Finger motion recognition robust to diverse arm postures using EMG and accelerometer

Rhee, Kiwon; Shin, Hyun-Chool

doi:10.1109/icoin.2018.8343237

Cited by 1 publication

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…26 In 2019, Kiwon and Hyun-Chool established a four-channel information fusion model based on an accelerometer and electromyography (EMG) for EMG-based finger and arm movements, compensated for the interference caused by the acceleration signal by fitting the gravity model, and used the quantized wavelength algorithm combined with the nearestneighbor method to establish an action classification model, with an experimental average accuracy of 85.7%, reducing the effect of different arm movements on EMG signal interference. 27 Wang et al proposed an adaptive neural control strategy by considering a quantization control approach, which is able to analyze the stability in time and eliminate the quantization error of a stochastic nonlinear system with finite time. 28 Ma et al established a sitting posture recognition system based on triaxial accelerometers, transformed the acceleration data into feature vectors for component analysis, and used SVM and K-means clustering to classify sitting postures, and experimentally demonstrated the superiority of the SVM algorithm on sitting posture classification.…”

Section: Sensor-based Gesture Recognitionmentioning

confidence: 99%

A fully connected deep learning approach to upper limb gesture recognition in a secure FES rehabilitation environment

Liu

Jiang

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

Stroke is one of the leading causes of death and disability in the world. The rehabilitation of Patients' limb functions has great medical value, for example, the therapy of functional electrical stimulation (FES) systems, but suffers from effective rehabilitation evaluation. In this paper, six gestures of upper limb rehabilitation were monitored and collected using microelectromechanical systems sensors, where data stability was guaranteed using data preprocessing methods, that is, deweighting, interpolation, and feature extraction. A fully connected neural network has been proposed investigating the effects of different hidden layers, and determining its activation functions and optimizers. Experiments have depicted that a three‐hidden‐layer model with a softmax function and an adaptive gradient descent optimizer can reach an average gesture recognition rate of 97.19%. A stop mechanism has been used via recognition of dangerous gesture to ensure the safety of the system, and the lightweight cryptography has been used via hash to ensure the security of the system. Comparison to the classification models, for example, k‐nearest neighbor, logistic regression, and other random gradient descent algorithms, was conducted to verify the outperformance in recognition of upper limb gesture data. This study also provides an approach to creating health profiles based on large‐scale rehabilitation data and therefore consequent diagnosis of the effects of FES rehabilitation.

show abstract

Section: Sensor-based Gesture Recognitionmentioning

confidence: 99%