putEMG-A Surface Electromyography Hand Gesture Recognition Dataset

EMG Dataset for Gesture Recognition with Arm Translation

Myoelectric control has emerged as a promising approach for a wide range of applications, including controlling limb prosthetics, teleoperating robots and enabling immersive interactions in the Metaverse. However, the accuracy and robustness of myoelectric control systems are often affected by various factors, including muscle fatigue, perspiration, drifts in electrode positions and changes in arm position. The latter has received less attention despite its significant impact on signal quality and decoding accuracy. To address this gap, we present a novel dataset of surface electromyographic (EMG) signals captured from multiple arm positions. This dataset, comprising EMG and hand kinematics data from 8 participants performing 6 different hand gestures, provides a comprehensive resource for investigating position-invariant myoelectric control decoding algorithms. We envision this dataset to serve as a valuable resource for both training and benchmark arm position-invariant myoelectric control algorithms. Additionally, to expand the publicly available data capturing the variability of EMG signals across diverse arm positions, we propose a novel data acquisition protocol that can be utilized for future data collection.

Estimation of Lower Limb Joint Angles Using sEMG Signals and RGB-D Camera

Estimating human joint angles is a crucial task in motion analysis, gesture recognition, and motion intention prediction. This paper presents a novel model-based approach for generating reliable and accurate human joint angle estimation using a dual-branch network. The proposed network leverages combined features derived from encoded sEMG signals and RGB-D image data. To ensure the accuracy and reliability of the estimation algorithm, the proposed network employs a convolutional autoencoder to generate a high-level compression of sEMG features aimed at motion prediction. Considering the variability in the distribution of sEMG signals, the proposed network introduces a vision-based joint regression network to maintain the stability of combined features. Taking into account latency, occlusion, and shading issues with vision data acquisition, the feature fusion network utilizes high-frequency sEMG features as weights for specific features extracted from image data. The proposed method achieves effective human body joint angle estimation for motion analysis and motion intention prediction by mitigating the effects of non-stationary sEMG signals.

A Multimodal Bracelet to Acquire Muscular Activity and Gyroscopic Data to Study Sensor Fusion for Intent Detection

Researchers have attempted to control robotic hands and prostheses through biosignals but could not match the human hand. Surface electromyography records electrical muscle activity using non-invasive electrodes and has been the primary method in most studies. While surface electromyography-based hand motion decoding shows promise, it has not yet met the requirements for reliable use. Combining different sensing modalities has been shown to improve hand gesture classification accuracy. This work introduces a multimodal bracelet that integrates a 24-channel force myography system with six commercial surface electromyography sensors, each containing a six-axis inertial measurement unit. The device's functionality was tested by acquiring muscular activity with the proposed device from five participants performing five different gestures in a random order. A random forest model was then used to classify the performed gestures from the acquired signal. The results confirmed the device's functionality, making it suitable to study sensor fusion for intent detection in future studies. The results showed that combining all modalities yielded the highest classification accuracies across all participants, reaching 92.3±2.6% on average, effectively reducing misclassifications by 37% and 22% compared to using surface electromyography and force myography individually as input signals, respectively. This demonstrates the potential benefits of sensor fusion for more robust and accurate hand gesture classification and paves the way for advanced control of robotic and prosthetic hands.

Surface Electromyography-Based Recognition of Electronic Taste Sensations

Taste sensation recognition is a core for taste-related queries. Most prior research has been devoted to recognizing the basic taste sensations using the Brain-Computer Interface (BCI), which includes EEG, MEG, EMG, and fMRI. This research aims to recognize electronic taste (E-Taste) sensations based on surface electromyography (sEMG). Silver electrodes with platinum plating of the E-Taste device were placed on the tongue's tip to stimulate various tastes and flavors. In contrast, the electrodes of the sEMG were placed on facial muscles to collect the data. The dataset was organized and preprocessed, and a random forest classifier was applied, giving a five-fold accuracy of 70.43%. The random forest classifier was used on each participant dataset individually and in groups, providing the highest accuracy of 84.79% for a single participant. Moreover, various feature combinations were extracted and acquired 72.56% accuracy after extracting eight features. For a future perspective, this research offers guidance for electronic taste recognition based on sEMG.

A Surface Electromyography (sEMG) System Applied for Grip Force Monitoring

Muscles play an indispensable role in human life. Surface electromyography (sEMG), as a non-invasive method, is crucial for monitoring muscle status. It is characterized by its real-time, portable nature and is extensively utilized in sports and rehabilitation sciences. This study proposed a wireless acquisition system based on multi-channel sEMG for objective monitoring of grip force. The system consists of an sEMG acquisition module containing four-channel discrete terminals and a host computer receiver module, using Bluetooth wireless transmission. The system is portable, wearable, low-cost, and easy to operate. Leveraging the system, an experiment for grip force prediction was designed, employing the bald eagle search (BES) algorithm to enhance the Random Forest (RF) algorithm. This approach established a grip force prediction model based on dual-channel sEMG signals. As tested, the performance of acquisition terminal proceeded as follows: the gain was up to 1125 times, and the common mode rejection ratio (CMRR) remained high in the sEMG signal band range (96.94 dB (100 Hz), 84.12 dB (500 Hz)), while the performance of the grip force prediction algorithm had an R2 of 0.9215, an MAE of 1.0637, and an MSE of 1.7479. The proposed system demonstrates excellent performance in real-time signal acquisition and grip force prediction, proving to be an effective muscle status monitoring tool for rehabilitation, training, disease condition surveillance and scientific fitness applications.

Synthesis of sEMG Signals for Hand Gestures Using a 1DDCGAN

The emergence of modern prosthetics controlled by bio-signals has been facilitated by AI and microchip technology innovations. AI algorithms are trained using sEMG produced by muscles during contractions. The data acquisition procedure may result in discomfort and fatigue, particularly for amputees. Furthermore, prosthetic companies restrict sEMG signal exchange, limiting data-driven research and reproducibility. GANs present a viable solution to the aforementioned concerns. GANs can generate high-quality sEMG, which can be utilised for data augmentation, decrease the training time required by prosthetic users, enhance classification accuracy and ensure research reproducibility. This research proposes the utilisation of a one-dimensional deep convolutional GAN (1DDCGAN) to generate the sEMG of hand gestures. This approach involves the incorporation of dynamic time wrapping, fast Fourier transform and wavelets as discriminator inputs. Two datasets were utilised to validate the methodology, where five windows and increments were utilised to extract features to evaluate the synthesised sEMG quality. In addition to the traditional classification and augmentation metrics, two novel metrics-the Mantel test and the classifier two-sample test-were used for evaluation. The 1DDCGAN preserved the inter-feature correlations and generated high-quality signals, which resembled the original data. Additionally, the classification accuracy improved by an average of 1.21-5%.

Novel Wearable HD-EMG Sensor With Shift-Robust Gesture Recognition Using Deep Learning

In this work, we present a hardware-software solution to improve the robustness of hand gesture recognition to confounding factors in myoelectric control. The solution includes a novel, full-circumference, flexible, 64-channel high-density electromyography (HD-EMG) sensor called EMaGer. The stretchable, wearable sensor adapts to different forearm sizes while maintaining uniform electrode density around the limb. Leveraging this uniformity, we propose novel array barrel-shifting data augmentation (ABSDA) approach used with a convolutional neural network (CNN), and an anti-aliased CNN (AA-CNN), that provides shift invariance around the limb for improved classification robustness to electrode movement, forearm orientation, and inter-session variability. Signals are sampled from a 4×16 HD-EMG array of electrodes at a frequency of 1 kHz and 16-bit resolution. Using data from 12 non-amputated participants, the approach is tested in response to sensor rotation, forearm rotation, and inter-session scenarios. The proposed ABSDA-CNN method improves inter-session accuracy by 25.67% on average across users for 6 gesture classes compared to conventional CNN classification. A comparison with other devices shows that this benefit is enabled by the unique design of the EMaGer array. The AA-CNN yields improvements of up to 63.05% accuracy over non-augmented methods when tested with electrode displacements ranging from -45 ° to +45 ° around the limb. Overall, this article demonstrates the benefits of co-designing sensor systems, processing methods, and inference algorithms to leverage synergistic and interdependent properties to solve state-of-the-art problems.

Power-Efficient Multisensory Reservoir Computing Based on Zr-Doped HfO2 Memcapacitive Synapse Arrays

Hardware implementation tailored to requirements in reservoir computing would facilitate lightweight and powerful temporal processing. Capacitive reservoirs would boost power efficiency due to their ultralow static power consumption but have not been experimentally exploited yet. Here, this work reports an oxide-based memcapacitive synapse (OMC) based on Zr-doped HfO2 (HZO) for a power-efficient and multisensory processing reservoir computing system. The nonlinearity and state richness required for reservoir computing could originate from the capacitively coupled polarization switching and charge trapping of hafnium-oxide-based devices. The power consumption (≈113.4 fJ per spike) and temporal processing versatility outperform most resistive reservoirs. This system is verified by common benchmark tasks, and it exhibits high accuracy (>94%) in recognizing multisensory information, including acoustic, electrophysiological, and mechanic modalities. As a proof-of-concept, a touchless user interface for virtual shopping based on the OMC-based reservoir computing system is demonstrated, benefiting from its interference-robust acoustic and electrophysiological perception. These results shed light on the development of highly power-efficient human-machine interfaces and machine-learning platforms.

Multi-dimensional task recognition for human-robot teaming: literature review

Human-robot teams collaborating to achieve tasks under various conditions, especially in unstructured, dynamic environments will require robots to adapt autonomously to a human teammate's state. An important element of such adaptation is the robot's ability to infer the human teammate's tasks. Environmentally embedded sensors (e.g., motion capture and cameras) are infeasible in such environments for task recognition, but wearable sensors are a viable task recognition alternative. Human-robot teams will perform a wide variety of composite and atomic tasks, involving multiple activity components (i.e., gross motor, fine-grained motor, tactile, visual, cognitive, speech and auditory) that may occur concurrently. A robot's ability to recognize the human's composite, concurrent tasks is a key requirement for realizing successful teaming. Over a hundred task recognition algorithms across multiple activity components are evaluated based on six criteria: sensitivity, suitability, generalizability, composite factor, concurrency and anomaly awareness. The majority of the reviewed task recognition algorithms are not viable for human-robot teams in unstructured, dynamic environments, as they only detect tasks from a subset of activity components, incorporate non-wearable sensors, and rarely detect composite, concurrent tasks across multiple activity components.

Evaluating Classifier Confidence for Surface EMG Pattern Recognition

Surface electromyogram (EMG) can be employed as an interface signal for various devices and software via pattern recognition. In EMG-based pattern recognition, the classifier should not only be accurate, but also output an appropriate confidence (i.e., probability of correctness) for its prediction. If the confidence accurately reflects the likelihood of true correctness, then it will be useful in various application tasks, such as motion rejection and online adaptation. The aim of this paper is to identify the types of classifiers that provide higher accuracy and better confidence in EMG pattern recognition. We evaluate the performance of various discriminative and generative classifiers on four EMG datasets, both visually and quantitatively. The analysis results show that while a discriminative classifier based on a deep neural network exhibits high accuracy, it outputs a confidence that differs from true probabilities. By contrast, a scale mixture model-based classifier, which is a generative classifier that can account for uncertainty in EMG variance, exhibits superior performance in terms of both accuracy and confidence.

Gender Differences in Taste Sensations Based on Frequency Analysis of Surface Electromyography

Males and females respond differently at the muscular level to various tastes and show varied responses when eating different foods. In this study, we used surface electromyography (sEMG) as a novel approach to examine gender differences in taste sensations. We collected sEMG data from 30 participants (15 males, 15 females) over various sessions for six taste states: a no-stimulation physiological state, sweet, sour, salty, bitter, and umami. We applied a Fast Fourier Transformation to the sEMG-filtered data and used a two-sample t-test algorithm to analyze and evaluate the resulting frequency spectrum. Our results showed that the female participants had more sEMG channels with low frequencies and fewer channels with high frequencies than the male participants during all taste states except the bitter taste sensation, meaning that for most sensations, the female participants had better tactile and fewer gustatory responses than the male participants. The female participants responded better to gustatory and tactile perceptions during bitter tasting because they had more channels throughout the frequency distribution. Moreover, the facial muscles of the female participants twitched with low frequencies, while the facial muscles of the male participants twitched with high frequencies for all taste states except the bitter sensation, for which the female facial muscles twitched throughout the range of the frequency distribution. This gender-dependent variation in sEMG frequency distribution provides new evidence of differentiated taste sensations between males and females.

Mechanical disturbances applied by motorized ankle foot orthosis to adapt ankle muscles activation—A validation study

Background: Reduced function of ankle muscles usually leads to impaired gait. Motorized ankle foot orthoses (MAFOs) have shown potential to improve neuromuscular control and increase volitional engagement of ankle muscles. In this study, we hypothesize that specific disturbances (adaptive resistance-based perturbations to the planned trajectory) applied by a MAFO can be used to adapt the activity of ankle muscles. The first goal of this exploratory study was to test and validate two different ankle disturbances based on plantarflexion and dorsiflexion resistance while training in standing still position. The second goal was to assess neuromuscular adaptation to these approaches, namely, in terms of individual muscle activation and co-activation of antagonists.

Methods: Two ankle disturbances were tested in ten healthy subjects. For each subject, the dominant ankle followed a target trajectory while the contralateral leg was standing still: a) dorsiflexion torque during the first part of the trajectory (Stance Correlate disturbance—StC), and b) plantarflexion torque during the second part of the trajectory (Swing Correlate disturbance—SwC). Electromyography was recorded from the tibialis anterior (TAnt) and gastrocnemius medialis (GMed) during MAFO and treadmill (baseline) trials.

Results: GMed (plantarflexor muscle) activation decreased in all subjects during the application of StC, indicating that dorsiflexion torque did not enhance GMed activity. On the other hand, TAnt (dorsiflexor muscle) activation increased when SwC was applied, indicating that plantarflexion torque succeeded in enhancing TAnt activation. For each disturbance paradigm, there was no antagonist muscle co-activation accompanying agonist muscle activity changes.

Conclusion: We successfully tested novel ankle disturbance approaches that can be explored as potential resistance strategies in MAFO training. Results from SwC training warrant further investigation to promote specific motor recovery and learning of dorsiflexion in neural-impaired patients. This training can potentially be beneficial during intermediate phases of rehabilitation prior to overground exoskeleton-assisted walking. Decreased activation of GMed during StC might be attributed to the unloaded body weight in the ipsilateral side, which typically decreases activation of anti-gravity muscles. Neural adaptation to StC needs to be studied thoroughly in different postures in futures studies.

sEMG-Based Continuous Hand Action Prediction by Using Key State Transition and Model Pruning

Conventional classification of hand motions and continuous joint angle estimation based on sEMG have been widely studied in recent years. The classification task focuses on discrete motion recognition and shows poor real-time performance, while continuous joint angle estimation evaluates the real-time joint angles by the continuity of the limb. Few researchers have investigated continuous hand action prediction based on hand motion continuity. In our study, we propose the key state transition as a condition for continuous hand action prediction and simulate the prediction process using a sliding window with long-term memory. Firstly, the key state modeled by GMM-HMMs is set as the condition. Then, the sliding window is used to dynamically look for the key state transition. The prediction results are given while finding the key state transition. To extend continuous multigesture action prediction, we use model pruning to improve reusability. Eight subjects participated in the experiment, and the results show that the average accuracy of continuous two-hand actions is 97% with a 70 ms time delay, which is better than LSTM (94.15%, 308 ms) and GRU (93.83%, 300 ms). In supplementary experiments with continuous four-hand actions, over 85% prediction accuracy is achieved with an average time delay of 90 ms.

Deep learning and session-specific rapid recalibration for dynamic hand gesture recognition from EMG

We anticipate wide adoption of wrist and forearm electomyographic (EMG) interface devices worn daily by the same user. This presents unique challenges that are not yet well addressed in the EMG literature, such as adapting for session-specific differences while learning a longer-term model of the specific user. In this manuscript we present two contributions toward this goal. First, we present the MiSDIREKt (Multi-Session Dynamic Interaction Recordings of EMG and Kinematics) dataset acquired using a novel hardware design. A single participant performed four kinds of hand interaction tasks in virtual reality for 43 distinct sessions over 12 days, totaling 814 min. Second, we analyze this data using a non-linear encoder-decoder for dimensionality reduction in gesture classification. We find that an architecture which recalibrates with a small amount of single session data performs at an accuracy of 79.5% on that session, as opposed to architectures which learn solely from the single session (49.6%) or learn only from the training data (55.2%).

Multi-day dataset of forearm and wrist electromyogram for hand gesture recognition and biometrics

Surface electromyography (sEMG) signals have been used for advanced prosthetics control, hand-gesture recognition (HGR), and more recently as a novel biometric trait. For these sEMG-based applications, the translation from laboratory research setting to real-life scenarios suffers from two major limitations: (1) a small subject pool, and (2) single-session data recordings, both of which prevents acceptable generalization ability. In this longitudinal database, forearm and wrist sEMG data were collected from 43 participants over three different days with long separation (Days 1, 8, and 29) while they performed static hand/wrist gestures. The objective of this dataset is to provide a comprehensive dataset for the development of robust machine learning algorithms of sEMG, for both HGR and biometric applications. We demonstrated the high quality of the current dataset by comparing with the Ninapro dataset. And we presented its usability for both HGR and biometric applications. Among other applications, the dataset can also be used for developing electrode-shift invariant generalized models, which can further bolster the development of wristband and forearm-bracelet sensors.

Dataset for multi-channel surface electromyography (sEMG) signals of hand gestures

This paper presents an electromyography (EMG) signal dataset for use in human-computer interaction studies. The dataset includes 4-channel surface EMG data from 40 participants with an equal gender distribution. The gestures in the data are rest or neutral state, extension of the wrist, flexion of the wrist, ulnar deviation of the wrist, radial deviation of the wrist, grip, abduction of all fingers, adduction of all fingers, supination, and pronation. Data were collected from 4 forearm muscles when simulating 10 unique hand gestures and recorded with the BIOPAC MP36 device using Ag/AgCl surface bipolar electrodes. Each participant's data contains five repetitive cycles of ten hand gestures. A demographic survey was applied to the participants before the signal recording process. This data can be utilized for recognition, classification, and prediction studies in order to develop EMG-based hand movement controller systems. The dataset can also be useful as a reference to create an artificial intelligence model (especially a deep learning model) to detect gesture-related EMG signals. Additionally, it is encouraged to use the proposed dataset for benchmarking current datasets in the literature or for validation of machine learning and deep learning models created with different datasets in accordance with the participant-independent validation strategy.

Quantitatively Recognizing Stimuli Intensity of Primary Taste Based on Surface Electromyography

A novel approach to quantitatively recognize the intensity of primary taste stimuli was explored based on surface electromyography (sEMG). We captured sEMG samples under stimuli of primary taste with different intensities and quantitatively recognized preprocessed samples with Support Vector Machine (SVM). The feasibility of quantitatively recognizing the intensity of Sour, Bitter, and Salty was verified. The sEMG signals were acquired under the stimuli of citric acid (aq), sucrose (aq), magnesium chloride (aq), sodium chloride (aq), and sodium glutamate (aq) with different concentrations, for five types of primary tastes: Sour, Sweet, Bitter, Salty, and Umami, whose order was fixed in this article. The acquired signals were processed with a method called Quadratic Variation Reduction to remove baseline wandering, and an adaptive notch to remove power frequency interference. After extracting 330 features for each sample, an SVM regressor with five-fold cross-validation was performed and the model reached R2 scores of 0.7277, 0.1963, 0.7450, 0.7642, and 0.5055 for five types of primary tastes, respectively, which manifested the feasibilities of the quantitative recognitions of Sour, Bitter, and Salty. To explore the facial responses to taste stimuli, we summarized and compared the muscle activities under stimuli of different taste types and taste intensities. To further simplify the model, we explored the impact of feature dimensionalities and optimized the feature combination for each taste in a channel-wise manner, and the feature dimensionality was reduced from 330 to 210, 120, 210, 260, 170 for five types of primary tastes, respectively. Lastly, we analyzed the model performance on multiple subjects and the relation between the model’s performance and the number of experiment subjects. This study can provide references for further research and applications on taste stimuli recognition with sEMG.

Qualitative Recognition of Primary Taste Sensation Based on Surface Electromyography

Based on surface electromyography (sEMG), a novel recognition method to distinguish six types of human primary taste sensations was developed, and the recognition accuracy was 74.46%. The sEMG signals were acquired under the stimuli of no taste substance, distilled vinegar, white granulated sugar, instant coffee powder, refined salt, and Ajinomoto. Then, signals were preprocessed with the following steps: sample augments, removal of trend items, high-pass filter, and adaptive power frequency notch. Signals were classified with random forest and the classifier gave a five-fold cross-validation accuracy of 74.46%, which manifested the feasibility of the recognition task. To further improve the model performance, we explored the impact of feature dimension, electrode distribution, and subject diversity. Accordingly, we provided an optimized feature combination that reduced the number of feature types from 21 to 4, a preferable selection of electrode positions that reduced the number of channels from 6 to 4, and an analysis of the relation between subject diversity and model performance. This study provides guidance for further research on taste sensation recognition with sEMG.

Prediction of motor Unified Parkinson's Disease Rating Scale scores in patients with Parkinson's disease using surface electromyography

OBJECTIVE

Parkinson's disease (PD) is a chronic neurodegenerative disorder with increasing prevalence in the elderly. Especially patients with advanced PD often require complex medication regimens due to fluctuations, that is abrupt transitions from ON to OFF or vice versa. Current gold standard to quantify PD-patients' motor symptoms is the assessment of the Unified Parkinson's Disease Rating Scale (UPDRS), which, however, is cumbersome and may depend upon investigators. This work aimed at developing a mobile, objective and unobtrusive measurement of motor symptoms in PD.

METHODS

Data from 45 PD-patients was recorded using surface electromyography (sEMG) electrodes attached to a wristband. The motor paradigm consisted of a tapping task performed with and without dopaminergic medication. Our aim was to predict UPDRS scores from the sEMG characteristics with distinct regression models and machine learning techniques.

RESULTS

A random forest regression model outnumbered other regression models resulting in a correlation of 0.739 between true and predicted UPDRS values.

CONCLUSIONS

PD-patients' motor affection can be extrapolated from sEMG data during a simple tapping task. In the future, such records could help determine the need for medication changes in telemedicine applications.

SIGNIFICANCE

Our findings support the utility of wearables to detect Parkinson's symptoms and could help in developing tailored therapies in the future.

Data Augmentation of Surface Electromyography for Hand Gesture Recognition

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.

Analysis of Influence of Segmentation, Features, and Classification in sEMG Processing: A Case Study of Recognition of Brazilian Sign Language Alphabet

Sign Language recognition systems aid communication among deaf people, hearing impaired people, and speakers. One of the types of signals that has seen increased studies and that can be used as input for these systems is surface electromyography (sEMG). This work presents the recognition of a set of alphabet gestures from Brazilian Sign Language (Libras) using sEMG acquired from an armband. Only sEMG signals were used as input. Signals from 12 subjects were acquired using a MyoTM armband for the 26 signs of the Libras alphabet. Additionally, as the sEMG has several signal processing parameters, the influence of segmentation, feature extraction, and classification was considered at each step of the pattern recognition. In segmentation, window length and the presence of four levels of overlap rates were analyzed, as well as the contribution of each feature, the literature feature sets, and new feature sets proposed for different classifiers. We found that the overlap rate had a high influence on this task. Accuracies in the order of 99% were achieved for the following factors: segments of 1.75 s with a 12.5% overlap rate; the proposed set of four features; and random forest (RF) classifiers.