Review of sEMG for Exoskeleton Robots: Motion Intention Recognition Techniques and Applications

The global aging trend is becoming increasingly severe, and the demand for life assistance and medical rehabilitation for frail and disabled elderly people is growing. As the best solution for assisting limb movement, guiding limb rehabilitation, and enhancing limb strength, exoskeleton robots are becoming the focus of attention from all walks of life. This paper reviews the progress of research on upper limb exoskeleton robots, sEMG technology, and intention recognition technology. It analyzes the literature using keyword clustering analysis and comprehensively discusses the application of sEMG technology, deep learning methods, and machine learning methods in the process of human movement intention recognition by exoskeleton robots. It is proposed that the focus of current research is to find algorithms with strong adaptability and high classification accuracy. Finally, traditional machine learning and deep learning algorithms are discussed, and future research directions are proposed, such as using a deep learning algorithm based on multi-information fusion to fuse EEG signals, electromyographic signals, and basic reference signals. A model with stronger generalization ability is obtained after training, thereby improving the accuracy of human movement intention recognition based on sEMG technology, which provides important support for the realization of human-machine fusion-embodied intelligence of exoskeleton robots.

sEMG-Based Gesture Recognition via Multi-Feature Fusion Network

The sparse surface electromyography-based gesture recognition suffers from the problems of feature information not richness and poor generalization to small sample data. Therefore, a multi-feature fusion network (MFF-Net) model is proposed in this paper. This network incorporates long short-term memory (LSTM) and the attention mechanism into the model, and three sub-networks are constructed for enhancement of features in the time, frequency and spatial domains, respectively. The introduced attention mechanism enhances useful features and weakens useless ones. Then, the processed features are spliced and stacked, which strengthens the information between time and channel to enrich features in sparse sEMG, improved model performance for feature processing. To further validate that the proposed model is effective in improving gesture recognition accuracy. We selected 18 gesture recognition tasks from the NinaPro DB3 and DB7 datasets for experimental evaluation. Among them, ablation experiments were conducted on intact subjects data in DB7. The experimental results show that the proposed model reaches the current optimal in gesture recognition, with 92.47% classification accuracy. Moreover, the model can be transferred to gesture recognition for small sample amputees data, which is also effective in solving insufficient data problem. Two amputees (in DB7) recognition rate have significantly improved from 60.35% to 84.93%, while eleven amputees (in DB3) recognition rate have significantly improved from 71.84% to 82.00%. It is demonstrated the applicability and generalization of the proposed model transfer learning to the amputees gesture recognition task.

Deep Learning Based Post-stroke Myoelectric Gesture Recognition: From Feature Construction to Network Design

Recently, robot-assisted rehabilitation has emerged as a promising solution to increase the training intensity of stroke patients while reducing workload on therapists, whilst surface electromyography (sEMG) is expected to serve as a viable control source. In this paper, we delve into the potential of deep learning (DL) for post-stroke hand gesture recognition by collecting the sEMG signals of eight chronic stroke subjects, focusing on three primary aspects: feature domains of sEMG (time, frequency, and wavelet), data structures (one or two-dimensional images), and neural network architectures (CNN, CNN-LSTM, and CNN-LSTM-Attention). A total of 18 DL models were comprehensively evaluated in both intra-subject testing and inter-subject transfer learning tasks, with two post-processing algorithms (Model Voting and Bayesian Fusion) analysed subsequently. Experiment results infer that for intra-subject testing, the average accuracy of CNN-LSTM using two-dimensional frequency features is the highest, reaching 72.95%. For inter-subject transfer learning, the average accuracy of CNN-LSTM-Attention using one-dimensional frequency features is the highest, reaching 68.38%. Through these two experiments, it was found that frequency features had significant advantages over other features in gesture recognition after stroke. Moreover, the post-processing algorithm can further improve the recognition accuracy, and the recognition effect can be increased by 2.03% through the model voting algorithm.

Big data in myoelectric control: large multi-user models enable robust zero-shot EMG-based discrete gesture recognition

Myoelectric control, the use of electromyogram (EMG) signals generated during muscle contractions to control a system or device, is a promising input, enabling always-available control for emerging ubiquitous computing applications. However, its widespread use has historically been limited by the need for user-specific machine learning models because of behavioural and physiological differences between users. Leveraging the publicly available 612-user EMG-EPN612 dataset, this work dispels this notion, showing that true zero-shot cross-user myoelectric control is achievable without user-specific training. By taking a discrete approach to classification (i.e., recognizing the entire dynamic gesture as a single event), a classification accuracy of 93.0% for six gestures was achieved on a set of 306 unseen users, showing that big data approaches can enable robust cross-user myoelectric control. By organizing the results into a series of mini-studies, this work provides an in-depth analysis of discrete cross-user models to answer unknown questions and uncover new research directions. In particular, this work explores the number of participants required to build cross-user models, the impact of transfer learning for fine-tuning these models, and the effects of under-represented end-user demographics in the training data, among other issues. Additionally, in order to further evaluate the performance of the developed cross-user models, a completely new dataset was created (using the same recording device) that includes known covariate factors such as cross-day use and limb-position variability. The results show that the large data models can effectively generalize to new datasets and mitigate the impact of common confounding factors that have historically limited the adoption of EMG-based inputs.

Authentication, access, and monitoring system for critical areas with the use of artificial intelligence integrated into perimeter security in a data center

Perimeter security in data centers helps protect systems and the data they store by preventing unauthorized access and protecting critical resources from potential threats. According to the report of the information security company SonicWall, in 2021, there was a 66% increase in the number of ransomware attacks. In addition, the message from the same company indicates that the total number of cyber threats detected in 2021 increased by 24% compared to 2019. Among these attacks, the infrastructure of data centers was compromised; for this reason, organizations include elements Physical such as security cameras, movement detection systems, authentication systems, etc., as an additional measure that contributes to perimeter security. This work proposes using artificial intelligence in the perimeter security of data centers. It allows the automation and optimization of security processes, which translates into greater efficiency and reliability in the operations that prevent intrusions through authentication, permit verification, and monitoring critical areas. It is crucial to ensure that AI-based perimeter security systems are designed to protect and respect user privacy. In addition, it is essential to regularly monitor the effectiveness and integrity of these systems to ensure that they function correctly and meet security standards.

Intramuscular EMG feature extraction and evaluation at different arm positions and hand postures based on a statistical criterion method

Prostheses control using electromyography signals have shown promising aspects in various fields including rehabilitation sciences and assistive technology controlled devices. Pattern recognition and machine learning methods have been observed to play a significant role in evaluating features and classifying different limb motions for enhanced prosthetic executions. This paper proposes feature extraction and evaluation method using intramuscular electromyography (iEMG) signals at different arm positions and hand postures based on the RES Index value statistical criterion method. Sixteen-time domain features were selected for the study at two main circumstances; fixed arm position (FAP) and fixed hand posture (FHP). Eight healthy male participants (30.62 ± 3.87 years) were asked to execute five motion classes including hand grip, hand open, rest, hand extension, and hand flexion at four different arm positions that comprise of 0°, 45°, 90°, and 135°. The classification process is accomplished via the application of the k-nearest neighbor (KNN) classifier. Then RES index was calculated to investigate the optimal features based on the proposed statistical criterion method. From the RES Index, we concluded that Variance (VAR) is the best feature while WAMP, Zero Crossing (ZC), and Slope Sign Change (SSC) are the worst ones in FAP conditions. On the contrary, we concluded that Average Amplitude Change (AAC) is the best feature while WAMP and Simple Square Integral (SSI) resulted in least RES Index values for FHP conditions. The proposed study has possible iEMG based applications such as assistive control devices, robotics. Also, working with the frequency domain features encapsulates the future scope of the study.

A novel SSD fault detection method using GRU-based Sparse Auto-Encoder for dimensionality reduction

In recent years, with the development of flash memory technology, storage systems in large data centers are typically built upon thousands or even millions of solid-state drives (SSDs). Therefore, the failure of SSDs is inevitable. An SSD failure may cause unrecoverable data loss or unavailable system service, resulting in catastrophic results. Active fault detection technologies are able to detect device problems in advance, so it is gaining popularity. Recent trends have turned toward applying AI algorithms based on SSD SMART data for fault detection. However, SMART data of new SSDs contains a large number of features, and the high dimension of data features results in poor accuracy of AI algorithms for fault detection. To tackle the above problems, we improve the structure of traditional Auto-Encoder (AE) based on GRU and propose an SSD fault detection method – GAL based on dimensionality reduction with Gated Recurrent Unit (GRU) sparse autoencoder (GRUAE) by combining the temporal characteristics of SSD SMART data. The proposed method trains the GRUAE model with SSD SMART data firstly, and then adopts the encoder of GRUAE model as the dimensionality reduction tool to reduce the original high-dimensional SSD SMART data, aiming at reducing the influence of noise features in original SSD SAMRT data and highlight the features more relevant to data characteristics to improve the accuracy of fault detection. Finally, LSTM is adopted for fault detection with low-dimensional SSD SMART data. Experimental results on real SSD dataset from Alibaba show that the fault detection accuracy of various AI algorithms can be improved by varying degrees after dimensionality reduction with the proposed method, and GAL performs best among all methods.

Feature Fusion-Based Improved Capsule Network for sEMG Signal Recognition

This paper proposes a feature fusion-based improved capsule network (FFiCAPS) to improve the performance of surface electromyogram (sEMG) signal recognition with the purpose of distinguishing hand gestures. Current deep learning models, especially convolution neural networks (CNNs), only take into account the existence of certain features and ignore the correlation among features. To overcome this problem, FFiCAPS adopts the capsule network with a feature fusion method. In order to provide rich information, sEMG signal information and feature data are incorporated together to form new features as input. Improvements made on capsule network are multilayer convolution layer and e-Squash function. The former aggregates feature maps learned by different layers and kernel sizes to extract information in a multiscale and multiangle manner, while the latter grows faster at later stages to strengthen the sensitivity of this model to capsule length changes. Finally, simulation experiments show that the proposed method exceeds other eight methods in overall accuracy under the condition of electrode displacement (86.58%) and among subjects (82.12%), with a notable improvement in recognizing hand open and radial flexion, respectively.

Control of Newly-Designed Wearable Robotic Hand Exoskeleton Based on Surface Electromyographic Signals

The human hand plays a role in a variety of daily activities. This intricate instrument is vulnerable to trauma or neuromuscular disorders. Wearable robotic exoskeletons are an advanced technology with the potential to remarkably promote the recovery of hand function. However, the still face persistent challenges in mechanical and functional integration, with real-time control of the multiactuators in accordance with the motion intentions of the user being a particular sticking point. In this study, we demonstrated a newly-designed wearable robotic hand exoskeleton with multijoints, more degrees of freedom (DOFs), and a larger range of motion (ROM). The exoskeleton hand comprises six linear actuators (two for the thumb and the other four for the fingers) and can realize both independent movements of each digit and coordinative movement involving multiple fingers for grasp and pinch. The kinematic parameters of the hand exoskeleton were analyzed by a motion capture system. The exoskeleton showed higher ROM of the proximal interphalangeal and distal interphalangeal joints compared with the other exoskeletons. Five classifiers including support vector machine (SVM), K-near neighbor (KNN), decision tree (DT), multilayer perceptron (MLP), and multichannel convolutional neural networks (multichannel CNN) were compared for the offline classification. The SVM and KNN had a higher accuracy than the others, reaching up to 99%. For the online classification, three out of the five subjects showed an accuracy of about 80%, and one subject showed an accuracy over 90%. These results suggest that the new wearable exoskeleton could facilitate hand rehabilitation for a larger ROM and higher dexterity and could be controlled according to the motion intention of the subjects.

The Study of Influence of Sound on Visual ERP-Based Brain Computer Interface

The performance of the event-related potential (ERP)-based brain–computer interface (BCI) declines when applying it into the real environment, which limits the generality of the BCI. The sound is a common noise in daily life, and whether it has influence on this decline is unknown. This study designs a visual-auditory BCI task that requires the subject to focus on the visual interface to output commands and simultaneously count number according to an auditory story. The story is played at three speeds to cause different workloads. Data collected under the same or different workloads are used to train and test classifiers. The results show that when the speed of playing the story increases, the amplitudes of P300 and N200 potentials decrease by 0.86 μV (p = 0.0239) and 0.69 μV (p = 0.0158) in occipital-parietal area, leading to a 5.95% decline (p = 0.0101) of accuracy and 9.53 bits/min decline (p = 0.0416) of information transfer rate. The classifier that is trained by the high workload data achieves higher accuracy than the one trained by the low workload if using the high workload data to test the performance. The result indicates that the sound could affect the visual ERP-BCI by increasing the workload. The large similarity of the training data and testing data is as important as the amplitudes of the ERP on obtaining high performance, which gives us an insight on how make to the ERP-BCI generalized.