Motion estimation of elbow joint from sEMG using continuous wavelet transform and back propagation neural networks

Continuous Motion Intention Prediction Using sEMG for Upper-Limb Rehabilitation: A Systematic Review of Model-Based and Model-Free Approaches

Upper limb functional impairments persisting after stroke significantly affect patients' quality of life. Precise adjustment of robotic assistance levels based on patients' motion intentions using sEMG signals is crucial for active rehabilitation. This paper systematically reviews studies on continuous prediction of upper limb single joints and multi-joint combinations motion intention using Model-Based (MB) and Model-Free (MF) approaches over the past decade, based on 186 relevant studies screened from six major electronic databases. The findings indicate ongoing challenges in terms of subject composition, algorithm robustness and generalization, and algorithm feasibility for practical applications. Moreover, it suggests integrating the strengths of both MB and MF approaches to improve existing algorithms. Therefore, future research should further explore personalized MB-MF combination methods incorporating deep learning, attention mechanisms, muscle synergy features, motor unit features, and closed-loop feedback to achieve precise, real-time, and long-duration prediction of multi-joint complex movements, while further refining the transfer learning strategy for rapid algorithm deployment across days and subjects. Overall, this review summarizes the current research status, significant findings, and challenges, aiming to inspire future research on predicting upper limb motion intentions based on sEMG.

A Hand Gesture Recognition Strategy Based on Virtual-Dimension Increase of EMG

The electromyography(EMG) signal is the biocurrent associated with muscle contraction and can be used as the input signal to a myoelectric intelligent bionic hand to control different gestures of the hand. Increasing the number of myoelectric-signal channels can yield richer information of motion intention and improve the accuracy of gesture recognition. However, as the number of acquisition channels increases, its effect on the improvement of the accuracy of gesture recognition gradually diminishes, resulting in the improvement of the control effect reaching a plateau. To address these problems, this paper presents a proposed method to improve gesture recognition accuracy by virtually increasing the number of EMG signal channels. This method is able to improve the recognition accuracy of various gestures by virtually increasing the number of EMG signal channels and enriching the motion intention information extracted from data collected from a certain number of physical channels, ultimately providing a solution to the issue of the recognition accuracy plateau caused by saturation of information from physical recordings. Meanwhile, based on the idea of the filtered feature selection method, a quantitative measure of sample sets (separability of feature vectors [SFV]) derived from the divergence and correlation of the extracted features is introduced. The SFV value can predict the classification effect before performing the classification, and the effectiveness of the virtual-dimension increase strategy is verified from the perspective of feature set differentiability change. Compared to the statistical motion intention recognition success rate, SFV is a more representative and faster measure of classification effectiveness and is also suitable for small sample sets.

A membership-function-based broad learning system for human-robot interaction force estimation under drawing task

Estimating interaction force is of great significance in the field of human-robot interaction (HRI) thanks to its guarantee of interaction safety. To this end, this paper proposes a novel estimation method by leveraging broad learning system (BLS) and human surface electromyography (sEMG) signals. Since the previous sEMG may also contain valuable information of human muscle force, it would cause the estimation to be incomplete and abate the estimation accuracy in the case of neglecting the previous sEMG. To remedy this thorn, a new linear membership function is first developed to calculate contributions of sEMG at different sampling times in the proposed method. Subsequently, the contribution values calculated by the membership function are integrated with features of sEMG to be considered as the input layer of BLS. For extensive studies, five different features extracted from sEMG signals and their combination are explored to estimate the interaction force by the proposed method. Lastly, the performance of the proposed method is compared with those of three well-known methods through experimental test regarding the drawing task. The experimental results confirm that combining the time domain (TD) with frequency domain (FD) features of sEMG can enhance the estimation quality. Moreover, the proposed method outperforms its contenders with respect to estimation accuracy.

Elbow Joint Stiffness Functional Scales Based on Hill's Muscle Model and Genetic Optimization

The ultimate goal of rehabilitation engineering is to provide objective assessment tools for the level of injury and/or the degree of neurorehabilitation recovery based on a combination of different sensing technologies that enable the monitoring of relevant measurable variables, as well as the assessment of non-measurable variables (such as muscle effort/force and joint mechanical stiffness). This paper aims to present a feasibility study for a general assessment methodology for subject-specific non-measurable elbow model parameter prediction and elbow joint stiffness estimation. Ten participants without sensorimotor disorders performed a modified "Reach and retrieve" task of the Wolf Motor Function Test while electromyography (EMG) data of an antagonistic muscle pair (the triceps brachii long head and biceps brachii long head muscle) and elbow angle were simultaneously acquired. A complete list of the Hill's muscle model and passive joint structure model parameters was generated using a genetic algorithm (GA) on the acquired training dataset with a maximum deviation of 6.1% of the full elbow angle range values during the modified task 8 of the Wolf Motor Function Test, and it was also verified using two experimental test scenarios (a task tempo variation scenario and a load variation scenario with a maximum deviation of 8.1%). The recursive least square (RLS) algorithm was used to estimate elbow joint stiffness (Stiffness) based on the estimated joint torque and the estimated elbow angle. Finally, novel Stiffness scales (general patterns) for upper limb functional assessment in the two performed test scenarios were proposed. The stiffness scales showed an exponentially increasing trend with increasing movement tempo, as well as with increasing weights. The obtained general Stiffness patterns from the group of participants without sensorimotor disorders could significantly contribute to the further monitoring of motor recovery in patients with sensorimotor disorders.

A noise-suppressing neural network approach for upper limb human-machine interactive control based on sEMG signals

The use of upper limb rehabilitation robots to assist the affected limbs for active rehabilitation training is an inevitable trend in the field of rehabilitation medicine. In particular, the active motion intention-based control of the upper limb rehabilitation robots to assist subjects in rehabilitation training is a hot research topic in human-computer interaction control. Therefore, improving the accuracy of active motion intention recognition is the premise of the human-machine interaction controller design. Furthermore, there are external disturbances (bounded/unbounded disturbances) during rehabilitation training, which seriously threaten the safety of subjects. Thereby, eliminating external disturbances (especially unbounded disturbances) is the difficulty and key to the human-machine interaction control of the upper limb rehabilitation robots. In response to these problems, based on the surface electromyogram signal of the human upper limb, this paper proposes a fuzzy neural network active motion intention recognition method to explore the internal connection between the surface electromyogram signal of the human upper limb and active motion intention, and improve the real-time and accuracy of recognition. Based on this, two types of human-machine interaction controllers, which can be called as zeroing neural network controller and noise-suppressing zeroing neural network controller are designed to establish a safe and comfortable training environment to avoid secondary damage to the affected limb. Numerical experiments verify the feasibility and effectiveness of the proposed theories and methods.