Robust Continuous Hand Motion Recognition Using Wearable Array Myoelectric Sensor

Abstract

With the advantages of comfortable wearing and outdoor usage, the myoelectric gesture recognition techniques have gained much attention in the field of human-machine interaction (HMI). The purpose of this study is to optimize model structure and transfer generalized features to improve the robustness of myoelectric hand motion decoding. We derived the hand motion recognition framework from the muscle synergy theory, which is formulated as a temporal convolutional (TC) model of array sEMG signals, then a hierarchical myoelectric decoding model was proposed to predict simultaneous and continuous hand motion. The model was trained by the methods of unsupervised low-level feature learning and automated data labeling to minimize training supervision. Extensive experiments on the public sEMG database (17 subjects in Biopatrec) show that the TC model can extract muscle synergy features with higher fidelity ( =0.85±0.23) than the traditional instantaneous mixture model, the results of online test demonstrate robust myoelectric decoding on multiple simultaneous and continuous hand motions. More importantly, the analysis of weights visualization shows that the low-level feature representation layer of TC model can be migrated across the individuals, which provides a transferrable feature extraction layer for generalized hand motion decoding.

Intelligent Correction Method of Shooting Action Based on Computer Vision

“…With the formation of clear action image and the establishment of correct action concept, through visual and auditory information feedback, students gradually establish the proprioception of muscle activities in imitation and trial, and the excitation and inhibition of nerve center are gradually improved and accurate in time and space, initially forming the action skill of in situ one-handed shoulder shooting, but at this time, the action is not coordinated and coherent enough, and it is easy to be disturbed by new differences or strong stimuli [13][14][15][16][17][18]. erefore, in the differentiation stage, we should also pay attention to avoid the generation and correction of nonstandard actions.…”

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

“…Furthermore, the study also conducted experiments based on static isometric contraction under different intensities, compound synergistic movements, and mirrored movements, as well as simultaneous predictions of joint kinematics and dynamics. Additionally, over one-third of these studies utilized the public NinaPro dataset, along with other public datasets (e.g., putEMG-Force [11], Biopatrec [12], and KIN-MUS UJI [13]) for the development of prediction algorithms. Fig.…”

“…However, its performance was still limited by sEMG sequence lengths. The Temporal Convolution (TC) model in [12] utilized 1D-CNN and PCA for advanced feature extraction, AE for unsupervised learning of MS features, and finally RNN for real-time mapping between MS and motion intention. This method outperformed instantaneous mixture models in MS reconstruction and predictive performance and showed generalizability to untrained new data.…”

Hand Gestures Recognition for Human-Machine Interfaces: A Low-Power Bio-Inspired Armband

“…All the reported works developed their wearable device, but only [7], [16], [29], [40] managed to fit their learner into an embedded prototype. The armband developed in [9], for example, is reported to be designed to support the embedding of ML algorithms, but all the predictions are still evaluated 1 Current Absorption, 2 Battery Capacity, 3 Operating Time, 4 Discrete Wavelet Transform, 5 Linear Discriminant Analysis Acquisition window 6 Gated Recurrent Unit, 7 Considering the most comfortable use-case with idle norm equal to 5 Prediction on a computer. Similarly, [3], [23] use the Myo armband as acquisition device, sending data via wireless communication to an elaboration unit, and [33] still involves electrodes matrices wired to a data collection unit, which sends the processed information to a computer for the further prediction.…”