Fusion Learning for sEMG Recognition of Multiple Upper-Limb Rehabilitation Movements

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.

Research Hotspots of the Rehabilitation Medicine Use of sEMG in Recent 12 Years: A Bibliometric Analysis

Objective

Surface electromyography (sEMG) has been widely applied to rehabilitation medicine. However, the bibliometric analysis of the rehabilitation medicine use of sEMG is vastly unknown. Therefore, this research aimed to investigate the current trends of the rehabilitation medicine use of sEMG in the recent 12 years by using CiteSpace (5.8).

Methods

Literature relating to rehabilitation medicine use of sEMG from 2010 to 2021 was retrieved from the Web of Science. CiteSpace analyzed country, institution, cited journals, authors, cited references and keywords. An analysis of counts and centrality was used to reveal publication outputs, countries, institutions, core journals, active authors, foundation references, hot topics and frontiers.

Results

A total of 1949 publications were retrieved from 2010 to 2021. The total number of publications continually increased over the past 12 years, and the most active countries, institutions, journals and authors in rehabilitation medicine use of sEMG were identified. The most productive country and institution in this field were America (484) and the University of Sao Paulo (36). Andersen LL (28) was the most prolific author, and Dario Farina ranked first among the cited authors. Besides, there were three main frontiers in keywords for sEMG research, including “activation”, “exercise”, and “strength”.

Conclusion

The findings from this bibliometric study provide the current status and trends in clinical research of rehabilitation medicine use of sEMG over the past ten years, which may help researchers identify hot topics and explore new directions for future research in this field.

Recognition of Upper Limb Action Intention Based on IMU

Using motion information of the upper limb to control the prosthetic hand has become a hotspot of current research. The operation of the prosthetic hand must also be coordinated with the user's intention. Therefore, identifying action intention of the upper limb based on motion information of the upper limb is key to controlling the prosthetic hand. Since a wearable inertial sensor bears the advantages of small size, low cost, and little external environment interference, we employ an inertial sensor to collect angle and angular velocity data during movement of the upper limb. Aiming at the action classification for putting on socks, putting on shoes and tying shoelaces, this paper proposes a recognition model based on the Dynamic Time Warping (DTW) algorithm of the motion unit. Based on whether the upper limb is moving, the complete motion data are divided into several motion units. Considering the delay associated with controlling the prosthetic hand, this paper only performs feature extraction on the first motion unit and the second motion unit, and recognizes action on different classifiers. The experimental results reveal that the DTW algorithm based on motion unit bears a higher recognition rate and lower running time. The recognition rate reaches as high as 99.46%, and the average running time measures 8.027 ms. In order to enable the prosthetic hand to understand the grasping intention of the upper limb, this paper proposes a Generalized Regression Neural Network (GRNN) model based on 10-fold cross-validation. The motion state of the upper limb is subdivided, and the static state is used as the sign of controlling the prosthetic hand. This paper applies a 10-fold cross-validation method to train the neural network model to find the optimal smoothing parameter. In addition, the recognition performance of different neural networks is compared. The experimental results show that the GRNN model based on 10-fold cross-validation exhibits a high accuracy rate, capable of reaching 98.28%. Finally, the two algorithms proposed in this paper are implemented in an experiment of using the prosthetic hand to reproduce an action, and the feasibility and practicability of the algorithm are verified by experiment.