PaWFE: Fast Signal Feature Extraction Using Parallel Time Windows

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%.

ViT-HGR: Vision Transformer-based Hand Gesture Recognition from High Density Surface EMG Signals

Recently, there has been a surge of significant interest on application of Deep Learning (DL) models to autonomously perform hand gesture recognition using surface Electromyogram (sEMG) signals. Many of the existing DL models are, however, designed to be applied on sparse sEMG signals. Furthermore, due to the complex structure of these models, typically, we are faced with memory constraint issues, require large training times and a large number of training samples, and; there is the need to resort to data augmentation and/or transfer learning. In this paper, for the first time (to the best of our knowledge), we investigate and design a Vision Transformer (ViT) based architecture to perform hand gesture recognition from High Density (HD-sEMG) signals. Intuitively speaking, we capitalize on the recent breakthrough role of the transformer architecture in tackling different com-plex problems together with its potential for employing more input parallelization via its attention mechanism. The proposed Vision Transformer-based Hand Gesture Recognition (ViT-HGR) framework can overcome the aforementioned training time problems and can accurately classify a large number of hand gestures from scratch without any need for data augmentation and/or transfer learning. The efficiency of the proposed ViT-HGR framework is evaluated using a recently-released HD-sEMG dataset consisting of 65 isometric hand gestures. Our experiments with 64-sample (31.25 ms) window size yield average test accuracy of 84.62 ± 3.07%, where only 78,210 learnable parameters are utilized in the model. The compact structure of the proposed ViT-based ViT-HGR framework (i.e., having significantly reduced number of trainable parameters) shows great potentials for its practical application for prosthetic control.

An Exploration of the Optimal Feature-Classifier Combinations for Transradial Prosthesis Control

Within state-of-the-art gesture-based upper-limb myoelectric prosthesis control, gesture recognition commonly relies on the classification of features extracted from electromyographic (EMG) data gathered from the amputee's residual forearm musculature. Despite best efforts in broadly maximizing gesture recognition accuracy, there does not yet exist a feature-classifier combination accepted as best-practice. In turn, this work hypothesizes that no single feature-classifier combination can consistently maximize accuracy across subjects, positing instead that control schemes should be personalized to the individual. To investigate this hypothesis, the study employed the 40-subject, 49-gesture Ninapro Database 2 (DB2) to compare the performance of 7 different historic, more recent, and state-of-the-art feature sets when classified by 5 machine learning algorithms commonly seen within EMG-based pattern recognition literature. The results demonstrate the ability of Linear Discriminant Analysis (LDA) to marginally exceed other more computationally intensive classifiers in terms of mean accuracy, while the feature set which maximized the highest proportion of individuals' accuracies was shown to vary with both classifier choice and gesture count.

Spatio-temporal warping for myoelectric control: an offline, feasibility study

Objective.The efficacy of an adopted feature extraction method directly affects the classification of the electromyographic (EMG) signals in myoelectric control applications. Most methods attempt to extract the dynamics of the multi-channel EMG signals in the time domain and on a channel-by-channel, or at best pairs of channels, basis. However, considering multi-channel information to build a similarity matrix has not been taken into account.Approach.Combining methods of long and short-term memory (LSTM) and dynamic temporal warping, we developed a new feature, called spatio-temporal warping (STW), for myoelectric signals. This method captures the spatio-temporal relationships of multi-channels EMG signals.Main results. Across four online databases, we show that in terms of average classification error and standard deviation values, the STW feature outperforms traditional features by 5%-17%. In comparison to the more recent deep learning models, e.g. convolutional neural networks (CNNs), STW outperformed by 5%-18%. Also, STW showed enhanced performance when compared to the CNN + LSTM model by 2%-14%. All differences were statistically significant with a large effect size.Significance.This feasibility study provides evidence supporting the hypothesis that the STW feature of the EMG signals can enhance the classification accuracy in an explainable way when compared to recent deep learning methods. Future work includes real-time implementation of the method and testing for prosthesis control.

A Data-Driven Investigation on Surface Electromyography Based Clinical Assessment in Chronic Stroke

Background: Surface electromyography (sEMG) based robot-assisted rehabilitation systems have been adopted for chronic stroke survivors to regain upper limb motor function. However, the evaluation of rehabilitation effects during robot-assisted intervention relies on traditional manual assessments. This study aimed to develop a novel sEMG data-driven model for automated assessment. Method: A data-driven model based on a three-layer backpropagation neural network (BPNN) was constructed to map sEMG data to two widely used clinical scales, i.e., the Fugl-Meyer Assessment (FMA) and the Modified Ashworth Scale (MAS). Twenty-nine stroke participants were recruited in a 20-session sEMG-driven robot-assisted upper limb rehabilitation, which consisted of hand reaching and withdrawing tasks. The sEMG signals from four muscles in the paretic upper limbs, i.e., biceps brachii (BIC), triceps brachii (TRI), flexor digitorum (FD), and extensor digitorum (ED), were recorded before and after the intervention. Meanwhile, the corresponding clinical scales of FMA and MAS were measured manually by a blinded assessor. The sEMG features including Mean Absolute Value (MAV), Zero Crossing (ZC), Slope Sign Change (SSC), Root Mean Square (RMS), and Wavelength (WL) were adopted as the inputs to the data-driven model. The mapped clinical scores from the data-driven model were compared with the manual scores by Pearson correlation. Results: The BPNN, with 15 nodes in the hidden layer and sEMG features, i.e., MAV, ZC, SSC, and RMS, as the inputs to the model, was established to achieve the best mapping performance with significant correlations (r > 0.9, P < 0.001), according to the FMA. Significant correlations were also obtained between the mapped and manual FMA subscores, i.e., FMA-wrist/hand and FMA-shoulder/elbow, before and after the intervention (r > 0.9, P < 0.001). Significant correlations (P < 0.001) between the mapped and manual scores of MASs were achieved, with the correlation coefficients r = 0.91 at the fingers, 0.88 at the wrist, and 0.91 at the elbow after the intervention. Conclusion: An sEMG data-driven BPNN model was successfully developed. It could evaluate upper limb motor functions in chronic stroke and have potential application in automated assessment in post-stroke rehabilitation, once validated with large sample sizes. Clinical Trial Registration: www.ClinicalTrials.gov, identifier: NCT02117089.

Intelligent body behavior feature extraction based on convolution neural network in patients with craniocerebral injury

Patients with craniocerebral injury are in serious condition and inconvenient to take care of. This paper proposes a method of extracting the patient's body behavior feature based on convolution neural network, in order to reduce nursing workload and save hospital costs. The algorithm adopts double network model design, including the patient detection network model and the patient's body behavior feature extraction model. The algorithm is applied to the patient's body behavior detection system, so as to realize the recognition and monitoring of patients and improve the level of intelligent medical care for craniocerebral injury. Finally, the open source framework platform is used to test the patient behavior detection system. The experimental results show that the larger the test data set is, the higher the accuracy of patient body behavior feature extraction is. The average recognition rate of patient body behavior category is 97.8%, which verifies the effectiveness and correctness of the system. The application of convolution neural network connects image recognition with intelligent medical nursing, which provides reference and experience for intelligent medical nursing of patients with craniocerebral injury.