 40 ms and 150 ms, respectively. Furthermore, 3D CNN achieves a competitive performance in comparison to the baseline methods.

With the trend going on in ubiquitous computing, everything is going to be connected to the Internet and its data will be used for various progressive purposes, creating not only information from it, but also, knowledge and even wisdom. Internet of Things (IoT) is becoming important because the amount of data could make it possible to create more usefulness and develop smart applications for the users. Meanwhile, it mainly focuses on how to enable general objects to see, hear, and smell the physical world for themselves, and make them connected to share the observations. In this paper, we focus our attention on the integration of artificial sensory perception and haptic feedback in sEMG hands, which is an intelligent application of the IoT. Artificial sensory perception and haptic feedback are essential elements for amputees with myoelectric hands to restore the grasping function. They can provide information to users, such as forces of interaction and surface properties at points of contact between hands and objects. Recent advancements in robot tactile sensing led to development of many computational techniques that exploit this important sensory channel. At the same time, Surface electromyography (sEMG) is perhaps most useful for providing insight into how the neuromuscular system behaves. Therefore, integration of sEMG technology, artificial sensation and haptic feedback plays an important role in improving the manipulation performance and enhancing perceptual embodiment for users. This paper provides sEMG technologies that involve Multichannel sEMG electrodes array and processing methods, and then reviews current state-of-the-art of artificial sensation and haptic feedback. Drawing from advancements and taking into design considerations of each feedback modality and individual haptic technology, the paper outline challenging issues and future developments.

High-density surface electromyography (HD-sEMG) plays a crucial role in medical diagnostics, prosthetic control, and human-machine interactions. Compared to traditional bipolar sEMG, HD-sEMG employs smaller electrode spacing and sizes. This configuration not only reduces the signal collection area but also increases sensitivity to individual variations in skin impedance. Additionally, smaller high-density electrodes are more susceptible to environmental electromagnetic interference, thereby increasing the risk of signal loss and limiting the further development and application of HD-sEMG technology. To address this issue, this study introduces a novel deep learning-based technique specifically designed to restore lost HD-sEMG signals. Through an improved novel convolutional neural network (CNN), our method can reconstruct HD-sEMG signals both efficiently and accurately. Experimental results demonstrate that the proposed CNN algorithm effectively reconstructs lost HD-sEMG signals with high fidelity. The average root mean square error (RMSE) across all participants was 0.108, the mean absolute error (MAE) was 0.070, and the coefficient of determination ($$R^2$$R 2 ) was 0.98. Furthermore, the model achieved an average structural similarity index measure (SSIM) of 0.96 and a peak signal-to-noise ratio (PSNR) of 29.13 dB, indicating high levels of structural similarity and signal clarity in the reconstructed data. These findings highlight the robustness and effectiveness of our method, suggesting its potential for enhancing the reliability and utility of HD-sEMG signals in real applications.

The principal component analysis method and GRNN neural network are used to construct the gesture recognition system, so as to reduce the redundant information of EMG signals, reduce the signal dimension, improve the recognition efficiency and accuracy, and enhance the feasibility of real-time recognition. Using the means of extracting key information of human motion, the specific action mode is identified. In this paper, nine static gestures are taken as samples, and the surface EMG signal of the arm is collected by the electromyography instrument to extract four kinds of characteristics of the signal. After dimension reduction and neural network learning, the overall recognition rate of the system reached 95.1%, and the average recognition time was 0.19 s.

The range of applications of electromyography-based gesture recognition has increased over the last years. A common problem regularly encountered in literature is the inadequate data availability. Data augmentation, which aims at generating new synthetic data from the existing ones, is the most common approach to deal with this data shortage in other research domains. In the case of surface electromyography (sEMG) signals, there is limited research in augmentation methods and quite regularly the results differ between available studies. In this work, we provide a detailed evaluation of existing (i.e., additive noise, overlapping windows) and novel (i.e., magnitude warping, wavelet decomposition, synthetic sEMG models) strategies of data augmentation for electromyography signals. A set of metrics (i.e., classification accuracy, silhouette score, and Davies–Bouldin index) and visualizations help with the assessment and provides insights about their performance. Methods like signal magnitude warping and wavelet decomposition yield considerable increase (up to 16%) in classification accuracy across two benchmark datasets. Particularly, a significant improvement of 1% in the classification accuracy of the state-of-the-art model in hand gesture recognition is achieved.

Continuous joint angle estimation based on a surface electromyography (sEMG) signal can be used to improve the man-machine coordination performance of the exoskeleton. In this study, we proposed a time-advanced feature and utilized long short-term memory (LSTM) with a root mean square (RMS) feature and its time-advanced feature (RMSTAF; collectively referred to as RRTAF) of sEMG to estimate the knee joint angle. To evaluate the effect of joint angle estimation, we used root mean square error (RMSE) and cross-correlation coefficient ρ between the estimated angle and actual angle. We also compared three methods (i.e., LSTM using RMS, BPNN (back propagation neural network) using RRTAF, and BPNN using RMS) with LSTM using RRTAF to highlight its good performance. Five healthy subjects participated in the experiment and their eight muscle (i.e., rectus femoris (RF), biceps femoris (BF), semitendinosus (ST), gracilis (GC), semimembranosus (SM), sartorius (SR), medial gastrocnemius (MG), and tibialis anterior (TA)) sEMG signals were taken as algorithm inputs. Moreover, the knee joint angles were used as target values. The experimental results showed that, compared with LSTM using RMS, BPNN using RRTAF, and BPNN using RMS, the average RMSE values of LSTM using RRTAF were respectively reduced by 8.57%, 46.62%, and 68.69%, whereas the average ρ values were respectively increased by 0.31%, 4.15%, and 18.35%. The results demonstrated that LSTM using RRTAF, which contained the time-advanced feature, had better performance for estimating the knee joint motion.